ALBERT

Description: Traditional research methods in software defect prediction use part of the data in the same project to train the defect prediction model and predict the defect label of the remaining part of the data. However, in the practical realm of software development, the software project that needs to be predicted is generally a brand new software project, and there is not enough labeled data to build a defect prediction model; therefore, traditional methods are no longer applicable. Cross-project defect prediction uses the labeled data of the same type of project similar to the target project to build the defect prediction model, so as to solve the problem of data loss in traditional methods. However, the difference in data distribution between the same type of project and the target project reduces the performance of defect prediction. To solve this problem, this paper proposes a cross-project defect prediction method based on manifold feature transformation. This method transforms the original feature space of the project into a manifold space, then reduces the difference in data distribution of the transformed source project and the transformed target project in the manifold space, and finally uses the transformed source project to train a naive Bayes prediction model with better performance. A comparative experiment was carried out using the Relink dataset and the AEEEM dataset. The experimental results show that compared with the benchmark method and several cross-project defect prediction methods, the proposed method effectively reduces the difference in data distribution between the source project and the target project, and obtains a higher F1 value, which is an indicator commonly used to measure the performance of the two-class model.

Description: During transmission of digital images, secret messages can be embedded using data hiding techniques. Such techniques can transfer private secrets without drawing the attention of eavesdroppers. To reduce the amount of transmitted data, image compression methods are widely applied. Hiding secret data in compressed images is a hot issue recently. In this paper, we apply the de-clustering concept and the indicator-free search-order coding (IFSOC) technique to hide information into vector quantization (VQ) compressed images. Experimental results show that the proposed two-layer reversible data hiding scheme for IFSOC-encoded VQ index table can hide a large amount of secret data among state-of-the-art methods with a relatively lower bit rate and high security.

Description: Using automotive smartphone applications (apps) provided by car manufacturers may offer numerous advantages to the vehicle owner, including improved safety, fuel efficiency, anytime monitoring of vehicle data, and timely over-the-air delivery of software updates. On the other hand, the continuous tracking of the vehicle data by such apps may also pose a risk to the car owner, if, say, sensitive pieces of information are leaked to third parties or the app is vulnerable to attacks. This work contributes the first to our knowledge full-fledged security assessment of all the official single-vehicle management apps offered by major car manufacturers who operate in Europe. The apps are scrutinised statically with the purpose of not only identifying surfeits, say, in terms of the permissions requested, but also from a vulnerability assessment viewpoint. On top of that, we run each app to identify possible weak security practices in the owner-to-app registration process. The results reveal a multitude of issues, ranging from an over-claim of sensitive permissions and the use of possibly privacy-invasive API calls, to numerous potentially exploitable CWE and CVE-identified weaknesses and vulnerabilities, the, in some cases, excessive employment of third-party trackers, and a number of other flaws related to the use of third-party software libraries, unsanitised input, and weak user password policies, to mention just a few.

Description: Research on flexible unit systems (FUS) with the context of descriptive, predictive, and prescriptive analysis have remarkably progressed in recent times, being now reinforced in the current Industry 4.0 era with the increased focus on integration of distributed and digitalized systems. In the existing literature, most of the work focused on the individual contributions of the above mentioned three analyses. Moreover, the current literature is unclear with respect to the integration of degradation and upgradation models for FUS. In this paper, a systematic literature review on degradation, residual life distribution, workload adjustment strategy, upgradation, and predictive maintenance as major performance measures to investigate the performance of the FUS has been considered. In order to identify the key issues and research gaps in the existing literature, the 59 most relevant papers from 2009 to 2020 have been sorted and analyzed. Finally, we identify promising research opportunities that could expand the scope and depth of FUS.

Description: Community detection plays an essential role in understanding network topology and mining underlying information. A bipartite network is a complex network with more important authenticity and applicability than a one-mode network in the real world. There are many communities in the network that present natural overlapping structures in the real world. However, most of the research focuses on detecting non-overlapping community structures in the bipartite network, and the resolution of the existing evaluation function for the community structure’s merits are limited. So, we propose a novel function for community detection and evaluation of the bipartite network, called community density D. And based on community density, a bipartite network community detection algorithm DSNE (Density Sub-community Node-pair Extraction) is proposed, which is effective for overlapping community detection from a micro point of view. The experiments based on artificially-generated networks and real-world networks show that the DSNE algorithm is superior to some existing excellent algorithms; in comparison, the community density (D) is better than the bipartite network’s modularity.

Description: Existing product anti-counterfeiting and traceability solutions across today’s internationally spanning supply chain networks are indeed developed and implemented with centralized system architecture relying on centralized authorities or intermediaries. Vulnerabilities of centralized product anti-counterfeiting solutions could possibly lead to system failure or susceptibility of malicious modifications performed on product records or various potential attacks to the system components by dishonest participant nodes traversing along the supply chain. Blockchain technology has progressed from simply being a use case of immutable ledger for cryptocurrency transactions, to a programmable interactive environment of developing decentralized and reliable applications addressing different use cases globally. Key areas of decentralization, fundamental system requirements, and feasible mechanisms of developing decentralized product anti-counterfeiting and traceability ecosystems utilizing blockchain technology are identified in this research, via a series of security analyses performed against solutions currently implemented in supply chain industry with centralized architecture. The decentralized solution will be a secure and immutable scientific data provenance tracking and management platform where provenance records, providing compelling properties on data integrity of luxurious goods, are recorded and verified automatically across the supply chain.

Description: An interesting research problem in the supply chain industry is evaluating and determining the provenance of physical goods—demonstrating the authenticity of luxury goods such as bottled wine. However, many supply chain systems and networks have been built and implemented with centralized system architecture, relying on centralized authorities or any form of intermediary, and leading to issues such as single-point processing, storage and failure, which could be susceptible to malicious modifications to product records or various potential attacks to system components by dishonest participant nodes traversing along the supply chain. Blockchain technology has evolved from merely being a decentralized, distributed and immutable ledger of cryptocurrency transactions to a programmable interactive environment for building decentralized and reliable applications addressing different use-cases and existing problems in the world. In this research, with a chosen research method of proof-by-demonstration, the Decentralized NFC-Enabled Anti-Counterfeiting System (dNAS) is proposed and developed, decentralizing a legacy anti-counterfeiting system of the supply-chain industry using Blockchain technology to facilitate trustworthy data provenance retrieval, verification and management, as well as strengthening the capability of the product’s anti-counterfeiting and traceability qualities in the wine industry, with the capacity to further extend this to the supply chain industry as a whole. The proposed dNAS utilizes a decentralized blockchain network with a consensus protocol compatible with the concept of enterprise blockchain, programmable smart contracts and a distributed file storage system to develop a secure and immutable scientific-data provenance tracking and management platform on which provenance records, providing compelling properties of the data integrity of luxurious goods, are recorded, verified and validated automatically.

Description: In location-based social networks (LBSNs), exploit several key features of points-of-interest (POIs) and users on precise POI recommendation be significant. In this work, a novel POI recommendation pipeline based on the convolutional neural network named RecPOID is proposed, which can recommend an accurate sequence of top-k POIs and considers only the effect of the most similar pattern friendship rather than all user’s friendship. We use the fuzzy c-mean clustering method to find the similarity. Temporal and spatial features of similar friends are fed to our Deep CNN model. The 10-layer convolutional neural network can predict longitude and latitude and the Id of the next proper locations; after that, based on the shortest time distance from a similar pattern’s friendship, select the smallest distance locations. The proposed structure uses six features, including user’s ID, month, day, hour, minute, and second of visiting time by each user as inputs. RecPOID based on two accessible LBSNs datasets is evaluated. Experimental outcomes illustrate considering most similar friendship could improve the accuracy of recommendations and the proposed RecPOID for POI recommendation outperforms state-of-the-art approaches.

Description: In the upcoming decade and beyond, the Cooperative, Connected and Automated Mobility (CCAM) initiative will play a huge role in increasing road safety, traffic efficiency and comfort of driving in Europe. While several individual vehicular wireless communication technologies exist, there is still a lack of real flexible and modular platforms that can support the need for hybrid communication. In this paper, we propose a novel vehicular communication management framework (CAMINO), which incorporates flexible support for both short-range direct and long-range cellular technologies and offers built-in Cooperative Intelligent Transport Systems’ (C-ITS) services for experimental validation in real-life settings. Moreover, integration with vehicle and infrastructure sensors/actuators and external services is enabled using a Distributed Uniform Streaming (DUST) framework. The framework is implemented and evaluated in the Smart Highway test site for two targeted use cases, proofing the functional operation in realistic environments. The flexibility and the modular architecture of the hybrid CAMINO framework offers valuable research potential in the field of vehicular communications and CCAM services and can enable cross-technology vehicular connectivity.

Description: Social media services make it possible for an increasing number of people to express their opinion publicly. In this context, large amounts of hateful comments are published daily. The PHARM project aims at monitoring and modeling hate speech against refugees and migrants in Greece, Italy, and Spain. In this direction, a web interface for the creation and the query of a multi-source database containing hate speech-related content is implemented and evaluated. The selected sources include Twitter, YouTube, and Facebook comments and posts, as well as comments and articles from a selected list of websites. The interface allows users to search in the existing database, scrape social media using keywords, annotate records through a dedicated platform and contribute new content to the database. Furthermore, the functionality for hate speech detection and sentiment analysis of texts is provided, making use of novel methods and machine learning models. The interface can be accessed online with a graphical user interface compatible with modern internet browsers. For the evaluation of the interface, a multifactor questionnaire was formulated, targeting to record the users’ opinions about the web interface and the corresponding functionality.

Description: Great achievements have been made in pedestrian detection through deep learning. For detectors based on deep learning, making better use of features has become the key to their detection effect. While current pedestrian detectors have made efforts in feature utilization to improve their detection performance, the feature utilization is still inadequate. To solve the problem of inadequate feature utilization, we proposed the Multi-Level Feature Fusion Module (MFFM) and its Multi-Scale Feature Fusion Unit (MFFU) sub-module, which connect feature maps of the same scale and different scales by using horizontal and vertical connections and shortcut structures. All of these connections are accompanied by weights that can be learned; thus, they can be used as adaptive multi-level and multi-scale feature fusion modules to fuse the best features. Then, we built a complete pedestrian detector, the Adaptive Feature Fusion Detector (AFFDet), which is an anchor-free one-stage pedestrian detector that can make full use of features for detection. As a result, compared with other methods, our method has better performance on the challenging Caltech Pedestrian Detection Benchmark (Caltech) and has quite competitive speed. It is the current state-of-the-art one-stage pedestrian detection method.

Description: With the emergence of various types of applications such as delay-sensitive applications, future communication networks are expected to be increasingly complex and dynamic. Network Function Virtualization (NFV) provides the necessary support towards efficient management of such complex networks, by virtualizing network functions and placing them on shared commodity servers. However, one of the critical issues in NFV is the resource allocation for the highly complex services; moreover, this problem is classified as an NP-Hard problem. To solve this problem, our work investigates the potential of Deep Reinforcement Learning (DRL) as a swift yet accurate approach (as compared to integer linear programming) for deploying Virtualized Network Functions (VNFs) under several Quality-of-Service (QoS) constraints such as latency, memory, CPU, and failure recovery requirements. More importantly, the failure recovery requirements are focused on the node-outage problem where outage can be either due to a disaster or unavailability of network topology information (e.g., due to proprietary and ownership issues). In DRL, we adopt a Deep Q-Learning (DQL) based algorithm where the primary network estimates the action-value function Q, as well as the predicted Q, highly causing divergence in Q-value’s updates. This divergence increases for the larger-scale action and state-space causing inconsistency in learning, resulting in an inaccurate output. Thus, to overcome this divergence, our work has adopted a well-known approach, i.e., introducing Target Neural Networks and Experience Replay algorithms in DQL. The constructed model is simulated for two real network topologies—Netrail Topology and BtEurope Topology—with various capacities of the nodes (e.g., CPU core, VNFs per Core), links (e.g., bandwidth and latency), several VNF Forwarding Graph (VNF-FG) complexities, and different degrees of the nodal outage from 0% to 50%. We can conclude from our work that, with the increase in network density or nodal capacity or VNF-FG’s complexity, the model took extremely high computation time to execute the desirable results. Moreover, with the rise in complexity of the VNF-FG, the resources decline much faster. In terms of the nodal outage, our model provided almost 70–90% Service Acceptance Rate (SAR) even with a 50% nodal outage for certain combinations of scenarios.

Description: Most retailers are integrating their practices with modern technologies to enhance the effectiveness of their operations. The adoption of technology aims to enable businesses to accurately meet customer needs and expectations. This study focused on examining the role of mobile application (app) acceptance in shaping customer electronic experience. A mixed method was adopted, in which qualitative data were collected using interviews, and quantitative data were gathered using the questionnaires. The results indicate that mobile app acceptance contributes to a positive customer experience while purchasing products and services from online retailers. Mobile apps are associated with benefits, such as convenience, ease of use, and the ability to access various products and services. With the rapid development in technology, e-commerce retailers should leverage such innovations to meet customer needs.

Description: Numerous middleware application programming interfaces (APIs) and protocols were introduced in the literature in order to facilitate the application development of the Internet of Things (IoT). Such applications are built on reliable or even unreliable protocols that may implement different quality-of-service (QoS) delivery modes. The exploitation of these protocols, APIs and QoS modes, can satisfy QoS requirements in critical IoT applications (e.g., emergency response operations). To study QoS in IoT applications, it is essential to leverage a performance analysis methodology. Queueing-network models offer a modeling and analysis framework that can be adopted for the IoT interactions of QoS representation through either analytical or simulation models. In this paper, various types of queueing models are presented that can be used for the representation of various QoS settings of IoT interactions. In particular, we propose queueing models to represent message-drop probabilities, intermittent mobile connectivity, message availability or validity, the prioritization of important information, and the processing or transmission of messages. Our simulation models demonstrate the significant effect on delivery success rates and response times when QoS settings are varied.

Description: With the application of vehicles to everything (V2X) technologies, drivers can obtain massive traffic information and adjust their car-following behavior according to the information. The macro-characteristics of traffic flow are essentially the overall expression of the micro-behavior of drivers. There are some shortcomings in the previous researches on traffic flow in the V2X environment, which result in difficulties to employ the related models or methods in exploring the characteristics of traffic flow affected by the information of generalized preceding vehicles (GPV). Aiming at this, a simulation framework based on the car-following model and the cellular automata (CA) is proposed in this work, then the traffic flow affected by the information of GPV is simulated and analyzed utilizing this framework. The research results suggest that the traffic flow, which is affected by the information of GPV in the V2X environment, would operate with a higher value of velocity, volume as well as jamming density and can maintain the free flow state with a much higher density of vehicles. The simulation framework constructed in this work can provide a reference for further research on the characteristics of traffic flow affected by various information in the V2X environment.

Description: Simulation has become an indispensable technique for modelling and evaluating the performance of large-scale systems efficiently and at a relatively low cost. ElasticSearch (ES) is one of the most popular open source large-scale distributed data indexing systems worldwide. In this paper, we use the RECAP Discrete Event Simulator (DES) simulator, an extension of CloudSimPlus, to model and evaluate the performance of a real-world cloud-based ES deployment by an Irish small and medium-sized enterprise (SME), Opening.io. Following simulation experiments that explored how much query traffic the existing Opening.io architecture could cater for before performance degradation, a revised architecture was proposed, adding a new virtual machine in order to dissolve the bottleneck. The simulation results suggest that the proposed improved architecture can handle significantly larger query traffic (about 71% more) than the current architecture used by Opening.io. The results also suggest that the RECAP DES simulator is suitable for simulating ES systems and can help companies to understand their infrastructure bottlenecks under various traffic scenarios and inform optimisation and scalability decisions.

Description: Dedicated Short-Range Communication (DSRC) or IEEE 802.11p/OCB (Out of the Context of a Base-station) is widely considered to be a primary technology for Vehicle-to-Vehicle (V2V) communication, and it is aimed toward increasing the safety of users on the road by sharing information between one another. The requirements of DSRC are to maintain real-time communication with low latency and high reliability. In this paper, we investigate how communication can be used to improve stopping distance performance based on fieldwork results. In addition, we assess the impacts of reduced reliability, in terms of distance independent, distance dependent and density-based consecutive packet losses. A model is developed based on empirical measurements results depending on distance, data rate, and traveling speed. With this model, it is shown that cooperative V2V communications can effectively reduce reaction time and increase safety stop distance, and highlight the importance of high reliability. The obtained results can be further used for the design of cooperative V2V-based driving and safety applications.

Description: This paper presents a planning system based on semantic reasoning for a general-purpose service robot, which is aimed at behaving more intelligently in domains that contain incomplete information, under-specified goals, and dynamic changes. First, Two kinds of data are generated by Natural Language Processing module from the speech: (i) action frames and their relationships; (ii) the modifier used to indicate some property or characteristic of a variable in the action frame. Next, the task’s goals are generated from these action frames and modifiers. These goals are represented as AI symbols, combining world state and domain knowledge, which are used to generate plans by an Answer Set Programming solver. Finally, the plan’s actions are executed one by one, and continuous sensing grounds useful information, which makes the robot use contingent knowledge to adapt to dynamic changes and faults. For each action in the plan, the planner gets its preconditions and effects from domain knowledge, so during the execution of the task, the environmental changes, especially those conflict with the actions, not only the action being performed but also the subsequent actions, can be detected and handled as early as possible. A series of case studies are used to evaluate the system and verify its ability to acquire knowledge through dialogue with users, solve problems with the acquired causal knowledge, and plan for complex tasks autonomously in the open world.

Description: Content is a key influencing factor in Web Quality of Experience (QoE) estimation. A web user’s satisfaction can be influenced by how long it takes to render and visualize the visible parts of the web page in the browser. This is referred to as the Above-the-fold (ATF) time. SpeedIndex (SI) has been widely used to estimate perceived web page loading speed of ATF content and a proxy metric for Web QoE estimation. Web application developers have been actively introducing innovative interactive features, such as animated and multimedia content, aiming to capture the users’ attention and improve the functionality and utility of the web applications. However, the literature shows that, for the websites with animated content, the estimated ATF time using the state-of-the-art metrics may not accurately match completed ATF time as perceived by users. This study introduces a new metric, Plausibly Complete Time (PCT), that estimates ATF time for a user’s perception of websites with and without animations. PCT can be integrated with SI and web QoE models. The accuracy of the proposed metric is evaluated based on two publicly available datasets. The proposed metric holds a high positive Spearman’s correlation (rs=0.89) with the Perceived ATF reported by the users for websites with and without animated content. This study demonstrates that using PCT as a KPI in QoE estimation models can improve the robustness of QoE estimation in comparison to using the state-of-the-art ATF time metric. Furthermore, experimental result showed that the estimation of SI using PCT improves the robustness of SI for websites with animated content. The PCT estimation allows web application designers to identify where poor design has significantly increased ATF time and refactor their implementation before it impacts end-user experience.

Description: Blockchain, a distributed ledger technology (DLT), refers to a list of records with consecutive time stamps. This decentralization technology has become a powerful model to establish trust among trustless entities, in a verifiable manner. Motivated by the recent advancement of multi-access edge computing (MEC) and artificial intelligence (AI), blockchain-enabled edge intelligence has become an emerging technology for the Internet of Things (IoT). We review how blockchain-enabled edge intelligence works in the IoT domain, identify the emerging trends, and suggest open issues for further research. To be specific: (1) we first offer some basic knowledge of DLT, MEC, and AI; (2) a comprehensive review of current peer-reviewed literature is given to identify emerging trends in this research area; and (3) we discuss some open issues and research gaps for future investigations. We expect that blockchain-enabled edge intelligence will become an important enabler of future IoT, providing trust and intelligence to satisfy the sophisticated needs of industries and society.

Description: Network slicing is considered a key technology in enabling the underlying 5G mobile network infrastructure to meet diverse service requirements. In this article, we demonstrate how transport network slicing accommodates the various network service requirements of Massive IoT (MIoT), Critical IoT (CIoT), and Mobile Broadband (MBB) applications. Given that most of the research conducted previously to measure 5G network slicing is done through simulations, we utilized SimTalk, an IoT application traffic emulator, to emulate large amounts of realistic traffic patterns in order to study the effects of transport network slicing on IoT and MBB applications. Furthermore, we developed several MIoT, CIoT, and MBB applications that operate sustainably on several campuses and directed both real and emulated traffic into a Programming Protocol-Independent Packet Processors (P4)-based 5G testbed. We then examined the performance in terms of throughput, packet loss, and latency. Our study indicates that applications with different traffic characteristics need different corresponding Committed Information Rate (CIR) ratios. The CIR ratio is the CIR setting for a P4 meter in physical switch hardware over the aggregated data rate of applications of the same type. A low CIR ratio adversely affects the application’s performance because P4 switches will dispatch application packets to the low-priority queue if the packet arrival rate exceeds the CIR setting for the same type of applications. In our testbed, both exemplar MBB applications required a CIR ratio of 140% to achieve, respectively, a near 100% throughput percentage with a 0.0035% loss rate and an approximate 100% throughput percentage with a 0.0017% loss rate. However, the exemplar CIoT and MIoT applications required a CIR ratio of 120% and 100%, respectively, to reach a 100% throughput percentage without any packet loss. With the proper CIR settings for the P4 meters, the proposed transport network slicing mechanism can enforce the committed rates and fulfill the latency and reliability requirements for 5G MIoT, CIoT, and MBB applications in both TCP and UDP.

Description: With the progressive deterioration of cyber threats, collecting cyber threat intelligence (CTI) from open-source threat intelligence publishing platforms (OSTIPs) can help information security personnel grasp public opinions with specific pertinence, handle emergency events, and even confront the advanced persistent threats. However, due to the explosive growth of information shared on multi-type OSTIPs, manually collecting the CTI has had low efficiency. Articles published on the OSTIPs are unstructured, leading to an imperative challenge to automatically gather CTI records only through natural language processing (NLP) methods. To remedy these limitations, this paper proposes an automatic approach to generate the CTI records based on multi-type OSTIPs (GCO), combing the NLP method, machine learning method, and cybersecurity threat intelligence knowledge. The experiment results demonstrate that the proposed GCO outperformed some state-of-the-art approaches on article classification and cybersecurity intelligence details (CSIs) extraction, with accuracy, precision, and recall all over 93%; finally, the generated records in the Neo4j-based CTI database can help reveal malicious threat groups.

Description: Graph variational auto-encoder (GVAE) is a model that combines neural networks and Bayes methods, capable of deeper exploring the influential latent features of graph reconstruction. However, several pieces of research based on GVAE employ a plain prior distribution for latent variables, for instance, standard normal distribution (N(0,1)). Although this kind of simple distribution has the advantage of convenient calculation, it will also make latent variables contain relatively little helpful information. The lack of adequate expression of nodes will inevitably affect the process of generating graphs, which will eventually lead to the discovery of only external relations and the neglect of some complex internal correlations. In this paper, we present a novel prior distribution for GVAE, called Dirichlet process (DP) construction for Student’s t (St) distribution. The DP allows the latent variables to adapt their complexity during learning and then cooperates with heavy-tailed St distribution to approach sufficient node representation. Experimental results show that this method can achieve a relatively better performance against the baselines.

Description: At present, our online activity is almost constant, either producing information or consuming it, both for the social and academic fields. The spaces in which people move and travel every day, innocently divided between the face-to-face and the virtual, affect the way we communicate and perceive ourselves. In this document, a characterization of the academic digital identity of Chilean university students is proposed and an invitation to teachers to redefine learning spaces is made, allowing integrating all those technological tools that the student actually uses. This study was developed within the logic of pragmatism based on mixed methodology, non-experimental design, and a descriptive–quantitative cross-sectional approach. A non-probabilistic sample was made up of 509 students, who participated voluntarily with an online questionnaire. The Stata Version-14 program was used, applying the Mann–Whitney–Wilcoxon and Kruskal–Wallis U tests. To develop characterizations, a conglomerate analysis was performed with a hierarchical dissociative method. In general, Chilean university students are highly truthful on the Internet without making significant differences between face-to-face and digital interactions, with low awareness of their ID, being easily recognizable on the Web. Regarding their educational process, they manage it with analogical/face-to-face mixing formal and informal technological tools to optimize their learning process. These students manifest a hybrid academic digital identity, without gender difference in the deployment of their PLEs, but maintaining stereotypical gender behaviors in the construction of their digital identity on the Web, which shows a human-technological development similar to that of young Asians and Europeans.

Description: The combination of mobile edge computing (MEC) and wireless power transfer (WPT) is recognized as a promising technology to solve the problem of limited battery capacities and insufficient computation capabilities of mobile devices. This technology can transfer energy to users by radio frequency (RF) in wireless powered mobile edge computing. The user converts the harvested energy, stores it in the battery, and utilizes the harvested energy to execute corresponding local computing and offloading tasks. This paper adopts the Frequency Division Multiple Access (FDMA) technique to achieve task offloading from multiple mobile devices to the MEC server simultaneously. Our objective is to study multiuser dynamic joint optimization of computation and wireless resource allocation under multiple time blocks to solve the problem of maximizing residual energy. To this end, we formalize it as a nonconvex problem that jointly optimizes the number of offloaded bits, energy harvesting time, and transmission bandwidth. We adopt convex optimization technology, combine with Karush–Kuhn–Tucker (KKT) conditions, and finally transform the problem into a univariate constrained convex optimization problem. Furthermore, to solve the problem, we propose a combined method of Bisection method and sequential unconstrained minimization based on Reformulation-Linearization Technique (RLT). Numerical results demonstrate that the performance of our joint optimization method outperforms other benchmark schemes for the residual energy maximization problem. Besides, the algorithm can maximize the residual energy, reduce the computation complexity, and improve computation efficiency.

Description: Using the single premise entailment (SPE) model to accomplish the multi-premise entailment (MPE) task can alleviate the problem that the neural network cannot be effectively trained due to the lack of labeled multi-premise training data. Moreover, the abundant judgment methods for the relationship between sentence pairs can also be applied in this task. However, the single-premise pre-trained model does not have a structure for processing multi-premise relationships, and this structure is a crucial technique for solving MPE problems. This paper proposes adding a multi-premise relationship processing module based on not changing the structure of the pre-trained model to compensate for this deficiency. Moreover, we proposed a three-step training method combining this module, which ensures that the module focuses on dealing with the multi-premise relationship during matching, thus applying the single-premise model to multi-premise tasks. Besides, this paper also proposes a specific structure of the relationship processing module, i.e., we call it the attention-backtracking mechanism. Experiments show that this structure can fully consider the context of multi-premise, and the structure combined with the three-step training can achieve better accuracy on the MPE test set than other transfer methods.

Description: Federated learning is a novel distributed learning framework, which enables thousands of participants to collaboratively construct a deep learning model. In order to protect confidentiality of the training data, the shared information between server and participants are only limited to model parameters. However, this setting is vulnerable to model poisoning attack, since the participants have permission to modify the model parameters. In this paper, we perform systematic investigation for such threats in federated learning and propose a novel optimization-based model poisoning attack. Different from existing methods, we primarily focus on the effectiveness, persistence and stealth of attacks. Numerical experiments demonstrate that the proposed method can not only achieve high attack success rate, but it is also stealthy enough to bypass two existing defense methods.

Description: Person re-identification (ReID) plays a significant role in video surveillance analysis. In the real world, due to illumination, occlusion, and deformation, pedestrian features extraction is the key to person ReID. Considering the shortcomings of existing methods in pedestrian features extraction, a method based on attention mechanism and context information fusion is proposed. A lightweight attention module is introduced into ResNet50 backbone network equipped with a small number of network parameters, which enhance the significant characteristics of person and suppress irrelevant information. Aiming at the problem of person context information loss due to the over depth of the network, a context information fusion module is designed to sample the shallow feature map of pedestrians and cascade with the high-level feature map. In order to improve the robustness, the model is trained by combining the loss of margin sample mining with the loss function of cross entropy. Experiments are carried out on datasets Market1501 and DukeMTMC-reID, our method achieves rank-1 accuracy of 95.9% on the Market1501 dataset, and 90.1% on the DukeMTMC-reID dataset, outperforming the current mainstream method in case of only using global feature.

Description: Many countries worldwide face challenges in controlling building incidence prevention measures for fire disasters. The most critical issues are the localization, identification, detection of the room occupant. Internet of Things (IoT) along with machine learning proved the increase of the smartness of the building by providing real-time data acquisition using sensors and actuators for prediction mechanisms. This paper proposes the implementation of an IoT framework to capture indoor environmental parameters for occupancy multivariate time-series data. The application of the Long Short Term Memory (LSTM) Deep Learning algorithm is used to infer the knowledge of the presence of human beings. An experiment is conducted in an office room using multivariate time-series as predictors in the regression forecasting problem. The results obtained demonstrate that with the developed system it is possible to obtain, process, and store environmental information. The information collected was applied to the LSTM algorithm and compared with other machine learning algorithms. The compared algorithms are Support Vector Machine, Naïve Bayes Network, and Multilayer Perceptron Feed-Forward Network. The outcomes based on the parametric calibrations demonstrate that LSTM performs better in the context of the proposed application.

Description: In a community with an aging population, helping each other is a must society function. Lacking mutual trust makes the need for a fair and transparent service exchange platform on top of the public service administration’s list. We present an efficient blockchain-based TimeBank realization with a newly proposed dynamic service matching algorithm (DSMA) in this work. The Hyperledger Fabric (or Fabric in short), one of the well-known Consortium Blockchains, is chosen as our system realization platform. It provides the identity certification mechanism and has an extendable network structure. The performance of a DSMA is measured by the waiting time for a service to get a match, called the service-matching waiting time (SMWT). In our DSMA, the decision as to whether a service is to get a match or wait for a later chance depends dynamically on the total number of contemporarily available services (i.e., the thickness of the service market). To better the proposed TimeBank system’s service quality, a Dynamic Tuning Strategy (DTS) is designed to thicken the market size. Experimental results show that a thicker market makes on-chain nodes have more links, and in turn, they find a match easier (i.e., consume a shorter SMWT).

Description: Network caching is a technique used to speed-up user access to frequently requested contents in complex data networks. This paper presents a two-layer overlay network caching system for content distribution. It is used to define some caching scenarios with increasing complexity, which refers to real situations, including mobile 5G connectivity. For each scenario our aim is to maximize the hit ratio, which leads to the formulation of NP-complete optimization problems. The heuristic solutions proposed are based on the theory of the maximization of monotone submodular functions under matroid constraints. After the determination of the approximation ratio of the greedy heuristic algorithms proposed, a numerical performance analysis is shown. This analysis includes a comparison with the Least-Frequently Used (LFU) eviction strategy adapted to the analyzed systems. Results show very good performance, under the hypotheses of either known or unknown popularity of contents.

Description: The pervasiveness of online social networks has reshaped the way people access information. Online social networks make it common for users to inform themselves online and share news among their peers, but also favor the spreading of both reliable and fake news alike. Because fake news may have a profound impact on the society at large, realistically simulating their spreading process helps evaluate the most effective countermeasures to adopt. It is customary to model the spreading of fake news via the same epidemic models used for common diseases; however, these models often miss concepts and dynamics that are peculiar to fake news spreading. In this paper, we fill this gap by enriching typical epidemic models for fake news spreading with network topologies and dynamics that are typical of realistic social networks. Specifically, we introduce agents with the role of influencers and bots in the model and consider the effects of dynamical network access patterns, time-varying engagement, and different degrees of trust in the sources of circulating information. These factors concur with making the simulations more realistic. Among other results, we show that influencers that share fake news help the spreading process reach nodes that would otherwise remain unaffected. Moreover, we emphasize that bots dramatically speed up the spreading process and that time-varying engagement and network access change the effectiveness of fake news spreading.

Description: The continuous increase in network traffic has sharply increased the demand for high-performance packet processing systems. For a high-performance packet processing system based on multi-core processors, the packet scheduling algorithm is critical because of the significant role it plays in load distribution, which is related to system throughput, attracting intensive research attention. However, it is not an easy task since the canonical flow-level packet scheduling algorithm is vulnerable to traffic locality, while the packet-level packet scheduling algorithm fails to maintain cache affinity. In this paper, we propose an adaptive throughput-first packet scheduling algorithm for DPDK-based packet processing systems. Combined with the feature of DPDK burst-oriented packet receiving and transmitting, we propose using Subflow as the scheduling unit and the adjustment unit making the proposed algorithm not only maintain the advantages of flow-level packet scheduling algorithms when the adjustment does not happen but also avoid packet loss as much as possible when the target core may be overloaded Experimental results show that the proposed method outperforms Round-Robin, HRW (High Random Weight), and CRC32 on system throughput and packet loss rate.

Description: Variational graph autoencoder, which can encode structural information and attribute information in the graph into low-dimensional representations, has become a powerful method for studying graph-structured data. However, most existing methods based on variational (graph) autoencoder assume that the prior of latent variables obeys the standard normal distribution which encourages all nodes to gather around 0. That leads to the inability to fully utilize the latent space. Therefore, it becomes a challenge on how to choose a suitable prior without incorporating additional expert knowledge. Given this, we propose a novel noninformative prior-based interpretable variational graph autoencoder (NPIVGAE). Specifically, we exploit the noninformative prior as the prior distribution of latent variables. This prior enables the posterior distribution parameters to be almost learned from the sample data. Furthermore, we regard each dimension of a latent variable as the probability that the node belongs to each block, thereby improving the interpretability of the model. The correlation within and between blocks is described by a block–block correlation matrix. We compare our model with state-of-the-art methods on three real datasets, verifying its effectiveness and superiority.

Description: Social isolation during the pandemic contributed to the transition of educational processes to e-learning. A short-term e-marketing education program for a variety of students was introduced in May 2020 and is taught entirely online. A survey was conducted regularly in the last week of training using Google Forms, and three cohorts were surveyed in July, September, and December 2020. A high level of satisfaction indicates an interest in the content and a positive assessment of the level of comfort of an organization adapted to the needs of students; this positive result contrasted with the negative opinion of the remote learning in Russia since March 2020, and this surprising satisfaction of students has motivated the study to try to explain its reasons. This result was compared with the short-term course taught through the educational pedagogical platform of a university. The students of traditional short- and long-term university programs were asked to assess their satisfaction with different digital communication tools used for e-learning. They showed low satisfaction with the pedagogical platform and a positive reaction to the e-communication tools (messengers, social media, short surveys, video conferences, etc.). The qualitative responses helped to better understand the real problems of the cognitive process and the triple structure of intellectual production during e-learning, including interest in the intellectual outcome, the need for emotional and motivational elements of cooperation and competition between students, and smooth behavioral enrichment, which requires special efforts from students and their leading from teachers. The main conclusion concerns a practical decision to continue the implementation of the educational program in the form of an online course with the use of the mixed digital communication tools of social media, messengers, and video conferences, which most likely meets the expectations and capabilities of students.

Description: Social media has played a significant role in disaster management, as it enables the general public to contribute to the monitoring of disasters by reporting incidents related to disaster events. However, the vast volume and wide variety of generated social media data create an obstacle in disaster management by limiting the availability of actionable information from social media. Several approaches have therefore been proposed in the literature to cope with the challenges of social media data for disaster management. To the best of our knowledge, there is no published literature on social media data management and analysis that identifies the research problems and provides a research taxonomy for the classification of the common research issues. In this paper, we provide a survey of how social media data contribute to disaster management and the methodologies for social media data management and analysis in disaster management. This survey includes the methodologies for social media data classification and event detection as well as spatial and temporal information extraction. Furthermore, a taxonomy of the research dimensions of social media data management and analysis for disaster management is also proposed, which is then applied to a survey of existing literature and to discuss the core advantages and disadvantages of the various methodologies.

Description: Digital regulation implies the quantified measuring and the network infrastructure allowing managers to control the processes of value creation. Digital regulation needs to take into account tacit elements of the value creation process, including unconscious competency, creativity, and intuitive anticipation, to assure the resulting network’s innovation growth. Digital society in developing countries is built on the ground of fact change of the economy and social relations, of transition towards an emerging market within the global offline network of interactions and online activities through Internet; the innovative growth imposes the evolution of managerial behavior and attitudes. The main objective of the paper is to obtain indications on the perception of intellectual capital by corporate managers. The exploratory study was carried out in Russian companies operating in different sectors, with the use of the open-ended approach, including focused interviews and group discussion among experts, middle and senior managers from marketing or corporate governance background. The data were complemented by documentary analysis of descriptions of internal processes of the implementation of digital tools of accounting, which includes the human resources control applied for the remote work during the pandemic. Networking helps to coordinate functions between team members at remote work and between teams and administrators. The interviews demonstrated the administrative tendency to under-estimate the non-formalized factors of innovation activity, such as awareness of corporate strategy, creativity, motivation, and affective and behavioral components of communication of the persons involved in the enrichment of intellectual capital. The results show fuzzy boundaries between the intellectual capital components that are difficult to control. This difficulty provokes the preference for the use of “traditional” quantitative indicators that had been implemented at the stage of the financial digitalization, instead of developing new parameters or measuring approaches. The networking emerges synergetic effect if the administrators refuse their monopoly on the uncertainty zones and are oriented to construct the trustful atmosphere of personal responsibility within the network.

Description: Blockchain is becoming more and more popular in various fields. Since the information transmission mode of the blockchain is data broadcasting, the traditional TCP/IP network cannot support the blockchain system well, but the Named-Data Networking (NDN) could be a good choice because of its multi-path forwarding and intra-network caching functions. In this article, we propose a new blockchain information transmission acceleration strategy (AITS) combining with graph theory and probability theory based on the NDN architecture. We select some more important nodes in the network as “secondary nodes”, and give them more bandwidth and cache space to assist the NDN network in data transmission. In order to select the correct node as the secondary node, we present a method to calculate the number of secondary nodes, and give the function to calculate the importance of each node. The simulation results show that in complex networks, the proposed method has superior performance in accelerating information transmission and reducing data overhead.

Description: Recent developments in the fields of computer science, such as advances in the areas of big data, knowledge extraction, and deep learning, have triggered the application of data-driven research methods to disciplines such as the social sciences and humanities. This article presents a collaborative, interdisciplinary process for adapting data-driven research to research questions within other disciplines, which considers the methodological background required to obtain a significant impact on the target discipline and guides the systematic collection and formalization of domain knowledge, as well as the selection of appropriate data sources and methods for analyzing, visualizing, and interpreting the results. Finally, we present a case study that applies the described process to the domain of communication science by creating approaches that aid domain experts in locating, tracking, analyzing, and, finally, better understanding the dynamics of media criticism. The study clearly demonstrates the potential of the presented method, but also shows that data-driven research approaches require a tighter integration with the methodological framework of the target discipline to really provide a significant impact on the target discipline.

Description: Research professors develop scientific products that impact and benefit society, but their competencies in doing so are rarely evaluated. Therefore, by employing a mixed two-stage sequential design, this study developed a self-assessment model of research professors’ competencies with four domains, seven competencies, and 30 competency elements. Next, we conducted descriptive statistical analysis of those elements. In the first year, 320 respondents rated themselves on four levels: initial, basic, autonomous, and consolidated. In the assessment model’s second year, we compared 30 respondents’ results with those of their initial self-assessment. The main developmental challenge was Originality and Innovation, which remained at the initial level. Both Training of Researchers and Transformation of Society were at the basic level, and Digital Competency was at the autonomous level. Both Teaching Competence and Ethics and Citizenship attained the consolidated level. This information helps establish priorities for accelerating researchers’ training and the quality of their research.

Description: The demands for information security in higher education will continue to increase. Serious data breaches have occurred already and are likely to happen again without proper risk management. This paper applies the Comprehensive Literature Review (CLR) Model to synthesize research within cybersecurity risk by reviewing existing literature of known assets, threat events, threat actors, and vulnerabilities in higher education. The review included published studies from the last twelve years and aims to expand our understanding of cybersecurity’s critical risk areas. The primary finding was that empirical research on cybersecurity risks in higher education is scarce, and there are large gaps in the literature. Despite this issue, our analysis found a high level of agreement regarding cybersecurity issues among the reviewed sources. This paper synthesizes an overview of mission-critical assets, everyday threat events, proposes a generic threat model, and summarizes common cybersecurity vulnerabilities. This report concludes nine strategic cyber risks with descriptions of frequencies from the compiled dataset and consequence descriptions. The results will serve as input for security practitioners in higher education, and the research contains multiple paths for future work. It will serve as a starting point for security researchers in the sector.

Description: Collaborative filtering (CF) is a widely used method in recommendation systems. Linear models are still the mainstream of collaborative filtering research methods, but non-linear probabilistic models are beyond the limit of linear model capacity. For example, variational autoencoders (VAEs) have been extensively used in CF, and have achieved excellent results. Aiming at the problem of the prior distribution for the latent codes of VAEs in traditional CF is too simple, which makes the implicit variable representations of users and items too poor. This paper proposes a variational autoencoder that uses a Gaussian mixture model for latent factors distribution for CF, GVAE-CF. On this basis, an optimization function suitable for GVAE-CF is proposed. In our experimental evaluation, we show that the recommendation performance of GVAE-CF outperforms the previously proposed VAE-based models on several popular benchmark datasets in terms of recall and normalized discounted cumulative gain (NDCG), thus proving the effectiveness of the algorithm.

Description: Due to its novelty, the recent pandemic of the coronavirus disease (COVID-19), which is associated with the spread of the new severe acute respiratory syndrome coronavirus (SARS-CoV-2), triggered the public’s interest in accessing information, demonstrating the importance of obtaining and analyzing credible and updated information from an epidemiological surveillance context. For this purpose, health authorities, international organizations, and university institutions have published online various graphic and cartographic representations of the evolution of the pandemic with daily updates that allow the almost real-time monitoring of the evolutionary behavior of the spread, lethality, and territorial distribution of the disease. The purpose of this article is to describe the technical solution and the main results associated with the publication of the COMPRIME_COMPRI_MOv dashboard for the dissemination of information and multi-scale knowledge of COVID-19. Under two rapidly implementing research projects for innovative solutions to respond to the COVID-19 pandemic, promoted in Portugal by the FCT (Foundation for Science and Technology), a website was created. That website brings together a diverse set of variables and indicators in a dynamic and interactive way that reflects the evolutionary behavior of the pandemic from a multi-scale perspective, in Portugal, constituting itself as a system for monitoring the evolution of the pandemic. In the current situation, this type of exploratory solutions proves to be crucial to guarantee everyone’s access to information while simultaneously emerging as an epidemiological surveillance tool that is capable of assisting decision-making by public authorities with competence in defining control policies and fight the spread of the new coronavirus.

Description: Currently, private universities, as a result of the pandemic that the world is facing, are going through very delicate moments in several areas, both academic and financial. Academically, there are learning problems and these are directly related to the dropout rate, which brings financial problems. Added to this are the economic problems caused by the pandemic, where the rates of students who want to access a private education have dropped considerably. For this reason, it is necessary for all private universities to have support to improve their student income and avoid cuts in budgets and resources. However, the academic part represents a great effort to fulfill their academic activities, which are the priority, with attention on those interested in pursuing a training programs. To solve these problems, it is important to integrate technologies such as Chatbots, which use artificial intelligence in such a way that tasks such as providing information on an academic courses are addressed by them, reducing the administrative burden and improving the user experience. At the same time, this encourages people to be a part of the college.

Description: Nowadays, there is an increasing need to understand the behavior of COVID-19. After the Directorate-General of Health of Portugal made available the infected patient’s data, it became possible to analyze it and gather some conclusions, obtaining a better understanding of the matter. In this context, the project developed—ioCOVID19—Intelligent Decision Support Platform aims to identify patterns and develop intelligent models to predict and support clinical decisions. This article explores which typologies are associated with different outcomes to help clinicians fight the virus with a decision support system. So, to achieve this purpose, classification algorithms were used, and one target was studied—Patients outcome, that is, to predict if the patient will die or recover. Regarding the obtained results, the model that stood out is composed of scenario s4 (composed of all comorbidities, symptoms, and age), the decision tree algorithm, and the oversampling sampling method. The obtained results by the studied metrics were (in order of importance): Sensitivity of 95.20%, Accuracy of 90.67%, and Specificity of 86.08%. The models were deployed as a service, and they are part of a clinical decision support system that is available for authorized users anywhere and anytime.

Description: Phubbing, or using a phone to snub another person, has been investigated through social and personality frameworks. Phubbing involves attending to and performing competing tasks, implying the involvement of attentional abilities. Yet, past research has not yet used a cognitive framework to establish a link between phubbing and attention. Using self-report data from a large online sample, we explored the associations between phubbing and everyday attentional failures. Phubbing was associated with difficulties in attentional shifting and distractibility, frequent attentional lapses, spontaneous and deliberate mind wandering, and attention-related cognitive errors. When examining these attention variables alongside several psychosocial and personality variables, attention-related cognitive errors acted as the biggest predictor of phubbing behavior. Phubbing was also positively correlated with media multitasking, which is a conceptually similar yet distinct technology use behavior. The results suggest that perceived everyday attentional failures are strongly associated with, and to an extent can predict, phubbing behavior, even more so than some social and personality variables. Technology has incorporated itself as a necessity, or at the very least a favored convenience, in most people’s lives. Characterizing technology multitasking behaviors from a variety of frameworks can help us better understand who is engaging in these behaviors and why.

Description: The problem of automatic detection of fake news in social media, e.g., on Twitter, has recently drawn some attention. Although, from a technical perspective, it can be regarded as a straight-forward, binary classification problem, the major challenge is the collection of large enough training corpora, since manual annotation of tweets as fake or non-fake news is an expensive and tedious endeavor, and recent approaches utilizing distributional semantics require large training corpora. In this paper, we introduce an alternative approach for creating a large-scale dataset for tweet classification with minimal user intervention. The approach relies on weak supervision and automatically collects a large-scale, but very noisy, training dataset comprising hundreds of thousands of tweets. As a weak supervision signal, we label tweets by their source, i.e., trustworthy or untrustworthy source, and train a classifier on this dataset. We then use that classifier for a different classification target, i.e., the classification of fake and non-fake tweets. Although the labels are not accurate according to the new classification target (not all tweets by an untrustworthy source need to be fake news, and vice versa), we show that despite this unclean, inaccurate dataset, the results are comparable to those achieved using a manually labeled set of tweets. Moreover, we show that the combination of the large-scale noisy dataset with a human labeled one yields more advantageous results than either of the two alone.

Description: A real-time news spreading is now available for everyone, especially thanks to Online Social Networks (OSNs) that easily endorse gate watching, so the collective intelligence and knowledge of dedicated communities are exploited to filter the news flow and to highlight and debate relevant topics. The main drawback is that the responsibility for judging the content and accuracy of information moves from editors and journalists to online information users, with the side effect of the potential growth of fake news. In such a scenario, trustworthiness about information providers cannot be overlooked anymore, rather it more and more helps in discerning real news from fakes. In this paper we evaluate how trustworthiness among OSN users influences the news spreading process. To this purpose, we consider the news spreading as a Susceptible-Infected-Recovered (SIR) process in OSN, adding the contribution credibility of users as a layer on top of OSN. Simulations with both fake and true news spreading on such a multiplex network show that the credibility improves the diffusion of real news while limiting the propagation of fakes. The proposed approach can also be extended to real social networks.

Description: The definition of suitable generative models for synthetic yet realistic social networks is a widely studied problem in the literature. By not being tied to any real data, random graph models cannot capture all the subtleties of real networks and are inadequate for many practical contexts—including areas of research, such as computational epidemiology, which are recently high on the agenda. At the same time, the so-called contact networks describe interactions, rather than relationships, and are strongly dependent on the application and on the size and quality of the sample data used to infer them. To fill the gap between these two approaches, we present a data-driven model for urban social networks, implemented and released as open source software. By using just widely available aggregated demographic and social-mixing data, we are able to create, for a territory of interest, an age-stratified and geo-referenced synthetic population whose individuals are connected by “strong ties” of two types: intra-household (e.g., kinship) or friendship. While household links are entirely data-driven, we propose a parametric probabilistic model for friendship, based on the assumption that distances and age differences play a role, and that not all individuals are equally sociable. The demographic and geographic factors governing the structure of the obtained network, under different configurations, are thoroughly studied through extensive simulations focused on three Italian cities of different size.

Description: Classification of resource can help us effectively reduce the work of filtering massive academic resources, such as selecting relevant papers and focusing on the latest research by scholars in the same field. However, existing graph neural networks do not take into account the associations between academic resources, leading to unsatisfactory classification results. In this paper, we propose an Association Content Graph Attention Network (ACGAT), which is based on the association features and content attributes of academic resources. The semantic relevance and academic relevance are introduced into the model. The ACGAT makes full use of the association commonality and the influence information of resources and introduces an attention mechanism to improve the accuracy of academic resource classification. We conducted experiments on a self-built scholar network and two public citation networks. Experimental results show that the ACGAT has better effectiveness than existing classification methods.

Description: Software Defined Networking (SDN) provides a new perspective for the Internet of Things (IoT), since, with the separation of the control from the data planes, it is viable to optimise the traditional networks operation management. In particular, the SDN Controller has a global vision of the network of sensors/actuators domain, allowing real-time network nodes and data flows reconfiguration. As a consequence, devices, usually facing limited communications and computing resources, are relieved of the route selection task in a distributed and, thus, suboptimal way. This paper proposes a SDN-IoT architecture, specifically focusing on the Controller design, which dynamically optimises in real time the end-to-end flows delivery. In particular, the dynamic routing policy adaptation is based on the real-time estimation of the network status and it allows jointly minimising the end-to-end latency and energy consumption and, consequently, to improve the network life time. The performance of the proposed approach is analysed in terms of the average latency, energy consumption and overhead, pointing out a better behaviour in comparison with the existing distributed approaches.

Description: Software-defined Networking (SDN) has recently developed and been put forward as a promising and encouraging solution for future internet architecture. Managed, the centralized and controlled network has become more flexible and visible using SDN. On the other hand, these advantages bring us a more vulnerable environment and dangerous threats, causing network breakdowns, systems paralysis, online banking frauds and robberies. These issues have a significantly destructive impact on organizations, companies or even economies. Accuracy, high performance and real-time systems are essential to achieve this goal successfully. Extending intelligent machine learning algorithms in a network intrusion detection system (NIDS) through a software-defined network (SDN) has attracted considerable attention in the last decade. Big data availability, the diversity of data analysis techniques, and the massive improvement in the machine learning algorithms enable the building of an effective, reliable and dependable system for detecting different types of attacks that frequently target networks. This study demonstrates the use of machine learning algorithms for traffic monitoring to detect malicious behavior in the network as part of NIDS in the SDN controller. Different classical and advanced tree-based machine learning techniques, Decision Tree, Random Forest and XGBoost are chosen to demonstrate attack detection. The NSL-KDD dataset is used for training and testing the proposed methods; it is considered a benchmarking dataset for several state-of-the-art approaches in NIDS. Several advanced preprocessing techniques are performed on the dataset in order to extract the best form of the data, which produces outstanding results compared to other systems. Using just five out of 41 features of NSL-KDD, a multi-class classification task is conducted by detecting whether there is an attack and classifying the type of attack (DDoS, PROBE, R2L, and U2R), accomplishing an accuracy of 95.95%.

Description: The COVID-19 crisis has shown that we can only prevent the risk of mass contagion through timely, large-scale, coordinated, and decisive actions. This pandemic has also highlighted the critical importance of generating rigorous evidence for decision-making, and actionable insights from data, considering further the intricate web of causes and drivers behind observed patterns of contagion diffusion. Using mobility, socioeconomic, and epidemiological data recorded throughout the pandemic development in the Santiago Metropolitan Region, we seek to understand the observed patterns of contagion. We characterize human mobility patterns during the pandemic through different mobility indices and correlate such patterns with the observed contagion diffusion, providing data-driven models for insights, analysis, and inferences. Through these models, we examine some effects of the late application of mobility restrictions in high-income urban regions that were affected by high contagion rates at the beginning of the pandemic. Using augmented synthesis control methods, we study the consequences of the early lifting of mobility restrictions in low-income sectors connected by public transport to high-risk and high-income communes. The Santiago Metropolitan Region is one of the largest Latin American metropolises with features that are common to large cities. Therefore, it can be used as a relevant case study to unravel complex patterns of the spread of COVID-19.

Description: With the rise of misinformation, there is a great need for scalable educational interventions supporting students’ abilities to determine the trustworthiness of digital news. We address this challenge in our study by developing an online intervention tool based on tutorials in civic online reasoning that aims to teach adolescents how to critically assess online information comprising text, videos and images. Our findings from an online intervention with 209 upper secondary students highlight how observational learning and feedback support their ability to read laterally and improve their performance in determining the credibility of digital news and social media posts.

Description: The Distributed Ledger Technology (DLT) provides an infrastructure for developing decentralized applications with no central authority for registering, sharing, and synchronizing transactions on digital assets. In the last years, it has drawn high interest from the academic community, technology developers, and startups mostly by the advent of its most popular type, blockchain technology. In this paper, we provide a comprehensive overview of DLT analyzing the challenges, provided solutions or alternatives, and their usage for developing decentralized applications. We define a three-tier based architecture for DLT applications to systematically classify the technology solutions described in over 100 papers and startup initiatives. Protocol and Network Tier contains solutions for digital assets registration, transactions, data structure, and privacy and business rules implementation and the creation of peer-to-peer networks, ledger replication, and consensus-based state validation. Scalability and Interoperability Tier solutions address the scalability and interoperability issues with a focus on blockchain technology, where they manifest most often, slowing down its large-scale adoption. The paper closes with a discussion on challenges and opportunities for developing decentralized applications by providing a multi-step guideline for decentralizing the design and implementation of traditional systems.

Description: Background: Coronavirus Disease 2019 (COVID-19) is the main discussed topic worldwide in 2020 and at the beginning of the Italian epidemic, scientists tried to understand the virus diffusion and the epidemic curve of positive cases with controversial findings and numbers. Objectives: In this paper, a data analytics study on the diffusion of COVID-19 in Lombardy Region and Campania Region is developed in order to identify the driver that sparked the second wave in Italy. Methods: Starting from all the available official data collected about the diffusion of COVID-19, we analyzed Google mobility data, school data and infection data for two big regions in Italy: Lombardy Region and Campania Region, which adopted two different approaches in opening and closing schools. To reinforce our findings, we also extended the analysis to the Emilia Romagna Region. Results: The paper shows how different policies adopted in school opening/closing may have had an impact on the COVID-19 spread, while other factors related to citizen mobility did not affect the second Italian wave. Conclusions: The paper shows that a clear correlation exists between the school contagion and the subsequent temporal overall contagion in a geographical area. Moreover, it is clear that highly populated provinces have the greatest spread of the virus.

Description: In real applications, massive data with graph structures are often incomplete due to various restrictions. Therefore, graph data imputation algorithms have been widely used in the fields of social networks, sensor networks, and MRI to solve the graph data completion problem. To keep the data relevant, a data structure is represented by a graph-tensor, in which each matrix is the vertex value of a weighted graph. The convolutional imputation algorithm has been proposed to solve the low-rank graph-tensor completion problem that some data matrices are entirely unobserved. However, this data imputation algorithm has limited application scope because it is compute-intensive and low-performance on CPU. In this paper, we propose a scheme to perform the convolutional imputation algorithm with higher time performance on GPUs (Graphics Processing Units) by exploiting multi-core GPUs of CUDA architecture. We propose optimization strategies to achieve coalesced memory access for graph Fourier transform (GFT) computation and improve the utilization of GPU SM resources for singular value decomposition (SVD) computation. Furthermore, we design a scheme to extend the GPU-optimized implementation to multiple GPUs for large-scale computing. Experimental results show that the GPU implementation is both fast and accurate. On synthetic data of varying sizes, the GPU-optimized implementation running on a single Quadro RTX6000 GPU achieves up to 60.50× speedups over the GPU-baseline implementation. The multi-GPU implementation achieves up to 1.81× speedups on two GPUs versus the GPU-optimized implementation on a single GPU. On the ego-Facebook dataset, the GPU-optimized implementation achieves up to 77.88× speedups over the GPU-baseline implementation. Meanwhile, the GPU implementation and the CPU implementation achieve similar, low recovery errors.

Description: This study presents a systematic review of 169 papers concerning the ICT (Information and Communication Technologies) related to rural areas, specifically to dairy farms. The objective was to delve into the relationship between dairy farmers and the administrative authorities via e-government, comparing this area to another eight concerning the farmer’s needs and expectations in relation to the ICT in different fields of their business. We observed that areas such as connectivity and digital inclusion are the most covered areas not only at the study level but also at the government level since countries all over the world are trying to develop politics to put an end to the so-called “digital divide,” which affects rural areas more intensely. This is increasing due to the growing technological innovations. The areas of the market, production, financial development, management and counseling, Smart Farming, and Internet of Things have been approached, associated with the ICT in dairy farms, showing in the latter two an increasing number of papers in the last few years. The area of public administration in relation to dairy farms has also been covered, being remarkable the low number of pieces of research concerning the interaction by the farmers, more specifically by dairy farmers, with the public administration, which is surprising due to the new global need and especially in the European Union (EU) of interacting with it telematically by all legal entities. The results show that there are still barriers to the implementation of the electronic government (e-government) since the websites do not meet the user’s expectations. Therefore, this study lays the ground for future research on this area. As a graphical abstract of the contributions of this paper, we present a graphic summary, where the different contributions by areas and expressed in percentage values are shown.

Description: Video captioning is a popular task which automatically generates a natural-language sentence to describe video content. Previous video captioning works mainly use the encoder–decoder framework and exploit special techniques such as attention mechanisms to improve the quality of generated sentences. In addition, most attention mechanisms focus on global features and spatial features. However, global features are usually fully connected features. Recurrent convolution networks (RCNs) receive 3-dimensional features as input at each time step, but the temporal structure of each channel at each time step has been ignored, which provide temporal relation information of each channel. In this paper, a video captioning model based on channel soft attention and semantic reconstructor is proposed, which considers the global information for each channel. In a video feature map sequence, the same channel of every time step is generated by the same convolutional kernel. We selectively collect the features generated by each convolutional kernel and then input the weighted sum of each channel to RCN at each time step to encode video representation. Furthermore, a semantic reconstructor is proposed to rebuild semantic vectors to ensure the integrity of semantic information in the training process, which takes advantage of both forward (semantic to sentence) and backward (sentence to semantic) flows. Experimental results on popular datasets MSVD and MSR-VTT demonstrate the effectiveness and feasibility of our model.

Description: As COVID-19 continues to impact upon education worldwide, systems and organizations are rapidly transiting their professional learning to online mode. This raises concerns, not simply about whether online professional learning can result in equivalent outcomes to face-to-face learning, but more importantly about how to best evaluate online professional learning so we can iteratively improve our approaches. This case study analyses the evaluation of an online teacher professional development workshop for the purpose of critically reflecting upon the efficacy of workshop evaluation techniques. The evaluation approach was theoretically based in a synthesis of six seminal workshop evaluation models, and structured around eight critical dimensions of educational technology evaluation. The approach involving collection of pre-workshop participant background information, pre-/post-teacher perceptions data, and post-workshop focus group perceptions, enabled the changes in teacher knowledge, skills, and beliefs to be objectively evaluated, at the same time as providing qualitative information to effectively improve future iterations of the workshops along a broad range of dimensions. The evaluation approach demonstrated that the professional learning that was shifted into online mode in response to COVID-19 could unequivocally result in significant improvements to professional learning outcomes. More importantly, the evaluation approach is critically contrasted with previous evaluation models, and a series of recommendations for the evaluation of technology-enhanced teacher professional development workshops are proposed.

Description: A data center undertakes increasing background services of various applications, and the data flows transmitted between the nodes in data center networks (DCNs) are consequently increased. At the same time, the traffic of each link in a DCN changes dynamically over time. Flow scheduling algorithms can improve the distribution of data flows among the network links so as to improve the balance of link loads in a DCN. However, most current load balancing works achieve flow scheduling decisions to the current links on the basis of past link flow conditions. This situation impedes the existing link scheduling methods from implementing optimal decisions for scheduling data flows among the network links in a DCN. This paper proposes a predictive link load balance routing algorithm for a DCN based on residual networks (ResNet), i.e., the link load balance route (LLBR) algorithm. The LLBR algorithm predicts the occupancy of the network links in the next duty cycle, according to the ResNet architecture, and then the optimal traffic route is selected according to the predictive network environment. The LLBR algorithm, round-robin scheduling (RRS), and weighted round-robin scheduling (WRRS) are used in the same experimental environment. Experimental results show that compared with the WRRS and RRS, the LLBR algorithm can reduce the transmission time by approximately 50%, reduce the packet loss rate from 0.05% to 0.02%, and improve the bandwidth utilization by 30%.

Description: The reporting of incidents of misconduct, violence, sexual assault, harassment, and other types of crime that constitute a major concern in modern society is of significant value when investigating such incidents. Unfortunately, people involved in such incidents, either as witnesses or victims, are often reluctant to report them when such reporting demands revealing the reporter’s true identity. In this paper, we propose an online reporting system that leverages Identity-Based Cryptography (IBC) and offers data authentication, data integrity, and data confidentiality services to both eponymous and anonymous users. The system, called ARIBC, is founded on a certificate-less, public-key, IBC infrastructure, implemented by employing the Sakai–Kasahara approach and by following the IEEE 1363.3-2013 standard. We develop a proof-of-concept implementation of the proposed scheme, and demonstrate its applicability in environments with constrained human, organizational and/or computational resources. The computational overheads imposed by the scheme are found to be well within the capabilities of modern fixed or mobile devices.

Description: Industry 4.0 and Society 5.0 are reshaping the way organizations function and interact with the communities they serve. The massive penetration of computer and network applications forces organizations to digitalize their processes and provide innovative products, services, and business models. The education market is suffering changes as well, but universities seem slow to react. This paper proposes the application of an integrated digital transformation model to assess the maturity level that educational institutions have in their digital transformation processes and compares them to other industries. Particular considerations to address when using the model for higher-education institutions are discussed. Our results show that universities fall behind other sectors, probably due to a lack of effective leadership and changes in culture. This is complemented negatively by an insufficient degree of innovation and financial support.

Description: Video conferencing services based on web real-time communication (WebRTC) protocol are growing in popularity among Internet users as multi-platform solutions enabling interactive communication from anywhere, especially during this pandemic era. Meanwhile, Internet service providers (ISPs) have deployed fiber links and customer premises equipment that operate according to recent 802.11ac/ax standards and promise users the ability to establish uninterrupted video conferencing calls with ultra-high-definition video and audio quality. However, the best-effort nature of 802.11 networks and the high variability of wireless medium conditions hinder users experiencing uninterrupted high-quality video conferencing. This paper presents a novel approach to estimate the perceived quality of service (PQoS) of video conferencing using only 802.11-specific network performance parameters collected from Wi-Fi access points (APs) on customer premises. This study produced datasets comprising 802.11-specific network performance parameters collected from off-the-shelf Wi-Fi APs operating at 802.11g/n/ac/ax standards on both 2.4 and 5 GHz frequency bands to train machine learning algorithms. In this way, we achieved classification accuracies of 92–98% in estimating the level of PQoS of video conferencing services on various Wi-Fi networks. To efficiently troubleshoot wireless issues, we further analyzed the machine learning model to correlate features in the model with the root cause of quality degradation. Thus, ISPs can utilize the approach presented in this study to provide predictable and measurable wireless quality by implementing a non-intrusive quality monitoring approach in the form of edge computing that preserves customers’ privacy while reducing the operational costs of monitoring and data analytics.

Description: Physical fitness and level of activity are considered important factors for patients with cancer undergoing major abdominal surgery. Cancer patients with low fitness capacity are at greater risk of postoperative complications, longer hospital stays, and mortality. One of the main challenges facing both healthcare providers and patients is to improve the patient’s physical fitness within the available short period (four to six weeks) prior to surgery. Supervised and unsupervised physical prehabilitation programs are the most common recommended methods for enhancing postoperative outcomes in patients undergoing abdominal surgery. Due to obstacles such as geographical isolation, many patients have limited access to medical centers and facilities that provide onsite prehabilitation programs. This article presents a review of the literature and the development of a model that can remotely monitor physical activities during the prehabilitation period. The mixed prehabilitation model includes the identification of fundamental parameters of physical activities (type, intensity, frequency, and duration) over time. A mathematical model has been developed to offer a solution for both the healthcare provider and patients. This offers the opportunity for physicians or physiotherapists to monitor patients performing their prescribed physical exercises in real time. The model that has been developed is embedded within the internet of things (IoT) system, which calculates the daily and weekly efforts made by the patients and automatically stores this in a comma-separated values (CSV) file that medical staff can access. In addition, this model allows the patient to compensate for missed prescribed activity by adding additional efforts to meet the prehabilitation requirements. As a result, healthcare staff are provided with feedback on patient engagement in prescribed exercise during the period of the prehabilitation program.

Description: When integrating digital technology into teaching, many teachers experience similar challenges. Nevertheless, sharing experiences is difficult as it is usually not possible to transfer teaching scenarios directly from one subject to another because subject-specific characteristics make it difficult to reuse them. To address this problem, instructional scenarios can be described as patterns, which has already been applied in educational contexts. Patterns capture proven teaching strategies and describe teaching scenarios in a unified structure that can be reused. Since priorities for content, methods, and tools are different in each subject, we show an approach to develop a domain-independent graph database to collect digital teaching practices from a taxonomic structure via the intermediate step of an ontology. Furthermore, we outline a method to identify effective teaching practices from interdisciplinary data as patterns from the graph database using an association rule algorithm. The results show that an association-based analysis approach can derive initial indications of effective teaching scenarios.

Description: The COVID-19 pandemic has provided a much-needed sanity check for IoT-inspired frameworks and solutions. IoT solutions such as remote health monitoring and contact tracing provided have support for authorities to successfully manage the spread of the coronavirus. This article provides the first comprehensive review of key IoT solutions that have had an impact on COVID-19 in healthcare, contact tracing, and transportation during the pandemic. Each sector is investigated in depth; and potential applications, social and economic impact, and barriers for mass adaptation are discussed in detail. Furthermore, it elaborates on the challenges and opportunities for IoT framework solutions in the immediate post-COVID-19 era. To this end, privacy and security concerns of IoT applications are analyzed in depth and emerging standards and code of practices for mass adaptation are also discussed. The main contribution of this review paper is the in-depth analysis and categorization of sector-wise IoT technologies, which have the potential to be prominent applications in the new normal. IoT applications in each selected sector are rated for their potential economic and social impact, timeline for mass adaptation, and Technology Readiness Level (TRL). In addition, this article outlines potential research directions for next-generation IoT applications that would facilitate improved performance with preserved privacy and security, as well as wider adaptation by the population at large.

Description: The XPRIZE Foundation designs and operates multi-million-dollar, global competitions to incentivize the development of technological breakthroughs that accelerate humanity toward a better future. To combat the COVID-19 pandemic, the foundation coordinated with several organizations to make datasets about different facets of the disease available and to provide the computational resources needed to analyze those datasets. This paper is a case study of the requirements, design, and implementation of the XPRIZE Data Collaborative, which is a Cloud-based infrastructure that enables the XPRIZE to meet its COVID-19 mission and host future data-centric competitions. We examine how a Cloud Native Application can use an unexpected variety of Cloud technologies, ranging from containers, serverless computing, to even older ones such as Virtual Machines. We also search and document the effects that the pandemic had on application development in the Cloud. We include our experiences of having users successfully exercise the Data Collaborative, detailing the challenges encountered and areas for improvement and future work.

Description: The stranger on the Internet effect has been studied in relation to self-disclosure. Nonetheless, quantitative evidence about how people mentally represent and perceive strangers online is still missing. Given the dynamic development of web technologies, quantifying how much strangers can be considered suitable for pro-social acts such as self-disclosure appears fundamental for a whole series of phenomena ranging from privacy protection to fake news spreading. Using a modified and online version of the Ultimatum Game (UG), we quantified the mental representation of the stranger on the Internet effect and tested if people modify their behaviors according to the interactors’ identifiability (i.e., reputation). A total of 444 adolescents took part in a 2 × 2 design experiment where reputation was set active or not for the two traditional UG tasks. We discovered that, when matched with strangers, people donate the same amount of money as if the other has a good reputation. Moreover, reputation significantly affected the donation size, the acceptance rate and the feedback decision making as well.

Description: Smart agriculture and wildlife monitoring are one of the recent trends of Internet of Things (IoT) applications, which are evolving in providing sustainable solutions from producers. This article details the design, development and assessment of a wildlife monitoring application for IoT animal repelling devices that is able to cover large areas, thanks to the low power wide area networks (LPWAN), which bridge the gap between cellular technologies and short range wireless technologies. LoRa, the global de-facto LPWAN, continues to attract attention given its open specification and ready availability of off-the-shelf hardware, with claims of several kilometers of range in harsh challenging environments. At first, this article presents a survey of the LPWAN for smart agriculture applications. We proceed to evaluate the performance of LoRa transmission technology operating in the 433 MHz and 868 MHz bands, aimed at wildlife monitoring in a forest vegetation area. To characterize the communication link, we mainly use the signal-to-noise ratio (SNR), received signal strength indicator (RSSI) and packet delivery ratio (PDR). Findings from this study show that achievable performance can greatly vary between the 433 MHz and 868 MHz bands, and prompt caution is required when taking numbers at face value, as this can have implications for IoT applications. In addition, our results show that the link reaches up to 860 m in the highly dense forest vegetation environment, while in the not so dense forest vegetation environment, it reaches up to 2050 m.

Description: The mesh-type coronary model, obtained from three-dimensional reconstruction using the sequence of images produced by computed tomography (CT), can be used to obtain useful diagnostic information, such as extracting the projection of the lumen (planar development along an artery). In this paper, we have focused on automated coronary centerline extraction from cardiac computed tomography angiography (CCTA) proposing a 3D version of U-Net architecture, trained with a novel loss function and with augmented patches. We have obtained promising results for accuracy (between 90–95%) and overlap (between 90–94%) with various network training configurations on the data from the Rotterdam Coronary Artery Centerline Extraction benchmark. We have also demonstrated the ability of the proposed network to learn despite the huge class imbalance and sparse annotation present in the training data.

Description: Fake media is spreading like wildfire all over the internet as a result of the great advancement in deepfake creation tools and the huge interest researchers and corporations are showing to explore its limits. Now anyone can create manipulated unethical media forensics, defame, humiliate others or even scam them out of their money with a click of a button. In this research a new deepfake detection approach, iCaps-Dfake, is proposed that competes with state-of-the-art techniques of deepfake video detection and addresses their low generalization problem. Two feature extraction methods are combined, texture-based Local Binary Patterns (LBP) and Convolutional Neural Networks (CNN) based modified High-Resolution Network (HRNet), along with an application of capsule neural networks (CapsNets) implementing a concurrent routing technique. Experiments have been conducted on large benchmark datasets to evaluate the performance of the proposed model. Several performance metrics are applied and experimental results are analyzed. The proposed model was primarily trained and tested on the DeepFakeDetectionChallenge-Preview (DFDC-P) dataset then tested on Celeb-DF to examine its generalization capability. Experiments achieved an Area-Under Curve (AUC) score improvement of 20.25% over state-of-the-art models.

Description: In the current Internet of things era, all companies shifted from paper-based data to the electronic format. Although this shift increased the efficiency of data processing, it has security drawbacks. Healthcare databases are a precious target for attackers because they facilitate identity theft and cybercrime. This paper presents an approach for database damage assessment for healthcare systems. Inspired by the current behavior of COVID-19 infections, our approach views the damage assessment problem the same way. The malicious transactions will be viewed as if they are COVID-19 viruses, taken from infection onward. The challenge of this research is to discover the infected transactions in a minimal time. The proposed parallel algorithm is based on the transaction dependency paradigm, with a time complexity O((M+NQ+N^3)/L) (M = total number of transactions under scrutiny, N = number of malicious and affected transactions in the testing list, Q = time for dependency check, and L = number of threads used). The memory complexity of the algorithm is O(N+KL) (N = number of malicious and affected transactions, K = number of transactions in one area handled by one thread, and L = number of threads). Since the damage assessment time is directly proportional to the denial-of-service time, the proposed algorithm provides a minimized execution time. Our algorithm is a novel approach that outperforms other existing algorithms in this domain in terms of both time and memory, working up to four times faster in terms of time and with 120,000 fewer bytes in terms of memory.

Description: This paper deals with innovative fruition modalities of cultural heritage sites. Based on two ongoing experiments, four pillars are considered, that is, User Localization, Multimodal Interaction, User Understanding and Gamification. A survey of the existing literature regarding one or more issues related to the four pillars is proposed. It aims to put in evidence the exploitation of these contributions to cultural heritage. It is discussed how a cultural site can be enriched, extended and transformed into an intelligent multimodal environment in this perspective. This new augmented environment can focus on the visitor, analyze his activity and behavior, and make his experience more satisfying, fulfilling and unique. After an in-depth overview of the existing technologies and methodologies for the fruition of cultural interest sites, the two experiments are described in detail and the authors’ vision of the future is proposed.

Description: A Vehicular Ad-hoc Network (VANET) comprises a group of moving or stationary vehicles connected by a wireless network. VANETs play a vital role in providing safety and comfort to drivers in vehicular environments. They provide smart traffic control and real-time information, event allocation. VANETs have received attention in support of safe driving, intelligent navigation, emergency and entertainment applications in vehicles. Nevertheless, these increasingly linked vehicles pose a range of new safety and security risks to both the host and its associated properties and may even have fatal consequences. Violations of national privacy and vehicle identities are a major obstacle to introducing forced contact protocols in vehicles. Location privacy refers to the privacy of the vehicle (driver) and the location of the vehicle. Whenever a vehicle sends a message, no one but authorized entities should know their real identity and location of the vehicle. All the messages sent by the vehicle must be authenticated before processing, hence location privacy is an important design aspect to be considered in VANETs operations. The novelty of this paper is that it specifically reviews location privacy in VANETs in terms of operational and safety concerns. Furthermore, it presents a critical analysis of various attacks, identity thefts, manipulation and other techniques in vogue for location privacy protection available in state-of-the-art solutions for VANETs. The efforts in this paper will help researchers to develop a great breadth of understanding pertaining to location privacy issues and various security threats encountered by VANETs and present the critical analysis of the available state-of-the- art solutions to maintain location privacy in VANETs.

Description: Universities and high schools constantly research and develop educational methods to improve the student learning process. This paper presents a novel educational methodology for students to obtain better learning results in Spanish grammar through an intervention that fuses differentiated instructions, standardized evaluation, and a Fuzzy Logic Type 2 system. This successful case study in a Mexico City high school reports improved Spanish grammar outcomes after the intervention. Before then, 79% of the students did not obtain satisfactory scores in a national Spanish evaluation. This educational methodology uses a flexible intervention plan that could be replicated or tailored for various educational scenarios and topics using the same framework.

Description: The General Data Protection Regulation (GDPR) harmonizes personal data protection laws across the European Union, affecting all sectors including the healthcare industry. For processing operations that pose a high risk for data subjects, a Data Protection Impact Assessment (DPIA) is mandatory from May 2018. Taking into account the criticality of the process and the importance of its results, for the protection of the patients’ health data, as well as the complexity involved and the lack of past experience in applying such methodologies in healthcare environments, this paper presents the main steps of a DPIA study and provides guidelines on how to carry them out effectively. To this respect, the Privacy Impact Assessment, Commission Nationale de l’Informatique et des Libertés (PIA-CNIL) methodology has been employed, which is also compliant with the privacy impact assessment tasks described in ISO/IEC 29134:2017. The work presented in this paper focuses on the first two steps of the DPIA methodology and more specifically on the identification of the Purposes of Processing and of the data categories involved in each of them, as well as on the evaluation of the organization’s GDPR compliance level and of the gaps (Gap Analysis) that must be filled-in. The main contribution of this work is the identification of the main organizational and legal requirements that must be fulfilled by the health care organization. This research sets the legal grounds for data processing, according to the GDPR and is highly relevant to any processing of personal data, as it helps to structure the process, as well as be aware of data protection issues and the relevant legislation.

Description: The classification of different fine hand movements from electroencephalogram (EEG) signals represents a relevant research challenge, e.g., in BCI applications for motor rehabilitation. Here, we analyzed two different datasets where fine hand movements (touch, grasp, palmar, and lateral grasp) were performed in a self-paced modality. We trained and tested a newly proposed CNN, and we compared its classification performance with two well-established machine learning models, namely, shrinkage-linear discriminant analysis (LDA) and Random Forest (RF). Compared to previous literature, we included neuroscientific evidence, and we trained our Convolutional Neural Network (CNN) model on the so-called movement-related cortical potentials (MRCPs). They are EEG amplitude modulations at low frequencies, i.e., (0.3,3) Hz that have been proved to encode several properties of the movements, e.g., type of grasp, force level, and speed. We showed that CNN achieved good performance in both datasets (accuracy of 0.70±0.11 and 0.64±0.10, for the two datasets, respectively), and they were similar or superior to the baseline models (accuracy of 0.68±0.10 and 0.62±0.07 with sLDA; accuracy of 0.70±0.15 and 0.61±0.07 with RF, with comparable performance in precision and recall). In addition, compared to the baseline, our CNN requires a faster pre-processing procedure, paving the way for its possible use in online BCI applications.

Description: Blockchain is a technology that can be applied in different sectors to solve various problems. As a complex system, agribusiness presents many possibilities to take advantage of blockchain technology. The main goal of this paper is to identify the purposes for which blockchain has been applied in the agribusiness sector, for which a PRISMA-based systematic review was carried out. The scientific literature corpus was accessed and selected from Elsevier’s Scopus and ISI of Knowledge’s Web of Science (WoS) platforms, using the PRISMA protocol procedures. Seventy-one articles were selected for analysis. Blockchain application in agribusiness is a novel topic, with the first publication dating from 2016. The technological development prevails more than blockchain applications since it has been addressed mainly in the Computer Sciences and Engineering. Blockchain applications for agribusiness management of financial, energy, logistical, environmental, agricultural, livestock, and industrial purposes have been reported in the literature. The findings suggest that blockchain brings many benefits when used in agribusiness supply chains. We concluded that the research on blockchain applications in agribusiness is only at an early stage, as many prototypes are being developed and tested in the laboratory. In the near future, blockchain will be increasingly applied across all economic sectors, including agribusiness, promoting greater reliability and agility in information with a reduced cost. Several gaps for future studies were observed, with significant value for science, industry, and society.

Description: Privacy protection has been an important concern with the great success of machine learning. In this paper, it proposes a multi-party privacy preserving machine learning framework, named PFMLP, based on partially homomorphic encryption and federated learning. The core idea is all learning parties just transmitting the encrypted gradients by homomorphic encryption. From experiments, the model trained by PFMLP has almost the same accuracy, and the deviation is less than 1%. Considering the computational overhead of homomorphic encryption, we use an improved Paillier algorithm which can speed up the training by 25–28%. Moreover, comparisons on encryption key length, the learning network structure, number of learning clients, etc. are also discussed in detail in the paper.

Description: Cloud-native network design, which leverages network virtualization and softwarization together with the service-oriented architectural principle, is transforming communication networks to a versatile platform for converged network-cloud/edge service provisioning. Intelligent and autonomous management is one of the most challenging issues in cloud-native future networks, and a wide range of machine learning (ML)-based technologies have been proposed for addressing different aspects of the management challenge. It becomes critical that the various management technologies are applied on the foundation of a consistent architectural framework with a holistic vision. This calls for standardization of new management architecture that supports seamless the integration of diverse ML-based technologies in cloud-native future networks. The goal of this paper is to provide a big picture of the recent developments of architectural frameworks for intelligent and autonomous management for future networks. The paper surveys the latest progress in the standardization of network management architectures including works by 3GPP, ETSI, and ITU-Tand analyzes how cloud-native network design may facilitate the architecture development for addressing management challenges. Open issues related to intelligent and autonomous management in cloud-native future networks are also discussed in this paper to identify some possible directions for future research and development.

Description: The authors of the Education 4.0 concept postulated a flexible combination of digital literacy, critical thinking, and problem-solving in educational environments linked to real-world scenarios. Therefore, teachers have been challenged to develop new methods and resources to integrate into their planning in order to help students develop these desirable and necessary skills; hence, the question: What are the characteristics of a teacher to consider within the framework of Education 4.0? This study was conducted in a higher education institution in Ecuador, with the aim to identify the teaching profile required in new undergraduate programs within the framework of Education 4.0 in order to contribute to decision-making about teacher recruitment, professional training and evaluation, human talent management, and institutional policies interested in connecting competencies with the needs of society. Descriptive and exploratory approaches, where we applied quantitative and qualitative instruments (surveys) to 337 undergraduate students in education programs and 313 graduates, were used. We also included interviews with 20 experts in the educational field and five focus groups with 32 chancellors, school principals, university professors, and specialists in the educational area. The data were triangulated, and the results were organized into the categories of (a) processes as facilitators (b), soft skills, (c) human sense, and (d) the use of technologies. The results outlined the profile of a professor as a specialized professional with competencies for innovation, complex problem solving, entrepreneurship, collaboration, international perspective, leadership, and connection with the needs of society. This research study may be of value to administrators, educational and social entrepreneurs, trainers, and policy-makers interested in implementing innovative training programs and in supporting management and policy decisions.

Description: IoT group communication allows users to control multiple IoT devices simultaneously. A convenient method for implementing this communication paradigm is by leveraging software-defined networking (SDN) and allowing IoT endpoints to “advertise” the resources that can be accessed through group communication. In this paper, we propose a solution for securing this process by preventing IoT endpoints from advertising “fake” resources. We consider group communication using the constrained application protocol (CoAP), and we leverage Web of Things (WoT) Thing Description (TD) to enable resources’ advertisement. In order to achieve our goal, we are using linked-data proofs. Additionally, we evaluate the application of zero-knowledge proofs (ZKPs) for hiding certain properties of a WoT-TD file.

Description: The data market concept has gained a lot of momentum in recent years, fuelled by initiatives to set up such markets, e.g., on the European level. Still, the typical data market concept aims at providing a centralised platform with all of its positive and negative side effects. Internal data markets, also called local or on-premise data markets, on the other hand, are set up to allow data trade inside an institution (e.g., between divisions of a large company) or between members of a small, well-defined consortium, thus allowing the remuneration of providing data inside these structures. Still, while research on securing global data markets has garnered some attention throughout recent years, the internal data markets have been treated as being more or less similar in this respect. In this paper, we outline the major differences between global and internal data markets with respect to security and why further research is required. Furthermore, we provide a fundamental model for a secure internal data market that can be used as a starting point for the generation of concrete internal data market models. Finally, we provide an overview on the research questions we deem most pressing in order to make the internal data market concept work securely, thus allowing for more widespread adoption.

Description: Quality of experience (QoE) is an important measure of users’ satisfaction regarding their network-based services, and it is widely employed today to provide a real assessment of the service quality as perceived by the end users. QoE measures can be used to improve application performance, as well as to optimize network resources and reallocate them as needed when the service quality degrades. While quantitative QoE assessments based on network parameters may provide insights into users’ experience, subjective assessments through direct feedback from the users have also gathered interest recently due to their accuracy and interactive nature. In this paper, we propose a framework that can be used to collect real-time QoE feedback through crowdsourcing and forward it to network controllers to enhance streaming routes. We analyze how QoE can be affected by different network conditions, and how different streaming protocols compare against each other when the network parameters change dynamically. We also compare the real-time user feedback to predefined network changes to measure if participants will be able to identify all degradation events, as well as to examine which combination of degradation events are noticeable to the participants. Our aim is to demonstrate that real-time QoE feedback can enhance cloud-based services and can adjust service quality on the basis of real-time, active participants’ interactions.

Description: Digital technologies are an opportunity to overcome disabilities, provided that accessibility is ensured. In this paper, we focus on visual accessibility and the way it is supported in Operating Systems (OS). The significant variability in this support has practical consequences, e.g., the difficulty to recommend or select an OS, or migrate from one OS to another. This suggests building a variability model for OS that would classify them and would serve as a reference. We propose a methodology to build such a variability model with the help of the Formal Concept Analysis (FCA) framework. In addition, as visual accessibility can be divided into several concerns (e.g., zoom, or contrast), we leverage an extension of FCA, namely Relational Concept Analysis. We also build an ontology to dispose of a standardized description of visual accessibility options. We apply our proposal to the analysis of the variability of a few representative operating systems.

Description: Handwriting analysis is playing an important role in user authentication or online writer identification for more than a decade. It has a significant role in different applications such as e-security, signature biometrics, e-health, gesture analysis, diagnosis system of Parkinson’s disease, Attention-deficit/hyperactivity disorders, analysis of vulnerable people (stressed, elderly, or drugged), prediction of gender, handedness and so on. Classical authentication systems are image-based, text-dependent, and password or fingerprint-based where the former one has the risk of information leakage. Alternatively, image processing and pattern-analysis-based systems are vulnerable to camera attributes, camera frames, light effect, and the quality of the image or pattern. Thus, in this paper, we concentrate on real-time and context-free handwriting data analysis for robust user authentication systems using digital pen-tablet sensor data. Most of the state-of-the-art authentication models show suboptimal performance for improper features. This research proposed a robust and efficient user identification system using an optimal feature selection technique based on the features from the sensor’s signal of pen and tablet devices. The proposed system includes more genuine and accurate numerical data which are used for features extraction model based on both the kinematic and statistical features of individual handwritings. Sensor data of digital pen-tablet devices generate high dimensional feature vectors for user identification. However, all the features do not play equal contribution to identify a user. Hence, to find out the optimal features, we utilized a hybrid feature selection model. Extracted features are then fed to the popular machine learning (ML) algorithms to generate a nonlinear classifier through training and testing phases. The experimental result analysis shows that the proposed model achieves more accurate and satisfactory results which ensure the practicality of our system for user identification with low computational cost.

Description: Volunteer computing uses millions of consumer computing devices (desktop and laptop computers, tablets, phones, appliances, and cars) to do high-throughput scientific computing. It can provide Exa-scale capacity, and it is a scalable and sustainable alternative to data-center computing. Currently, about 30 science projects use volunteer computing in areas ranging from biomedicine to cosmology. Each project has application programs with particular hardware and software requirements (memory, GPUs, VM support, and so on). Each volunteered device has specific hardware and software capabilities, and each device owner has preferences for which science areas they want to support. This leads to a scheduling problem: how to dynamically assign devices to projects in a way that satisfies various constraints and that balances various goals. We describe the scheduling policy used in Science United, a global manager for volunteer computing.

Description: Owing to rapid development of the Internet and the rise of the big data era, microblog has become the main means for people to spread and obtain information. If people can accurately predict the development trend of a microblog event, it will be of great significance for the government to carry out public relations activities on network event supervision and guide the development of microblog event reasonably for network crisis. This paper presents effective solutions to deal with trend prediction of microblog events’ popularity. Firstly, by selecting the influence factors and quantifying the weight of each factor with an information entropy algorithm, the microblog event popularity is modeled. Secondly, the singular spectrum analysis is carried out to decompose and reconstruct the time series of the popularity of microblog event. Then, the box chart method is used to divide the popularity of microblog event into various trend spaces. In addition, this paper exploits the Bi-LSTM model to deal with trend prediction with a sequence to label model. Finally, the comparative experimental analysis is carried out on two real data sets crawled from Sina Weibo platform. Compared to three comparative methods, the experimental results show that our proposal improves F1-score by up to 39%.

Description: As a result of the confinement due to the COVID-19 pandemic, various educational institutions migrated their face-to-face teaching modality to a virtual modality. This article presents the implementation of the Flipped Classroom model in a completely virtual format to develop grammatical competency in Spanish. The model used videos from YouTube, one of the leading global social network platforms, and the videoconferencing system Zoom, the tool selected by the studied educational institution to continue academic operations during the health confinement. The model was enriched with the Index for Learning Style test to provide more differentiated teaching. This study showed considerable improvement in the academic performance of high school students taking a Spanish course at the Mexico City campus of Tecnologico de Monterrey. Of the total sample, 98% increased their score by between 2 and 46 points, from a total of 100, in their grammatical competency in Spanish. Additionally, the student satisfaction survey showed that more than 90% considered the course methodology beneficial for developing their grammatical competency in Spanish. This study demonstrates the potential of the Flipped Classroom model in a virtual format. This teaching structure using the Flipped Classroom model could be replicated in various educational settings and for different areas of knowledge.

Description: As part of studies that employ health electronic records databases, this paper advocates the employment of graph theory for investigating drug-switching behaviors. Unlike the shared approach in this field (comparing groups that have switched with control groups), network theory can provide information about actual switching behavior patterns. After a brief and simple introduction to fundamental concepts of network theory, here we present (i) a Python script to obtain an adjacency matrix from a records database and (ii) an illustrative example of the application of network theory basic concepts to investigate drug-switching behaviors. Further potentialities of network theory (weighted matrices and the use of clustering algorithms), along with the generalization of these methods to other kinds of switching behaviors beyond drug switching, are discussed.

Description: In this work, we present an innovative approach for damage detection of infrastructures on-edge devices, exploiting a brain-inspired algorithm. The proposed solution exploits recurrent spiking neural networks (LSNNs), which are emerging for their theoretical energy efficiency and compactness, to recognise damage conditions by processing data from low-cost accelerometers (MEMS) directly on the sensor node. We focus on designing an efficient coding of MEMS data to optimise SNN execution on a low-power microcontroller. We characterised and profiled LSNN performance and energy consumption on a hardware prototype sensor node equipped with an STM32 embedded microcontroller and a digital MEMS accelerometer. We used a hardware-in-the-loop environment with virtual sensors generating data on an SPI interface connected to the physical microcontroller to evaluate the system with a data stream from a real viaduct. We exploited this environment also to study the impact of different on-sensor encoding techniques, mimicking a bio-inspired sensor able to generate events instead of accelerations. Obtained results show that the proposed optimised embedded LSNN (eLSNN), when using a spike-based input encoding technique, achieves 54% lower execution time with respect to a naive LSNN algorithm implementation present in the state-of-the-art. The optimised eLSNN requires around 47 kCycles, which is comparable with the data transfer cost from the SPI interface. However, the spike-based encoding technique requires considerably larger input vectors to get the same classification accuracy, resulting in a longer pre-processing and sensor access time. Overall the event-based encoding techniques leads to a longer execution time (1.49×) but similar energy consumption. Moving this coding on the sensor can remove this limitation leading to an overall more energy-efficient monitoring system.

Description: Building fires constitute a significant threat that affects property, the environment, and human health. The management of this risk requires an efficient fire evacuation system for buildings’ occupants. Therefore, a smart fire evacuation system that combines building information modeling (BIM) and smart technologies is proposed. The system provides the following capacities: (i) early fire detection; (ii) the evaluation of environmental data; (iii) the identification of the best evacuation path; and (iv) information for occupants about the best evacuation routes. The system was implemented in a research building at Lille University in France. The results show the system’s capacities and benefits, particularly for the identification of the best evacuation paths.

Description: This work highlights how the stiffness index, which is often used as a measure of stiffness for differential problems, can be employed to model the spread of fake news. In particular, we show that the higher the stiffness index is, the more rapid the transit of fake news in a given population. The illustration of our idea is presented through the stiffness analysis of the classical SIR model, commonly used to model the spread of epidemics in a given population. Numerical experiments, performed on real data, support the effectiveness of the approach.

Description: In biometric systems, the process of identifying or verifying people using facial data must be highly accurate to ensure a high level of security and credibility. Many researchers investigated the fairness of face recognition systems and reported demographic bias. However, there was not much study on face presentation attack detection technology (PAD) in terms of bias. This research sheds light on bias in face spoofing detection by implementing two phases. First, two CNN (convolutional neural network)-based presentation attack detection models, ResNet50 and VGG16 were used to evaluate the fairness of detecting imposer attacks on the basis of gender. In addition, different sizes of Spoof in the Wild (SiW) testing and training data were used in the first phase to study the effect of gender distribution on the models’ performance. Second, the debiasing variational autoencoder (DB-VAE) (Amini, A., et al., Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure) was applied in combination with VGG16 to assess its ability to mitigate bias in presentation attack detection. Our experiments exposed minor gender bias in CNN-based presentation attack detection methods. In addition, it was proven that imbalance in training and testing data does not necessarily lead to gender bias in the model’s performance. Results proved that the DB-VAE approach (Amini, A., et al., Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure) succeeded in mitigating bias in detecting spoof faces.

Description: Online roadshow is a relatively new concept that has higher flexibility and scalability compared to the physical roadshow. This is because online roadshow is accessible through digital devices anywhere and anytime. In a physical roadshow, organizations can measure the effectiveness of the roadshow by interacting with the customers. However, organizations cannot monitor the effectiveness of the online roadshow by using the same method. A good user experience is important to increase the advertising effects on the online roadshow website. In web usage mining, clustering can discover user access patterns from the weblog. By applying a clustering technique, the online roadshow website can be further improved to provide a better user experience. This paper presents a review of clustering techniques used in web usage mining, namely the partition-based, hierarchical, density-based, and fuzzy clustering techniques. These clustering techniques are analyzed from three perspectives: their similarity measures, the evaluation metrics used to determine the optimality of the clusters, and the functional purpose of applying the techniques to improve the user experience of the website. By applying clustering techniques in different stages of the user activities in the online roadshow website, the advertising effectiveness of the website can be enhanced in terms of its affordance, flow, and interactivity.

Description: In the science and engineering fields of study, a hands-on learning experience is as crucial a part of the learning process for the student as the theoretical aspect of a given subject. With the COVID-19 pandemic in 2020, educational institutions were forced to migrate to digital platforms to ensure the continuity of the imparted lectures. The online approach can be challenging for engineering programs, especially in courses that employ practical laboratory methods as the primary teaching strategies. Laboratory courses that include specialized hardware and software cannot migrate to a virtual environment without compromising the advantages that a hands-on method provides to the engineering student. This work assesses different approaches in the virtualization process of a laboratory facility, diving these into key factors such as required communication infrastructure and available technologies; it opens a discussion on the trends and possible obstacles in the virtualization of a Real-Time (RT) laboratory intended for Microgrid education in a power electronics laboratory course, exposing the main simulation strategies that can be used in an RT environment and how these have different effects on the learning process of student, as well as addressing the main competencies an engineering student can strengthen through interaction with RT simulation technologies.

Description: Radio frequency identification (RFID) technology facilitates a myriad of applications. In such applications, an efficient reader–tag interrogation process is crucial. Nevertheless, throughout reader–tag communication, significant amounts of time and power are consumed on inescapable simultaneous tag replies (i.e., collisions) due to the lack of carrier sensing at the tags. This paper proposes the modulation cutoff intervals (MCI) process as a novel reader–tag interaction given the lack of carrier sensing constraints in passive RFID tags. MCI is facilitated through a simple digital baseband modulation termination (DBMT) circuit at the tag. DBMT detects the continuous-wave cutoff by the reader. In addition, DBMT provides different flags based on the duration of the continuous-wave cutoff. Given this capability at the tag, the reader cuts off its continuous-wave transmission for predefined intervals to indicate different commands to the interrogated tag(s). The MCI process is applied to tag interrogation (or anti-collision) and tag-counting protocols. The MCI process effect was evaluated by the two protocols under high and low tag populations. The performance of such protocols was significantly enhanced with precise synchronization within time slots with more than 50% and more than 55.6% enhancement on time and power performance of anti-collision and counting protocols, respectively. Through the MCI process, fast and power-efficient tag identification is achieved in inventory systems with low and high tag mobility; alternatively, in addition to the rapid and power efficient interaction with tags, anonymous tag counting is conducted by the proposed process.

Description: Preferences or dislikes for specific numbers are ubiquitous in human society. In traditional Chinese culture, people show special preference for some numbers, such as 6, 8, 10, 100, 200, etc. By analyzing the data of 6.8 million users of Sina Weibo, one of the largest online social media platforms in China, we discover that users exhibit a distinct preference for the number 200, i.e., a significant fraction of users prefer to follow 200 friends. This number, which is very close to the Dunbar number that predicts the cognitive limit on the number of stable social relationships, motivates us to investigate how the preference for numbers in traditional Chinese culture is reflected on social media. We systematically portray users who prefer 200 friends and analyze their several important social features, including activity, popularity, attention tendency, regional distribution, economic level, and education level. We find that the activity and popularity of users with the preference for the number 200 are relatively lower than others. They are more inclined to follow popular users, and their social portraits change relatively slowly. Besides, users who have a stronger preference for the number 200 are more likely to be located in regions with underdeveloped economies and education. That indicates users with the preference for the number 200 are likely to be vulnerable groups in society and are easily affected by opinion leaders.

Description: Hindi is the official language of India and used by a large population for several public services like postal, bank, judiciary, and public surveys. Efficient management of these services needs language-based automation. The proposed model addresses the problem of handwritten Hindi character recognition using a machine learning approach. The pre-trained DCNN models namely; InceptionV3-Net, VGG19-Net, and ResNet50 were used for the extraction of salient features from the characters’ images. A novel approach of fusion is adopted in the proposed work; the DCNN-based features are fused with the handcrafted features received from Bi-orthogonal discrete wavelet transform. The feature size was reduced by the Principal Component Analysis method. The hybrid features were examined with popular classifiers namely; Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). The recognition cost was reduced by 84.37%. The model achieved significant scores of precision, recall, and F1-measure—98.78%, 98.67%, and 98.69%—with overall recognition accuracy of 98.73%.