ALBERT

Description: Numerical investigations on flow and heat transfer characteristics in the heat exchanger tube with the V-wavy surface are presented. The finite volume method with the SIMPLE algorithm is selected to solve the present problem. The effects of flow attack angles (α = 15°, 20°, 25°, 30°, 35°, 40°, 45°, 50°, 55°, and 60°) and flow directions (V-tip pointing downstream known as “V-Downstream” and V-tip pointing upstream known as “V-Upstream”) for the V-wavy surface on flow and heat transfer patterns are considered for both laminar and turbulent regions. The laminar regime is studied in the range Re = 100–1200, while the turbulent region is investigated in the range Re = 3000–10,000. The mechanisms on flow and heat transfer in the test section are reported. The numerical results reveal that the V-wavy surface changes the flow structure in the test section. The vortex flow is produced by the V-wavy surface. The vortex flow disturbs the thermal boundary layer on the heat transfer surface that is the reason for heat transfer and thermal performance enhancements. The optimum flow attack angles of the V-wavy surface for laminar and turbulent regimes are concluded.

Description: Operational simulators have a fundamental role in space programs. During a satellite operation, these simulators are essential for validating critical manoeuvres, testing new on-board software versions, and supporting the diagnosis of anomalies. With the purpose of reusing the operational simulators, the Brazilian National Institute for Space Research has proposed a new standard for the specification of the components that must be integrated in their in-house developed simulators. The new standard describes the behaviour of satellite subsystems using cause-effect tables that relate telecommands, electrical switches, equipment working states, energy consumption, telemetries, and operating modes of the subsystem. Using this new standard as input, this work proposes an approach that merges model-based testing and model checking to verify the correct implementation of new components in the satellite simulator. The verification approach consists of extracting state machines from the cause-effect tables and used it to automatically derive a test case suite. In order to validate the proposal, we applied it to three different satellite subsystems and assessed the results obtained from the test campaigns. In all the three cases, the proposed approach identified errors in the simulator components that were not initially detected by the traditional testing approach used at the Brazilian National Institute for Space Research.

Description: Advanced driver assistance systems (ADAS) have recently been thrust into the spotlight in the automotive industry as carmakers and technology companies pursue effective active safety systems and fully autonomous vehicles. Various sensors such as lidar (light detection and ranging), radar (radio detection and ranging), ultrasonic, and optical cameras are employed to provide situational awareness to vehicles in a highly dynamic environment. Radar has emerged as a primary sensor technology for both active/passive safety and comfort-advanced driver-assistance systems. Physically building and testing radar systems to demonstrate reliability is an expensive and time-consuming process. Simulation emerges as the most practical solution to designing and testing radar systems. This paper provides a complete, full physics simulation workflow for automotive radar using finite element method and asymptotic ray tracing electromagnetic solvers. The design and optimization of both transmitter and receiver antennas is presented. Antenna interaction with vehicle bumper and fascia is also investigated. A full physics-based radar scene corner case is modelled to obtain high-fidelity range-Doppler maps. Finally, this paper investigates the effects of inclined roads on late pedestrian detection and the effects of construction metal plate radar returns on false target identification. Possible solutions are suggested and validated. Results from this study show how pedestrian radar returns can be increased by over 16 dB for early detection along with a 27 dB reduction in road construction plate radar returns to suppress false target identification. Both solutions to the above corner cases can potentially save pedestrian lives and prevent future accidents.

Description: Modeling approach for mesoscopic model of concrete depicting mass transportation and physicochemical reaction is important since there is growing demand for accuracy and computational efficiency of numerical simulation. Mesoscopic numerical simulation considering binder, aggregate, and interfacial transition zone (ITZ) generally produces huge number of DOFs, which is inapplicable for full structure. In this paper, a two-dimensional multiscale approach describing three-phase structure of concrete was discussed numerically. An effective approach generating random aggregate in polygon based on checking centroid distance and intersection of line segment was introduced. Moreover, ITZ elements were built by parallel expanding the edge of aggregates on inner side. By combining mesoscopic model including full-graded aggregate and macroscopic model, cases related to diffusivity and width of ITZ, volume fraction, and grade of aggregate were studied regarding the consideration of multiscale compensation. Result clearly showed that larger analysis model in multiscale model expanded the diffusion space of chloride ion and decreased chloride content in front of rebar. Finally, this paper addressed some noteworthy conclusions about the chloride distribution and rebar corrosion regarding the configuration of rebar diameter, concrete cover, and exposure period.

Description: A buck converter is a step-down switching regulator. Buck convertors are being widely used in industrial applications that rely on regulated output voltage under fluctuating input voltage. A buck convertor works in the following modes: (a) current-controlled or (b) voltage-controlled mode. But these convertors manifest several nonlinearites because of the switching operation. Hence, in order to generate a quality output of the convertor, the design of a controller becomes crucial. In this paper, the synthesis of a QFT-based robust controller and prefilter has been carried out for an uncertain buck converter with varying input voltage and varying load. The controller synthesis problem has been posed as an optimization problem, and metaheuristic algorithms have been used for obtaining the optimal gains for the QFT controller and prefilter. By doing this, the QFT synthesis can be carried out in a single step instead of following the sequential classical QFT process on Nichols charts and the need for the generation of templates and bounds has be eliminated. The designed 2-degree-of-freedom QFT control system offers a robust behavior and efficiently handles the parametric uncertainties. The robustness of the designed controller has been confirmed through simulation results for large input voltage and load fluctuations.

Description: Presents the front cover for this issue of the publication.

Description: Six senior computer science educators answer questions about the current state of computer science education, software engineering, and licensing software engineers.

Description: Provides a listing of current staff, committee members and society officers.

Description: The Internet of Things is a new department with the mission of presenting fresh ideas and applications from a practitioner point of view. The authors are interested in showcasing articles about real, implemented Internet of Things (IoT) systems.

Description: Commemorating the 20th anniversary of IT Professional, the advisory board chair and four past editors in chief reflect on the first two decades of the magazine.

Description: In a case study where a Dutch small-to-medium enterprise (SME) implemented test-driven development and continuous integration, researchers observed that the SME discovered a higher number of defects compared to a baseline case study, and that there was an increase in the focus on quality and test applications.

Description: By providing access to data from numerous systems in one database and supporting the systems that can produce an appropriate customer experience, a customer data platform overcomes the limitations imposed by fragmented point solutions and presents a holistic approach to customer interactions.

Description: An introduction to the new Life in the C-Suite column, which will help C-level executives understand the vast digital world in which they live, and how they should leverage digital technology into their business processes and business models.

Description: Student Forum is a new column that intends to connect IT students with industry, government, and academia.

Description: The new IT Economics department seeks to advance the understanding of various microeconomic and macroeconomic issues that IT managers need to examine in their decisions to adopt and implement information and communications technology-related systems, services, processes, and practices.

Description: Provides a listing of current committee members and society officers.

Description: Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers.

Description: Traffic flow monitoring involves the capturing and dissemination of real-time traffic flow information for a road network. When a vehicle, a ferromagnetic object, travels along a road, it disturbs the ambient Earth’s magnetic field, causing its distortion. The resulting distortion carries vehicle signature containing traffic flow related information such as speed, count, direction, and classification. To extract such information in chaotic cities, a novel algorithm based on the resulting magnetic field distortion was developed using nonintrusive sensor localization. The algorithm extracts traffic flow information from resulting magnetic field distortions sensed by magnetic wireless sensor nodes located on the sides of the road. The model magnetic wireless sensor networks algorithm for local Earth’s magnetic field performance was evaluated through simulation using Dar es Salaam City traffic flow conditions. Simulation results for vehicular detection and count showed 93% and 87% success rates during normal and congested traffic states, respectively. Travel Time Index (TTI) was used as a congestion indicator, where different levels of congestion were evaluated depending on the traffic state with a performance of 87% and 88% success rates during normal and congested traffic flow, respectively.

Description: Developed power variation of turbogenerator (TG) steam turbine, which operates at the conventional LNG carrier, allows insight into the change in turbine exergy efficiency and exergy destruction during the increase in turbine power. Measurements of required operating parameters were performed in eight different TG steam turbine operating points during exploitation. Turbine exergy efficiency increases from turbine power of 500 kW up to 2700 kW, and maximum exergy efficiency was obtained at 70.13% of maximum turbine developed power (at 2700 kW) in each operating point. From turbine developed power of 2700 kW until the maximum power of 3850 kW, exergy efficiency decreases. Obtained change in TG turbine exergy efficiency is caused by an uneven intensity of increase in turbine developed power and steam mass flow through the turbine. TG steam turbine exergy destruction change is directly proportional to turbine load and to steam mass flow through the turbine—higher steam mass flow results in a higher turbine load which leads to the higher exergy destruction and vice versa. The higher share of turbine developed power and the lower share of turbine exergy destruction in the TG turbine exergy power inlet lead to higher turbine exergy efficiencies. At each observed operating point, turbine exergy efficiency in exploitation is lower when compared to the maximum obtained one for 8.39% to 12.03%.

Description: A mission reliability evaluation methodology for a signal traffic controller is presented in this paper. To develop the new evaluation methodology, this paper combines the Discrete Event System Specification (DEVS) formalism which has been popular in manufacturing area for three reasons: (1) its features compatible with the object-oriented modeling; (2) its rigorous formal definition; and (3) its support for the specifications of discrete event models in a hierarchical and modular manner. By using the DEVS formalism, we construct a simulation model which takes into account not only the characteristics of a traffic signal controller but also the operating environment. Once a model is constructed, it is possible to perform simulation experiments. The proposed methodology computes the mission reliability of a traffic signal controller by using a simulation record, and this information plays a vital role in preparing optimized maintenance policies that maximize availability or minimize life cycle costs.

Description: Model inversion Iterative Learning Control (ILC) for a class of nonsquare linear time variant/invariant multi-input multi-output (MIMO) systems is considered in this paper. A new ILC algorithm is developed based on -right inversion of nonsquare learning gain matrices to resolve the matrix inversion problems appeared in the direct model inversion of nonsquare MIMO systems. Furthermore, a sufficient and necessary monotonic convergence condition is established. With rigorous analysis, the proposed ILC scheme guarantees the convergence of the tracking error. To prove the effectiveness and to illustrate the performance of the proposed approach for linear time-invariant (LTI) and time-varying nonsquare systems, two illustrative examples are simulated.

Description: This paper presents a new position sensorless scheme in which a smoothing filter algorithm is proposed to improve the results obtained through Extended Kalman Filter (EKF) algorithm in tracking the rotor position for sensorless control of brushless DC motors. The rotor position and speed are estimated from the input voltage and current using the Extended Kalman Filter. States obtained through filtering in each sampling instant are refined, using the new smoothing algorithm, giving much better results. In the proposed method, the estimated state in previous instant is enhanced using the present measurement sample by the smoothing algorithm which is then used to improve the present estimated state variables. The complete system is modelled and simulated in MATLAB to verify the merit of the proposed smoothing algorithm. A comparison with conventional EKF is done for various load torque and speed conditions to establish the performance of the new sensorless algorithm. Simulation results show that the proposed smoothing technique offers better estimation accuracy. The peak error in the estimated speed and rotor position is considerably reduced when compared with EKF. The improved state estimate can be used as feedback for speed control of brushless DC motors in variable speed drives.

Description: The various applications of squeezing flow between two parallel surfaces such as those that are evident in manufacturing industries, polymer processing, compression, power transmission, lubricating system, food processing, and cooling amongst others call for further study on the effects of various parameters on the flow phenomena. In the present study, effects of nanoparticle geometry, slip, and temperature jump conditions on thermo-magneto-solutal squeezing flow of nanofluid between two parallel disks embedded in a porous medium are investigated, analyzed, and discussed. Similarity variables are used to transform the developed governing systems of nonlinear partial differential equations to systems of nonlinear ordinary differential equations. Homotopy perturbation method is used to solve the systems of the nonlinear ordinary differential equations. In order to verify the accuracy of the developed analytical solutions, the results of the homotopy perturbation method are compared with the results of the numerical method using the shooting method coupled with the fourth-order Runge–Kutta, and good agreements are established. Through the approximate analytical solutions, parametric studies are carried out to investigate the effects of nanoparticle size and shape, Brownian motion parameter, nanoparticle parameter, thermophoresis parameter, Hartmann number, Lewis number and pressure gradient parameters, slip, and temperature jump boundary conditions on thermo-solutal and hydromagnetic behavior of the nanofluid. This study will enhance and advance the understanding of nanofluidics such as energy conservation, friction reduction, and micromixing of biological samples.

Description: Inventory reliability of the life-cycle assessment (LCA) model highly depends on the data quality and normally exhibits significant uncertainty. A rigorous statistical methodology was established to capture and quantify the inherent uncertainties linked to the results of the LCA model. Two sources of uncertainty, data quality and model, were identified. The former was captured by converting the deterministic value to probability density function using beta distribution according to the evaluation matrix of data quality; the latter was assessed by prescribing variation interval through defining uncertainty factor. The functional equivalent pavement structures were designed, and the corresponding energy consumption and CO2 emission were calculated by the LCA model. A 10% variation was observed for the LCA results and within 30-year analysis span, at the 95% confidence level, and environmental burdens of cement pavement are higher than those of asphalt pavements while the comparison between the two asphalt pavements is not significant statistically. Therefore, the established statistical methodology is capable of capturing the uncertainty of the LCA model and quantifying the reliability the LCA results.

Description: We propose a general formal modeling and verification of the air traffic control system (ATC). This study is based on the International Civil Aviation Organization (ICAO), Federal Aviation Administration (FAA), and National Aeronautics and Space Administration (NASA) standards and recommendations. It provides a sophisticated assistance system that helps in visualizing aircrafts and presents automatic bugs detection. In such a critical safety system, the use of robust formal methods that assure bugs absence is highly required. Therefore, this work suggests a formalism of discrete transition systems based on abstraction and refinement along proofs. These ensure the consistency of the system by means of invariants preservation and deadlock freedom. Hence, all invariants hold permanently providing a handy solution for bugs absence verification. It follows that the said deadlock freedom ensures a continuous running of a given system. This specification and modeling technique enable the system to be corrected by construction.

Description: In recent years, metaheuristic algorithms have revolutionized the world with their better problem solving capacity. Any metaheuristic algorithm has two phases: exploration and exploitation. The ability of the algorithm to solve a difficult optimization problem depends upon the efficacy of these two phases. These two phases are tied with a bridging mechanism, which plays an important role. This paper presents an application of chaotic maps to improve the bridging mechanism of Grasshopper Optimisation Algorithm (GOA) by embedding 10 different maps. This experiment evolves 10 different chaotic variants of GOA, and they are named as Enhanced Chaotic Grasshopper Optimization Algorithms (ECGOAs). The performance of these variants is tested over ten shifted and biased unimodal and multimodal benchmark functions. Further, the applications of these variants have been evaluated on three-bar truss design problem and frequency-modulated sound synthesis parameter estimation problem. Results reveal that the chaotic mechanism enhances the performance of GOA. Further, the results of the Wilcoxon rank sum test also establish the efficacy of the proposed variants.

Description: We present a data-driven modeling (DDM) approach for static modeling of commercial photovoltaic (PV) microinverters. The proposed modeling approach handles all possible microinverter operating modes, including burst mode. No prior knowledge of internal components, structure, and control algorithm is assumed in developing the model. The approach is based on Artificial Neural Network (ANN) and Fast Fourier Transform (FFT). To generate the data used to train the model, a Power Hardware in the Loop (PHIL) approach is applied. Instantaneous inputs-outputs data are collected from the terminals of a commercial PV microinverter at time domain. Then, the collected data are converted to the frequency domain using Fast Fourier Transform (FFT). The ANNs that are the core of the DDM are developed in frequency domain. The outputs of the ANNs are then converted back to time domain for validation and use in system level simulation. The comparison between measured and simulated data validates the performance of the presented approach.

Description: This article presents a real photovoltaic module with modeling and simulations starting from the model of a photovoltaic (PV) cell. ,, and characteristics are simulated for different solar irradiation, temperatures, series resistances, and parallel resistances. For a real photovoltaic module (ALTIUS Module AFP-235W) there are estimated series and parallel resistances for which the energetical performances of the module have optimal values for a solar radiation of 1000 W/m2 and a temperature of the environment of 25°C. Temperature influence over the PV module performances is analyzed by using a thermal model of the ALTIUS Module AFP-235W using the finite element method. A temperature variation on the surface of the PV module is starting from a low value 40.15°C to a high value of 52.07°C. Current and power estimation are within the errors from 1.55% to about 4.3%. Experimental data are measured for the photovoltaic ALTIUS Module AFP-235W for an entire daylight.

Description: The growing amount of data in healthcare industry has made inevitable the adoption of big data techniques in order to improve the quality of healthcare delivery. Despite the integration of big data processing approaches and platforms in existing data management architectures for healthcare systems, these architectures face difficulties in preventing emergency cases. The main contribution of this paper is proposing an extensible big data architecture based on both stream computing and batch computing in order to enhance further the reliability of healthcare systems by generating real-time alerts and making accurate predictions on patient health condition. Based on the proposed architecture, a prototype implementation has been built for healthcare systems in order to generate real-time alerts. The suggested prototype is based on spark and MongoDB tools.

Description: The emergence of tuberculosis is at the peak; therefore to station it at its lower level we hereby try bioinformatics approach against Mycobacterium tuberculosis [M. tuberculosis] pathogenesis. Rv3906c is a conserved hypothetical gene of M. tuberculosis and contains many GTP binding protein motif DXXG which demonstrate that this gene might be processed in a GTP binding or in GTP hydrolyzing manner. This gene shows interaction with its adjacent genes as well as pcnA which is a polymerase and localized in the extracellular region and found to be a soluble protein. Rv3906c has binding pockets for calcium atom at various positions which prove that calcium might have some role during the process of this gene. GTP binding protein motif DXXG is present in various positions and calcium binds at this site with a C-score of 0.25. Mutational analysis on this motif shows the large decrease of stability after mutation of aspartate residue with glycine. Stress conditions like pH and temperature also change stability of the protein. A decrease in stability at this position might play a role in inhibition of survival of the pathogen. These computational studies of this gene might be a successful step towards drug development against tuberculosis.

Description: Concept-centered semantic maps were created based on a text-mining analysis of PubMed using the BiblioEngine_v2018 software. The objects (“concepts”) of a semantic map can be MeSH-terms or other terms (names of proteins, diseases, chemical compounds, etc.) structured in the form of controlled vocabularies. The edges between the two objects were automatically calculated based on the index of semantic similarity, which is proportional to the number of publications related to both objects simultaneously. On the one hand, an individual semantic map created based on the already published papers allows us to trace scientific inquiry. On the other hand, a prospective analysis based on the study of PubMed search history enables us to determine the possible directions for future research.

Description: Ticks cause approximately $17–19 billion economic losses to the livestock industry globally. Development of recombinant antitick vaccine is greatly hindered by insufficient knowledge and understanding of proteins expressed by ticks. Ticks secrete immunosuppressant proteins that modulate the host’s immune system during blood feeding; these molecules could be a target for antivector vaccine development. Recombinant p36, a 36 kDa immunosuppressor from the saliva of female Dermacentor andersoni, suppresses T-lymphocytes proliferation in vitro. To identify potential unique structural and dynamic properties responsible for the immunosuppressive function of p36 proteins, this study utilized bioinformatic tool to characterize and model structure of D. andersoni p36 protein. Evaluation of p36 protein family as suitable vaccine antigens predicted a p36 homolog in Rhipicephalus appendiculatus, the tick vector of East Coast fever, with an antigenicity score of 0.7701 that compares well with that of Bm86 (0.7681), the protein antigen that constitute commercial tick vaccine Tickgard™. Ab initio modeling of the D. andersoni p36 protein yielded a 3D structure that predicted conserved antigenic region, which has potential of binding immunomodulating ligands including glycerol and lactose, found located within exposed loop, suggesting a likely role in immunosuppressive function of tick p36 proteins. Laboratory confirmation of these preliminary results is necessary in future studies.

Description: Hydrophobic-Polar model is a simplified representation of Protein Structure Prediction (PSP) problem. However, even with the HP model, the PSP problem remains NP-complete. This work proposes a systematic and problem specific design for operators of the evolutionary program which hybrids with local search hill climbing, to efficiently explore the search space of PSP and thereby obtain an optimum conformation. The proposed algorithm achieves this by incorporating the following novel features: (i) new initialization method which generates only valid individuals with (rather than random) better fitness values; (ii) use of probability-based selection operators that limit the local convergence; (iii) use of secondary structure based mutation operator that makes the structure more closely to the laboratory determined structure; and (iv) incorporating all the above-mentioned features developed a complete two-tier framework. The developed framework builds the protein conformation on the square and triangular lattice. The test has been performed using benchmark sequences, and a comparative evaluation is done with various state-of-the-art algorithms. Moreover, in addition to hypothetical test sequences, we have tested protein sequences deposited in protein database repository. It has been observed that the proposed framework has shown superior performance regarding accuracy (fitness value) and speed (number of generations needed to attain the final conformation). The concepts used to enhance the performance are generic and can be used with any other population-based search algorithm such as genetic algorithm, ant colony optimization, and immune algorithm.

Description: We performed locus similarity calculation by measuring fuzzy intersection between individual locus and reference locus and then performed CODIS STR-DNA similarity calculation. The fuzzy intersection calculation enables a more robust CODIS STR-DNA similarity calculation due to imprecision caused by noise produced by PCR machine. We also proposed shifted convoluted Gaussian fuzzy number (SCGFN) and Gaussian fuzzy number (GFN) to represent each locus value as improvement of triangular fuzzy number (TFN) as used in previous research. Compared to triangular fuzzy number (TFN), GFN is more realistic to represent uncertainty of locus information because the distribution is assumed to be Gaussian. Then, the original Gaussian fuzzy number (GFN) is convoluted with distribution of certain ethnic locus information to produce the new SCGFN which more represents ethnic information compared to original GFN. Experiments were done for the following cases: people with family relationships, people of the same tribe, and certain tribal populations. The statistical test with analysis of variance (ANOVA) shows the difference in similarity between SCGFN, GFN, and TFN with a significant level of 95%. The Tukey method in ANOVA shows that SCGFN yields a higher similarity which means being better than the GFN and TFN methods. The proposed method enables CODIS STR-DNA similarity calculation which is more robust to noise and performed better CODIS similarity calculation involving familial and tribal relationships.

Description: Nowadays, microarray technology has become one of the popular ways to study gene expression and diagnosis of disease. National Center for Biology Information (NCBI) hosts public databases containing large volumes of biological data required to be preprocessed, since they carry high levels of noise and bias. Robust Multiarray Average (RMA) is one of the standard and popular methods that is utilized to preprocess the data and remove the noises. Most of the preprocessing algorithms are time-consuming and not able to handle a large number of datasets with thousands of experiments. Parallel processing can be used to address the above-mentioned issues. Hadoop is a well-known and ideal distributed file system framework that provides a parallel environment to run the experiment. In this research, for the first time, the capability of Hadoop and statistical power of R have been leveraged to parallelize the available preprocessing algorithm called RMA to efficiently process microarray data. The experiment has been run on cluster containing 5 nodes, while each node has 16 cores and 16 GB memory. It compares efficiency and the performance of parallelized RMA using Hadoop with parallelized RMA using affyPara package as well as sequential RMA. The result shows the speed-up rate of the proposed approach outperforms the sequential approach and affyPara approach.

Description: lane-change path imposes symmetric conditions on the path geometric properties. This paper presents the comparative study of time-optimal velocities to minimize the time needed for traversal of three planar symmetric parametric polynomial lane-change paths followed by an autonomous vehicle, assuming that the neighboring lane is free. A simulated model based on unicycle that accounts for the acceleration and velocity bounds and is particularly simple for generating the time-optimal path parameterization of each lane-change path is adopted. We base the time-optimal trajectory simulations on numerical integration on a path basis under two different end conditions representing sufficient and restricted steering spaces with remarkable difference in allowable maximum curvature. The rest-to-rest lane-change maneuvering simulations highlight the effect of the most relevant path geometric properties on minimal travel time: a faster lane-change curve such as a quintic Bezier curve followed by a unicycle tends to be shorter in route length and lower in maximum curvature to have achievable highest speed at the maximum curvature points. The results have implications to path selection for parallel parking and allow the design of continuous acceleration profile via time scaling for smooth, faster motion along a given path. This could provide a reference for on-road lane-change trajectory planning along a given path other than parametric polynomials for significantly more complex, complete higher-dimensional highly nonlinear dynamic model of autonomous ground vehicle considering aerodynamic forces, tire and friction forces of tire-ground interaction, and terrain topology in real-world.

Description: In this paper, a novel swarm intelligence-based ensemble metaheuristic optimization algorithm, called Structured Clanning-based Ensemble Optimization, is proposed for solving complex numerical optimization problems. The proposed algorithm is inspired by the complex and diversified behaviour present within the fission-fusion-based social structure of the elephant society. The population of elephants can consist of various groups with relationship between individuals ranging from mother-child bond, bond groups, independent males, and strangers. The algorithm tries to model this individualistic behaviour to formulate an ensemble-based optimization algorithm. To test the efficiency and utility of the proposed algorithm, various benchmark functions of different geometric properties are used. The algorithm performance on these test benchmarks is compared to various state-of-the-art optimization algorithms. Experiments clearly showcase the success of the proposed algorithm in optimizing the benchmark functions to better values.

Description: Designs of buildings are changing with emerging demands of several aesthetical features and efficient design based on geometry. Development of new building materials and construction techniques have enabled us to build new buildings which are tall and unsymmetrical, but unfortunately such structures are more susceptible to wind loads. Thus it becomes necessary to estimate wind loads with higher degree of confidence. Although ample information regarding wind load on symmetrical and regular structure is available in various international codes, they lack the study of effect of wind forces on unsymmetrical structures. This paper presents experimental and numerical studies of the wind effect on commonly used C-shaped buildings with varying aspect ratio and its optimization caused by the alteration of angle of incidence. Furthermore, results obtained by numerical analysis have been validated with the experimental one. For this study, numerical analysis has been carried out using ANSYS Fluent with k-ε model of turbulence. Computational fluid dynamics (CFD) techniques is used to evaluate the surface pressure on various faces of the model for angle of attack of 0° to 180° at an interval of 30° in a subsonic open circuit wind tunnel. The results found by CFD technique are well compared with the experimental results which suggest the feasibility of using this technique of predicting wind pressures on building efficiently and accurately.

Description: Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the “perfect single frame detector”. We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech pedestrian dataset). After manually clustering the frequent errors of a top detector, we characterise both localisation and background-versus-foreground errors. To address localisation errors we study the impact of training annotation noise on the detector performance, and show that we can improve results even with a small portion of sanitised training data. To address background/foreground discrimination, we study convnets for pedestrian detection, and discuss which factors affect their performance. Other than our in-depth analysis, we report top performance on the Caltech pedestrian dataset, and provide a new sanitised set of training and test annotations.

Description: This paper addresses the problem of robust and efficient relative rotation averaging in the context of large-scale Structure from Motion. Relative rotation averaging finds global or absolute rotations for a set of cameras from a set of observed relative rotations between pairs of cameras. We propose a generalized framework of relative rotation averaging that can use different robust loss functions and jointly optimizes for all the unknown camera rotations. Our method uses a quasi-Newton optimization which results in an efficient iteratively reweighted least squares (IRLS) formulation that works in the Lie algebra of the 3D rotation group. We demonstrate the performance of our approach on a number of large-scale data sets. We show that our method outperforms existing methods in the literature both in terms of speed and accuracy.

Description: Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants engaged in multi-party interaction while they move around and turn their heads towards the other participants rather than facing the cameras and the microphones. Multiple-person visual tracking is combined with multiple speech-source localization in order to tackle the speech-to-person association problem. The latter is solved within a novel audio-visual fusion method on the following grounds: binaural spectral features are first extracted from a microphone pair, then a supervised audio-visual alignment technique maps these features onto an image, and finally a semi-supervised clustering method assigns binaural spectral features to visible persons. The main advantage of this method over previous work is that it processes in a principled way speech signals uttered simultaneously by multiple persons. The diarization itself is cast into a latent-variable temporal graphical model that infers speaker identities and speech turns, based on the output of an audio-visual association process, executed at each time slice, and on the dynamics of the diarization variable itself. The proposed formulation yields an efficient exact inference procedure. A novel dataset, that contains audio-visual training data as well as a number of scenarios involving several participants engaged in formal and informal dialogue, is introduced. The proposed method is thoroughly tested and benchmarked with respect to several state-of-the art diarization algorithms.

Description: The capabilities of (I) learning transferable knowledge across domains; and (II) fine-tuning the pre-learned base knowledge towards tasks with considerably smaller data scale are extremely important. Many of the existing transfer learning techniques are supervised approaches, among which deep learning has the demonstrated power of learning domain transferrable knowledge with large scale network trained on massive amounts of labeled data. However, in many biomedical tasks, both the data and the corresponding label can be very limited, where the unsupervised transfer learning capability is urgently needed. In this paper, we proposed a novel multi-scale convolutional sparse coding (MSCSC) method, that (I) automatically learns filter banks at different scales in a joint fashion with enforced scale-specificity of learned patterns; and (II) provides an unsupervised solution for learning transferable base knowledge and fine-tuning it towards target tasks. Extensive experimental evaluation of MSCSC demonstrates the effectiveness of the proposed MSCSC in both regular and transfer learning tasks in various biomedical domains.

Description: Learning visual representations from web data has recently attracted attention for object recognition. Previous studies have mainly focused on overcoming label noise and data bias and have shown promising results by learning directly from web data. However, we argue that it might be better to transfer knowledge from existing human labeling resources to improve performance at nearly no additional cost. In this paper, we propose a new semi-supervised method for learning via web data. Our method has the unique design of exploiting strong supervision, i.e., in addition to standard image-level labels, our method also utilizes detailed annotations including object bounding boxes and part landmarks. By transferring as much knowledge as possible from existing strongly supervised datasets to weakly supervised web images, our method can benefit from sophisticated object recognition algorithms and overcome several typical problems found in webly-supervised learning. We consider the problem of fine-grained visual categorization, in which existing training resources are scarce, as our main research objective. Comprehensive experimentation and extensive analysis demonstrate encouraging performance of the proposed approach, which, at the same time, delivers a new pipeline for fine-grained visual categorization that is likely to be highly effective for real-world applications.

Description: We are motivated by the need for a generic object proposal generation algorithm which achieves good balance between object detection recall, proposal localization quality and computational efficiency. We propose a novel object proposal algorithm, BING++ , which inherits the virtue of good computational efficiency of BING [1] but significantly improves its proposal localization quality. At high level we formulate the problem of object proposal generation from a novel probabilistic perspective, based on which our BING++ manages to improve the localization quality by employing edges and segments to estimate object boundaries and update the proposals sequentially. We propose learning the parameters efficiently by searching for approximate solutions in a quantized parameter space for complexity reduction. We demonstrate the generalization of BING++ with the same fixed parameters across different object classes and datasets. Empirically our BING++ can run at half speed of BING on CPU, but significantly improve the localization quality by 18.5 and 16.7 percent on both VOC2007 and Microhsoft COCO datasets, respectively. Compared with other state-of-the-art approaches, BING++ can achieve comparable performance, but run significantly faster.

Description: Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit's contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines $L_{0}$ , $L_{1}$ and $L_{2}$ regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture.

Description: The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method aims at generating a set of high-quality 3D object proposals by exploiting stereo imagery. We formulate the problem as minimizing an energy function that encodes object size priors, placement of objects on the ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. We then exploit a CNN on top of these proposals to perform object detection. In particular, we employ a convolutional neural net (CNN) that exploits context and depth information to jointly regress to 3D bounding box coordinates and object pose. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. When combined with the CNN, our approach outperforms all existing results in object detection and orientation estimation tasks for all three KITTI object classes. Furthermore, we experiment also with the setting where LIDAR information is available, and show that using both LIDAR and stereo leads to the best result.

Description: Phylogenetic tree reconciliation is an important technique for reconstructing the evolutionary histories of species and genes and other dependent entities. Reconciliation is typically performed in a maximum parsimony framework and the number of optimal reconciliations can grow exponentially with the size of the trees, making it difficult to understand the solution space. This paper demonstrates how a small number of reconciliations can be found that collectively contain the most highly supported events in the solution space. While we show that the formal problem is NP-complete, we give a $1-frac{1}{e}$ approximation algorithm, experimental results that indicate its effectiveness, and the new DTL-RnB software tool that uses our algorithms to summarize the space of optimal reconciliations ( www.cs.hmc.edu/dtlrnb ).

Description: We propose a methodology for model-based fault detection and diagnosis for stochastic Boolean dynamical systems indirectly observed through a single time series of transcriptomic measurements using Next Generation Sequencing (NGS) data. The fault detection consists of an innovations filter followed by a fault certification step, and requires no knowledge about the possible system faults. The innovations filter uses the optimal Boolean state estimator, called the Boolean Kalman Filter (BKF). In the presence of knowledge about the possible system faults, we propose an additional step of fault diagnosis based on a multiple model adaptive estimation (MMAE) method consisting of a bank of BKFs running in parallel. Performance is assessed by means of false detection and misdiagnosis rates, as well as average times until correct detection and diagnosis. The efficacy of the proposed methodology is demonstrated via numerical experiments using a p53-MDM2 negative feedback loop Boolean network with stuck-at faults that model molecular events commonly found in cancer.

Description: New de novo transcriptome assembly and annotation methods provide an incredible opportunity to study the transcriptome of organisms that lack an assembled and annotated genome. There are currently a number of de novo transcriptome assembly methods, but it has been difficult to evaluate the quality of these assemblies. In order to assess the quality of the transcriptome assemblies, we composed a workflow of multiple quality check measurements that in combination provide a clear evaluation of the assembly performance. We presented novel transcriptome assemblies and functional annotations for Pacific Whiteleg Shrimp ( Litopenaeus vannamei ), a mariculture species with great national and international interest, and no solid transcriptome/genome reference. We examined Pacific Whiteleg transcriptome assemblies via multiple metrics, and provide an improved gene annotation. Our investigations show that assessing the quality of an assembly purely based on the assembler's statistical measurements can be misleading; we propose a hybrid approach that consists of statistical quality checks and further biological-based evaluations.

Description: Hi-C technology, a chromosome conformation capture (3C) based method, has been developed to capture genome-wide interactions at a given resolution. The next challenge is to reconstruct 3D structure of genome from the 3C-derived data computationally. Several existing methods have been proposed to obtain a consensus structure or ensemble structures. These methods can be categorized as probabilistic models or restraint-based models. In this paper, we propose a method, named ShRec3D+, to infer a consensus 3D structure of a genome from Hi-C data. The method is a two-step algorithm which is based on ChromSDE and ShRec3D methods. First, correct the conversion factor by golden section search for converting interaction frequency data to a distance weighted graph. Second, apply shortest-path algorithm and multi-dimensional scaling (MDS) algorithm to compute the 3D coordinates of a set of genomic loci from the distance graph. We validate ShRec3D+ accuracy on both simulation data and publicly Hi-C data. Our test results indicate that our method successfully corrects the parameter with a given resolution, is more accurate than ShRec3D, and is more efficient and robust than ChromSDE.

Description: Determining gender by examining the human brain is not a simple task because the spatial structure of the human brain is complex, and no obvious differences can be seen by the naked eyes. In this paper, we propose a novel three-dimensional feature descriptor, the three-dimensional weighted histogram of gradient orientation (3D WHGO) to describe this complex spatial structure. The descriptor combines local information for signal intensity and global three-dimensional spatial information for the whole brain. We also improve a framework to address the classification of three-dimensional images based on MRI. This framework, three-dimensional spatial pyramid, uses additional information regarding the spatial relationship between features. The proposed method can be used to distinguish gender at the individual level. We examine our method by using the gender identification of individual magnetic resonance imaging (MRI) scans of a large sample of healthy adults across four research sites, resulting in up to individual-level accuracies under the optimized parameters for distinguishing between females and males. Compared with previous methods, the proposed method obtains higher accuracy, which suggests that this technology has higher discriminative power. With its improved performance in gender identification, the proposed method may have the potential to inform clinical practice and aid in research on neurological and psychiatric disorders.

Description: Ultra-high dimensional variable selection has become increasingly important in analysis of neuroimaging data. For example, in the Autism Brain Imaging Data Exchange (ABIDE) study, neuroscientists are interested in identifying important biomarkers for early detection of the autism spectrum disorder (ASD) using high resolution brain images that include hundreds of thousands voxels. However, most existing methods are not feasible for solving this problem due to their extensive computational costs. In this work, we propose a novel multiresolution variable selection procedure under a Bayesian probit regression framework. It recursively uses posterior samples for coarser-scale variable selection to guide the posterior inference on finer-scale variable selection, leading to very efficient Markov chain Monte Carlo (MCMC) algorithms. The proposed algorithms are computationally feasible for ultra-high dimensional data. Also, our model incorporates two levels of structural information into variable selection using Ising priors: the spatial dependence between voxels and the functional connectivity between anatomical brain regions. Applied to the resting state functional magnetic resonance imaging (R-fMRI) data in the ABIDE study, our methods identify voxel-level imaging biomarkers highly predictive of the ASD, which are biologically meaningful and interpretable. Extensive simulations also show that our methods achieve better performance in variable selection compared to existing methods.

Description: In systems neuroscience, it is becoming increasingly common to record the activity of hundreds of neurons simultaneously via electrode arrays. The ability to accurately measure the causal interactions among multiple neurons in the brain is crucial to understanding how neurons work in concert to generate specific brain functions. The development of new statistical methods for assessing causal influence between spike trains is still an active field of neuroscience research. Here, we suggest a copula-based Granger causality measure for the analysis of neural spike train data. This method is built upon our recent work on copula Granger causality for the analysis of continuous-valued time series by extending it to point-process neural spike train data. The proposed method is therefore able to reveal nonlinear and high-order causality in the spike trains while retaining all the computational advantages such as model-free, efficient estimation, and variability assessment of Granger causality. The performance of our algorithm can be further boosted with time-reversed data. Our method performed well on extensive simulations, and was then demonstrated on neural activity simultaneously recorded from primary visual cortex of a monkey performing a contour detection task.

Description: The focus of this paper is the frequent gene team problem. Given a quorum parameter μ and a set of m genomes, the problem is to find gene teams that occur in at least μ of the given genomes. In this paper, a new algorithm is presented. Previous solutions are efficient only when μ is small. Unlike previous solutions, the presented algorithm does not rely on examining every combination of μ genomes. Its time complexity is independent of μ. Under some realistic assumptions, the practical running time is estimated to be $O(m^{2}n^{2}; {mathrm{lg}};n)$ , where n is the maximum length of the input genomes. Experiments showed that the presented algorithm is extremely efficient. For any μ, it takes less than 1 second to process 100 bacterial genomes and takes only 10 minutes to process 2,000 genomes. The presented algorithm can be used as an effective tool for large scale genome analyses.

Description: In this era of genome-wide association studies (GWAS), the quest for understanding the genetic architecture of complex diseases is rapidly increasing more than ever before. The development of high throughput genotyping and next generation sequencing technologies enables genetic epidemiological analysis of large scale data. These advances have led to the identification of a number of single nucleotide polymorphisms (SNPs) responsible for disease susceptibility. The interactions between SNPs associated with complex diseases are increasingly being explored in the current literature. These interaction studies are mathematically challenging and computationally complex. These challenges have been addressed by a number of data mining and machine learning approaches. This paper reviews the current methods and the related software packages to detect the SNP interactions that contribute to diseases. The issues that need to be considered when developing these models are addressed in this review. The paper also reviews the achievements in data simulation to evaluate the performance of these models. Further, it discusses the future of SNP interaction analysis.

Description: Motifs in complex biological, technological, and social networks, or in other types of networks are connected to patterns that occur at significantly higher frequency compared to similar random networks. Finding motifs helps scientists to know more about networks’ structure and function, and this goal cannot be achieved without efficient algorithms. Existing methods for counting network motifs are extremely costly in CPU time and memory consumption. In addition, they restrict to the larger motifs. In this paper, a new algorithm called FraMo is presented based on ‘fractal theory’. This method consists of three phases: at first, a complex network is converted to a multifractal network. Then, using maximum likelihood estimation, distribution parameters is estimated for the multifractal network, and at last the approximate number of network motifs is calculated. Experimental results on several benchmark datasets show that our algorithm can efficiently approximate the number of motifs in any size in undirected networks and compare its performance favorably with similar existing algorithms in terms of CPU time and memory usage.

Description: Regions of interest (ROIs) based classification has been widely investigated for analysis of brain magnetic resonance imaging (MRI) images to assist the diagnosis of Alzheimer's disease (AD) including its early warning and developing stages, e.g., mild cognitive impairment (MCI) including MCI converted to AD (MCIc) and MCI not converted to AD (MCInc). Since an ROI representation of brain structures is obtained either by pre-definition or by adaptive parcellation, the corresponding ROI in different brains can be measured. However, due to noise and small sample size of MRI images, representations generated from single or multiple ROIs may not be sufficient to reveal the underlying anatomical differences between the groups of disease-affected patients and health controls (HC). In this paper, we employ a whole brain hierarchical network (WBHN) to represent each subject. The whole brain of each subject is divided into 90, 54, 14, and 1 regions based on Automated Anatomical Labeling (AAL) atlas. The connectivity between each pair of regions is computed in terms of Pearson's correlation coefficient and used as classification feature. Then, to reduce the dimensionality of features, we select the features with higher $F-$ scores. Finally, we use multiple kernel boosting (MKBoost) algorithm to perform the classification. Our proposed method is evaluated on MRI images of 710 subjects (200 AD, 120 MCIc, 160 MCInc, and 230 HC) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our proposed method achieves an accuracy of 94.65 percent and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.954 for AD/HC classification, an accuracy of 89.63 percent and an AUC of 0.907 for AD/MCI classification, an- accuracy of 85.79 percent and an AUC of 0.826 for MCI/HC classification, and an accuracy of 72.08 percent and an AUC of 0.716 for MCIc/MCInc classification, respectively. Our results demonstrate that our proposed method is efficient and promising for clinical applications for the diagnosis of AD via MRI images.

Description: Enumeration of chemical structures is useful for drug design, which is one of the main targets of computational biology and bioinformatics. A chemical graph $G$ with no other cycles than benzene rings is called tree-like , and becomes a tree $T$ possibly with multiple edges if we contract each benzene ring into a single virtual atom of valence 6. All tree-like chemical graphs with a given tree representation $T$ are called the substituted benzene isomers of $T$ . When we replace each virtual atom in $T$ with a benzene ring to obtain a substituted benzene isomer, distinct isomers of $T$ are caused by the difference in arrangements of atom groups around a benzene ring. In this paper, we propose an efficient algorithm that enumerates all substituted benzene isomers of a given tree representation $T$ . Our algorithm first counts the number

Description: Determining the dynamics of pathways associated with cancer progression is critical for understanding the etiology of diseases. Advances in biological technology have facilitated the simultaneous genomic profiling of multiple patients at different clinical stages, thus generating the dynamic genomic data for cancers. Such data provide enable investigation of the dynamics of related pathways. However, methods for integrative analysis of dynamic genomic data are inadequate. In this study, we develop a novel nonnegative matrix factorization algorithm for dynamic modules ( NMF-DM ), which simultaneously analyzes multiple networks for the identification of stage-specific and dynamic modules. NMF-DM applies the temporal smoothness framework by balancing the networks at the current stage and the previous stage. Experimental results indicate that the NMF-DM algorithm is more accurate than the state-of-the-art methods in artificial dynamic networks. In breast cancer networks, NMF-DM reveals the dynamic modules that are important for cancer stage transitions. Furthermore, the stage-specific and dynamic modules have distinct topological and biochemical properties. Finally, we demonstrate that the stage-specific modules significantly improve the accuracy of cancer stage prediction. The proposed algorithm provides an effective way to explore the time-dependent cancer genomic data.

Description: MicroRNAs (miRNAs) are known as an important indicator of cancers. The presence of cancer can be detected by identifying the responsible miRNAs. A fuzzy-rough entropy measure (FREM) is developed which can rank the miRNAs and thereby identify the relevant ones. FREM is used to determine the relevance of a miRNA in terms of separability between normal and cancer classes. While computing the FREM for a miRNA, fuzziness takes care of the overlapping between normal and cancer expressions, whereas rough lower approximation determines their class sizes. MiRNAs are sorted according to the highest relevance (i.e., the capability of class separation) and a percentage among them is selected from the top ranked ones. FREM is also used to determine the redundancy between two miRNAs and the redundant ones are removed from the selected set, as per the necessity. A histogram based patient selection method is also developed which can help to reduce the number of patients to be dealt during the computation of FREM, while compromising very little with the performance of the selected miRNAs for most of the data sets. The superiority of the FREM as compared to some existing methods is demonstrated extensively on six data sets in terms of sensitivity, specificity, and $F$ score. While for these data sets the $F$ score of the miRNAs selected by our method varies from 0.70 to 0.91 using SVM, those results vary from 0.37 to 0.90 for some other methods. Moreover, all the selected miRNAs corroborate with the findings of biological investigations or pathway analysis tools. The source code of FREM is available at http://www.jayanta.droppages.com/FREM.html .

Description: Identification of combinatorial markers from multiple data sources is a challenging task in bioinformatics. Here, we propose a novel computational framework for identifying significant combinatorial markers ( $SCM$ s) using both gene expression and methylation data. The gene expression and methylation data are integrated into a single continuous data as well as a (post-discretized) boolean data based on their intrinsic (i.e., inverse) relationship. A novel combined score of methylation and expression data (viz., $CoMEx$ ) is introduced which is computed on the integrated continuous data for identifying initial non-redundant set of genes. Thereafter, (maximal) frequent closed homogeneous genesets are identified using a well-known biclustering algorithm applied on the integrated boolean data of the determined non-redundant set of genes. A novel sample-based weighted support ( $WS$ ) is then proposed that is consecutively calculated on the integrated boolean data of the determined non-redundant set of genes in order to identify the non-redundant significant genesets. The top few resulting genesets are identified as potential $SCM$ s. Since our proposed method generates a smaller number of significant non-redundant genesets than those by other popular methods, the method is much faster than the others. Application of the proposed techniq- e on an expression and a methylation data for Uterine tumor or Prostate Carcinoma produces a set of significant combination of markers. We expect that such a combination of markers will produce lower false positives than individual markers.

Description: In this paper, we seek to improve deep neural networks by generalizing the pooling operations that play a central role in the current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in: (1) learning a pooling function via (two strategies of) combining of max and average pooling, and (2) learning a pooling function in the form of a tree-structured fusion of pooling filters that are themselves learned. In our experiments every generalized pooling operation we explore improves performance when used in place of average or max pooling. We experimentally demonstrate that the proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets. These benefits come with only a light increase in computational overhead during training (ranging from additional 5 to 15 percent in time complexity) and a very modest increase in the number of model parameters (e.g., additional 1, 9, and 27 parameters for mixed, gated, and 2-level tree pooling operators, respectively). To gain more insights about our proposed pooling methods, we also visualize the learned pooling masks and the embeddings of the internal feature responses for different pooling operations. Our proposed pooling operations are easy to implement and can be applied within various deep neural network architectures.

Description: Presents the front cover for this issue of the publication.

Description: The IEEE Geocience and Remote Sensing Society (GRSS) Nominations Committee calls upon our membership to nominate members to serve on the GRSS Administrative Committee (AdCom). A nominating petition carrying a minimum of 2% of the names of eligible Society members (~70), excluding students, shall automatically place that nominee on the slate. Such nominations must be made by 30 April 2018. The Nominations Committee may choose to include a name on the slate regardless of the number of names generated by the nominating petition process. Prior to submission of a nomination petition, the petitioner shall have determined that the nominee named in the petition is willing to serve if elected; and evidence of such willingness to serve shall be submitted with the petition. Candidates must be current Members of the IEEE and the GRSS. Petition signatures can be submitted electronically through the Society website or by signing, scanning, and electronically mailing the pdf file of the paper petition. The name of each member signing the paper petition shall be clearly printed or typed. For identification purposes of signatures on paper petitions, membership numbers and addresses as listed in the official IEEE Membership records shall be included. Only signatures submitted electronically through the Society website or original signatures on paper petitions shall be accepted. Further information is provided here.

Description: Presents the table of contents for this issue of the publication.

Description: Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Description: Presents the President’s message for this issue of the publication.

Description: Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers.

Description: The Lombardy Aerospace Industry Cluster [1] was founded in Italy in 2014 as the final step in constructing a representative institution for the regional system of aerospace industries. The process was initiated in 2009 with the first formal contacts between the local industry federation and the regional government of Lombardy, which led to the foundation of a provisional body (Distretto Aerospaziale Lombardo) in preparation for a more formalized industry cluster to come and in light of a mandate to represent the local aerospace industry politically.

Description: Hyperspectral imagery contains hundreds of contiguous bands with a wealth of spectral signatures, making it possible to distinguish materials through subtle spectral discrepancies. Because these spectral bands are highly correlated, dimensionality reduction, as the name suggests, seeks to reduce data dimensionality without losing desirable information. This article reviews discriminant analysisbased dimensionality-reduction approaches for hyperspectral imagery, including typical linear discriminant analysis (LDA), state-of-the-art sparse graph-based discriminant analysis (SGDA), and their extensions.

Description: Presents the introductory editorial for this issue of the publication.

Description: Describes the above-named upcoming conference event. May include topics to be covered or calls for papers.

Description: Graph algorithm is pervasive in many applications ranging from targeted advertising to natural language processing. Recently, Asynchronous Graph Processing (AGP) is becoming a promising model to support graph algorithm on large-scale distributed computing platforms because it enables faster convergence speed and lower synchronization cost than the synchronous model for no barrier between iterations. However, existing AGP methods still suffer from poor performance for inefficient vertex state propagation. In this paper, we propose an effective and low-cost forward and backward sweeping execution method to accelerate state propagation for AGP, based on a key observation that states in AGP can be propagated between vertices much faster when the vertices are processed sequentially along the graph path within each round. Through dividing graph into paths and asynchronously processing vertices on each path in an alternative forward and backward way according to their order on this path, vertex states in our approach can be quickly propagated to other vertices and converge in a faster way with only little additional overhead. In order to efficiently support it over distributed platforms, we also propose a scheme to reduce the communication overhead along with a static priority ordering scheme to further improve the convergence speed. Experimental results on a cluster with 1,024 cores show that our approach achieves excellent scalability for large-scale graph algorithms and the overall execution time is reduced by at least 39.8 percent, in comparison with the most cutting-edge methods.

Description: Deal selection on Groupon is a typical social learning and decision making process, where the quality of a deal is usually unknown to the customers. The customers must acquire this knowledge through social learning from other social medias such as reviews on Yelp. Additionally, the quality of a deal depends on both the state of the vendor and decisions of other customers on Groupon. How social learning and network externality affect the decisions of customers in deal selection on Groupon is our main interest. We develop a data-driven game-theoretic framework to understand the rational deal selection behaviors cross social medias. The sufficient condition of the Nash equilibrium is identified. A value-iteration algorithm is proposed to find the optimal deal selection strategy. We conduct a year-long experiment to trace the competitions among deals on Groupon and the corresponding Yelp ratings. We utilize the dataset to analyze the deal selection game with realistic settings. Finally, the performance of the proposed social learning framework is evaluated with real data. The results suggest that customers do make decisions in a rational way instead of following naive strategies, and there is still room to improve their decisions with assistance from the proposed framework.

Description: Various perceptual domains have underlying compositional semantics that are rarely captured in current models. We suspect this is because directly learning the compositional structure has evaded these models. Yet, the compositional structure of a given domain can be grounded in a separate domain thereby simplifying its learning. To that end, we propose a new approach to modeling bimodal perceptual domains that explicitly relates distinct projections across each modality and then jointly learns a bimodal sparse representation. The resulting model enables compositionality across these distinct projections and hence can generalize to unobserved percepts spanned by this compositional basis. For example, our model can be trained on red triangles and blue squares ; yet, implicitly will also have learned red squares and blue triangles . The structure of the projections and hence the compositional basis is learned automatically; no assumption is made on the ordering of the compositional elements in either modality. Although our modeling paradigm is general, we explicitly focus on a tabletop building-blocks setting. To test our model, we have acquired a new bimodal dataset comprising images and spoken utterances of colored shapes (blocks) in the tabletop setting. Our experiments demonstrate the benefits of explicitly leveraging compositionality in both quantitative and human evaluation studies.

Description: Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of Computer Vision and Natural Language Processing have achieved unprecedented breakthroughs in tasks like automatic captioning or image retrieval. Most of these learning methods, though, rely on large training sets of images associated with human annotations that specifically describe the visual content. In this paper we propose to go a step further and explore the more complex cases where textual descriptions are loosely related to the images. We focus on the particular domain of news articles in which the textual content often expresses connotative and ambiguous relations that are only suggested but not directly inferred from images. We introduce an adaptive CNN architecture that shares most of the structure for multiple tasks including source detection, article illustration and geolocation of articles. Deep Canonical Correlation Analysis is deployed for article illustration, and a new loss function based on Great Circle Distance is proposed for geolocation. Furthermore, we present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (such as GPS coordinates and user comments). We show this dataset to be appropriate to explore all aforementioned problems, for which we provide a baseline performance using various Deep Learning architectures, and different representations of the textual and visual features. We report very promising results and bring to light several limitations of current state-of-the-art in this kind of domain, which we hope will help spur progress in the field.

Description: Machine learning algorithms for the analysis of time-series often depend on the assumption that utilised data are temporally aligned. Any temporal discrepancies arising in the data is certain to lead to ill-generalisable models, which in turn fail to correctly capture properties of the task at hand. The temporal alignment of time-series is thus a crucial challenge manifesting in a multitude of applications. Nevertheless, the vast majority of algorithms oriented towards temporal alignment are either applied directly on the observation space or simply utilise linear projections-thus failing to capture complex, hierarchical non-linear representations that may prove beneficial, especially when dealing with multi-modal data (e.g., visual and acoustic information). To this end, we present Deep Canonical Time Warping (DCTW), a method that automatically learns non-linear representations of multiple time-series that are (i) maximally correlated in a shared subspace, and (ii) temporally aligned. Furthermore, we extend DCTW to a supervised setting, where during training, available labels can be utilised towards enhancing the alignment process. By means of experiments on four datasets, we show that the representations learnt significantly outperform state-of-the-art methods in temporal alignment, elegantly handling scenarios with heterogeneous feature sets, such as the temporal alignment of acoustic and visual information.

Description: Domain adaptation between diverse source and target domains is challenging, especially in the real-world visual recognition tasks where the images and videos consist of significant variations in viewpoints, illuminations, qualities, etc. In this paper, we propose a new approach for domain generalization and domain adaptation based on exemplar SVMs. Specifically, we decompose the source domain into many subdomains, each of which contains only one positive training sample and all negative samples. Each subdomain is relatively less diverse, and is expected to have a simpler distribution. By training one exemplar SVM for each subdomain, we obtain a set of exemplar SVMs. To further exploit the inherent structure of source domain, we introduce a nuclear-norm based regularizer into the objective function in order to enforce the exemplar SVMs to produce a low-rank output on training samples. In the prediction process, the confident exemplar SVM classifiers are selected and reweigted according to the distribution mismatch between each subdomain and the test sample in the target domain. We formulate our approach based on the logistic regression and least square SVM algorithms, which are referred to as low rank exemplar SVMs (LRE-SVMs) and low rank exemplar least square SVMs (LRE-LSSVMs), respectively. A fast algorithm is also developed for accelerating the training of LRE-LSSVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation, and show that our approach can also be applied to domain adaptation with evolving target domain, where the target data distribution is gradually changing. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation with fixed and evolving target domains.

Description: In content-based image retrieval, SIFT feature and the feature from deep convolutional neural network (CNN) have demonstrated promising performance. To fully explore both visual features in a unified framework for effective and efficient retrieval, we propose a collaborative index embedding method to implicitly integrate the index matrices of them. We formulate the index embedding as an optimization problem from the perspective of neighborhood sharing and solve it with an alternating index update scheme. After the iterative embedding, only the embedded CNN index is kept for on-line query, which demonstrates significant gain in retrieval accuracy, with very economical memory cost. Extensive experiments have been conducted on the public datasets with million-scale distractor images. The experimental results reveal that, compared with the recent state-of-the-art retrieval algorithms, our approach achieves competitive accuracy performance with less memory overhead and efficient query computation.

Description: In this paper, we propose a context-aware local binary feature learning (CA-LBFL) method for face recognition. Unlike existing learning-based local face descriptors such as discriminant face descriptor (DFD) and compact binary face descriptor (CBFD) which learn each feature code individually, our CA-LBFL exploits the contextual information of adjacent bits by constraining the number of shifts from different binary bits, so that more robust information can be exploited for face representation. Given a face image, we first extract pixel difference vectors (PDV) in local patches, and learn a discriminative mapping in an unsupervised manner to project each pixel difference vector into a context-aware binary vector. Then, we perform clustering on the learned binary codes to construct a codebook, and extract a histogram feature for each face image with the learned codebook as the final representation. In order to exploit local information from different scales, we propose a context-aware local binary multi-scale feature learning (CA-LBMFL) method to jointly learn multiple projection matrices for face representation. To make the proposed methods applicable for heterogeneous face recognition, we present a coupled CA-LBFL (C-CA-LBFL) method and a coupled CA-LBMFL (C-CA-LBMFL) method to reduce the modality gap of corresponding heterogeneous faces in the feature level, respectively. Extensive experimental results on four widely used face datasets clearly show that our methods outperform most state-of-the-art face descriptors.

Description: Single modality action recognition on RGB or depth sequences has been extensively explored recently. It is generally accepted that each of these two modalities has different strengths and limitations for the task of action recognition. Therefore, analysis of the RGB+D videos can help us to better study the complementary properties of these two types of modalities and achieve higher levels of performance. In this paper, we propose a new deep autoencoder based shared-specific feature factorization network to separate input multimodal signals into a hierarchy of components. Further, based on the structure of the features, a structured sparsity learning machine is proposed which utilizes mixed norms to apply regularization within components and group selection between them for better classification performance. Our experimental results show the effectiveness of our cross-modality feature analysis framework by achieving state-of-the-art accuracy for action classification on five challenging benchmark datasets.

Description: Recently, cross-modal search has attracted considerable attention but remains a very challenging task because of the integration complexity and heterogeneity of the multi-modal data. To address both challenges, in this paper, we propose a novel method termed hetero-manifold regularisation (HMR) to supervise the learning of hash functions for efficient cross-modal search. A hetero-manifold integrates multiple sub-manifolds defined by homogeneous data with the help of cross-modal supervision information. Taking advantages of the hetero-manifold, the similarity between each pair of heterogeneous data could be naturally measured by three order random walks on this hetero-manifold. Furthermore, a novel cumulative distance inequality defined on the hetero-manifold is introduced to avoid the computational difficulty induced by the discreteness of hash codes. By using the inequality, cross-modal hashing is transformed into a problem of hetero-manifold regularised support vector learning. Therefore, the performance of cross-modal search can be significantly improved by seamlessly combining the integrated information of the hetero-manifold and the strong generalisation of the support vector machine. Comprehensive experiments show that the proposed HMR achieve advantageous results over the state-of-the-art methods in several challenging cross-modal tasks.

Description: We propose Multi-Task Learning with Low Rank Attribute Embedding (MTL-LORAE) to address the problem of person re-identification on multi-cameras. Re-identifications on different cameras are considered as related tasks, which allows the shared information among different tasks to be explored to improve the re-identification accuracy. The MTL-LORAE framework integrates low-level features with mid-level attributes as the descriptions for persons. To improve the accuracy of such description, we introduce the low-rank attribute embedding, which maps original binary attributes into a continuous space utilizing the correlative relationship between each pair of attributes. In this way, inaccurate attributes are rectified and missing attributes are recovered. The resulting objective function is constructed with an attribute embedding error and a quadratic loss concerning class labels. It is solved by an alternating optimization strategy. The proposed MTL-LORAE is tested on four datasets and is validated to outperform the existing methods with significant margins.

Description: In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors ( de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

Description: This paper proposes a method for line segment detection in digital images. We propose a novel linelet-based representation to model intrinsic properties of line segments in rasterized image space. Based on this, line segment detection, validation, and aggregation frameworks are constructed. For a numerical evaluation on real images, we propose a new benchmark dataset of real images with annotated lines called YorkUrban-LineSegment. The results show that the proposed method outperforms state-of-the-art methods numerically and visually. To our best knowledge, this is the first report of numerical evaluation of line segment detection on real images.

Description: This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

Description: A minimum hybridization network is a rooted phylogenetic network that displays two given rooted phylogenetic trees using a minimum number of reticulations. Previous mathematical work on their calculation has usually assumed the input trees to be bifurcating, correctly rooted, or that they both contain the same taxa. These assumptions do not hold in biological studies and “realistic” trees have multifurcations, are difficult to root, and rarely contain the same taxa. We present a new algorithm for computing minimum hybridization networks for a given pair of “realistic” rooted phylogenetic trees. We also describe how the algorithm might be used to improve the rooting of the input trees. We introduce the concept of “autumn trees”, a nice framework for the formulation of algorithms based on the mathematics of “maximum acyclic agreement forests”. While the main computational problem is hard, the run-time depends mainly on how different the given input trees are. In biological studies, where the trees are reasonably similar, our parallel implementation performs well in practice. The algorithm is available in our open source program Dendroscope 3, providing a platform for biologists to explore rooted phylogenetic networks. We demonstrate the utility of the algorithm using several previously studied data sets.

Description: The human colorectal carcinoma cell line (Caco-2) is a commonly used in-vitro test that predicts the absorption potential of orally administered drugs. In-silico prediction methods, based on the Caco-2 assay data, may increase the effectiveness of the high-throughput screening of new drug candidates. However, previously developed in-silico models that predict the Caco-2 cellular permeability of chemical compounds use handcrafted features that may be dataset-specific and induce over-fitting problems. Deep Neural Network (DNN) generates high-level features based on non-linear transformations for raw features, which provides high discriminant power and, therefore, creates a good generalized model. We present a DNN-based binary Caco-2 permeability classifier. Our model was constructed based on 663 chemical compounds with in-vitro Caco-2 apparent permeability data. Two hundred nine molecular descriptors are used for generating the high-level features during DNN model generation. Dropout regularization is applied to solve the over-fitting problem and the non-linear activation. The Rectified Linear Unit (ReLU) is adopted to reduce the vanishing gradient problem. The results demonstrate that the high-level features generated by the DNN are more robust than handcrafted features for predicting the cellular permeability of structurally diverse chemical compounds in Caco-2 cell lines.

Description: Read trimming is a fundamental first step of the analysis of next generation sequencing (NGS) data. Traditionally, it is performed heuristically, and algorithmic work in this area has been neglected. Here, we address this topic and formulate three optimization problems for block-based trimming (truncating the same low-quality positions at both ends for all reads and removing low-quality truncated reads). We find that all problems are NP-hard. Hence, we investigate the approximability of the problems. Two of them are NP-hard to approximate. However, the non-random distribution of quality scores in NGS data sets makes it tempting to speculate that quality constraints for read positions are typically satisfied by fulfilling quality constraints for reads. Thus, we propose three relaxed problems and develop efficient polynomial-time algorithms for them including heuristic speed-up techniques and parallelizations. We apply these optimized block trimming algorithms to 12 data sets from three species, four sequencers, and read lengths ranging from 36 to 101 bp and find that (i) the omitted constraints are indeed almost always satisfied, (ii) the optimized read trimming algorithms typically yield a higher number of untrimmed bases than traditional heuristics, and (iii) these results can be generalized to alternative objective functions beyond counting the number of untrimmed bases.

Description: Advances in de novo synthesis of DNA and computational gene design methods make possible the customization of genes by direct manipulation of features such as codon bias and mRNA secondary structure. Codon context is another feature significantly affecting mRNA translational efficiency, but existing methods and tools for evaluating and designing novel optimized protein coding sequences utilize untested heuristics and do not provide quantifiable guarantees on design quality. In this study we examine statistical properties of codon context measures in an effort to better understand the phenomenon. We analyze the computational complexity of codon context optimization and design exact and efficient heuristic gene recoding algorithms under reasonable constraint models. We also present a web-based tool for evaluating codon context bias in the appropriate context.

Description: To assess the genetic diversity of an environmental sample in metagenomics studies, the amplicon sequences of 16s rRNA genes need to be clustered into operational taxonomic units (OTUs). Many existing tools for OTU clustering trade off between accuracy and computational efficiency. We propose a novel OTU clustering algorithm, hc-OTU, which achieves high accuracy and fast runtime by exploiting homopolymer compaction and k-mer profiling to significantly reduce the computing time for pairwise distances of amplicon sequences. We compare the proposed method with other widely used methods, including UCLUST, CD-HIT, MOTHUR, ESPRIT, ESPRIT-TREE, and CLUSTOM, comprehensively, using nine different experimental datasets and many evaluation metrics, such as normalized mutual information, adjusted Rand index, measure of concordance, and F-score. Our evaluation reveals that the proposed method achieves a level of accuracy comparable to the respective accuracy levels of MOTHUR and ESPRIT-TREE, two widely used OTU clustering methods, while delivering orders-of-magnitude speedups.

Description: Recent studies have suggested abnormal brain network organization in subjects with Autism Spectrum Disorders (ASD). Here we applied spectral clustering algorithm, diverse centrality measures (betweenness (BC), clustering (CC), eigenvector (EC), and degree (DC)), and also the network entropy (NE) to identify brain sub-systems associated with ASD. We have found that BC increases in the following ASD clusters: in the somatomotor, default-mode, cerebellar, and fronto-parietal. On the other hand, CC, EC, and DC decrease in the somatomotor, default-mode, and cerebellar clusters. Additionally, NE decreases in ASD in the cerebellar cluster. These findings reinforce the hypothesis of under-connectivity in ASD and suggest that the difference in the network organization is more prominent in the cerebellar system. The cerebellar cluster presents reduced NE in ASD, which relates to a more regular organization of the networks. These results might be important to improve current understanding about the etiological processes and the development of potential tools supporting diagnosis and therapeutic interventions.

Description: Probabilistic models have been successfully adopted in computational biology and bioinformatics. Recently, a number of powerful probabilistic models and methods have been developed in the field of computational neuroscience, and these effective models have significantly advanced this field. This special section aims to capture some snapshots of recent developments of probabilistic methods in the synergistic combinations of cognitive brain science, brain imaging, and neuroscience. It aims to report the latest advances in these fields to the research community working on probabilistic methods in brain imaging analysis and computational neuroscience. This special section includes five contributed articles.