ALBERT

Description: Fault tolerance in IoT systems is challenging to overcome due to its complexity, dynamicity, and heterogeneity. IoT systems are typically designed and constructed in layers. Every layer has its requirements and fault tolerance strategies. However, errors in one layer can propagate and cause effects on others. Thus, it is impractical to consider a centralized fault tolerance approach for an entire system. Consequently, it is vital to consider multiple layers in order to enable collaboration and information exchange when addressing fault tolerance. The purpose of this study is to propose a multi-layer fault tolerance approach, granting interconnection among IoT system layers, allowing information exchange and collaboration in order to attain the property of dependability. Therefore, we define an event-driven framework called FaTEMa (Fault Tolerance Event Manager) that creates a dedicated fault-related communication channel in order to propagate events across the levels of the system. The implemented framework assist with error detection and continued service. Additionally, it offers extension points to support heterogeneous communication protocols and evolve new capabilities. Our empirical results show that introducing FaTEMa provided improvements to the error detection and error resolution time, consequently improving system availability. In addition, the use of Fatema provided a reliability improvement and a reduction in the number of failures produced.

Description: This study presents a 2-D lidar odometry based on an ICP (iterative closest point) variant used in a simple and straightforward platform that achieves real-time and low-drift performance. With a designated multi-scale feature extraction procedure, the lidar cloud information can be utilized at multiple levels and the speed of data association can be accelerated according to the multi-scale data structure, thereby achieving robust feature extraction and fast scan-matching algorithms. First, on a large scale, the lidar point cloud data are classified according to the curvature into two parts: smooth collection and rough collection. Then, on a small scale, noise and unstable points in the smooth or rough collection are filtered, and edge points and corner points are extracted. Then, the proposed tangent-vector-pairs based on edge and corner points are applied to evaluate the rotation term, which is significant for producing a stable solution in motion estimation. We compare our performance with two excellent open-source SLAM algorithms, Cartographer and Hector SLAM, using collected and open-access datasets in structured indoor environments. The results indicate that our method can achieve better accuracy.

Description: Volcanic ash fall-out represents a serious hazard for air and road traffic. The forecasting models used to predict its time–space evolution require information about the core characteristics of volcanic particles, such as their granulometry. Typically, such information is gained by the spot direct observation of the ash collected at the ground or by using expensive instrumentation. In this paper, a vision-based methodology aimed at the estimation of ash granulometry is presented. A dedicated image processing paradigm was developed and implemented in LabVIEW™. The methodology was validated experimentally using digital reference images resembling different operating conditions. The outcome of the assessment procedure was very encouraging, showing an accuracy of the image processing algorithm of 1.76%.

Description: In this paper, we provide external image features and use the internal attention mechanism to solve the VQA problem given a dataset of textual questions and related images. Most previous models for VQA use a pair of images and questions as input. In addition, the model adopts a question-oriented attention mechanism to extract the features of the entire image and then perform feature fusion. However, the shortcoming of these models is that they cannot effectively eliminate the irrelevant features of the image. In addition, the problem-oriented attention mechanism lacks in the mining of image features, which will bring in redundant image features. In this paper, we propose a VQA model based on adversarial learning and bidirectional attention. We exploit external image features that are not related to the question to form an adversarial mechanism to boost the accuracy of the model. Target detection is performed on the image—that is, the image-oriented attention mechanism. The bidirectional attention mechanism is conducive to promoting model attention and eliminating interference. Experimental results are evaluated on benchmark datasets, and our model performs better than other models based on attention methods. In addition, the qualitative results show the attention maps on the images and leads to predicting correct answers.

Description: The signal-to-noise ratios (SNR) of ultrasonic imaging and non-destructive evaluation (NDE) applications can be greatly improved by driving each piezoelectric transducer (single or in array) with tuned HV capacitive-discharge drivers. These can deliver spikes with kW pulsed power at PRF ≈ 5000 spikes/s, achieving levels higher even than in CW high-power ultrasound: up to 5 kWpp. These conclusions are reached here by applying a new strategy proposed for the accurate modeling of own-design re-configurable HV capacitive drivers. To obtain such rigorous spike modeling, the real effects of very high levels of pulsed intensities (3–10 A) and voltages (300–700 V) were computed. Unexpected phenomena were found: intense brief pulses of driving power and probe emitted force, as well as nonlinearities in semiconductors, though their catalog data include only linear ranges. Fortunately, our piezoelectric and circuital devices working in such an intense regime have not shown serious heating problems, since the finally consumed “average” power is rather small. Intensity, power, and voltage, driving wideband transducers from our capacitive drivers, are researched here in order to drastically improve (∆ 〉〉 40 dB) their ultrasonic “net dynamic range available” (NDRA), achieving emitted forces 〉 240 Newtonspp and receiving ultrasonic signals of up to 76–205 Vpp. These measurements of ultrasonic pulsed voltages, received in NDE and Imaging, are approximately 10,000 larger than those usual today. Thus, NDRA ranges were optimized for three laboratory capacitive drivers (with six commercial transducers), which were successfully applied in the aircraft industry for imaging landing flaps in Boeing wings, despite suffering acoustic losses 〉 120 dB.

Description: The activities performed by nurses in their daily activities involve frequent forward bending and awkward back postures. These movements contribute to the prevalence and development of low back pain (LBP). In previous studies, it has been shown that modifying their posture by education and training in proper lifting techniques decreases the prevalence of LBP. However, this education and training needs to be implemented daily. Hence, implementing the use of a wearable device to monitor the back posture with haptic feedback would be of importance to prevent LBP. This paper proposes a wearable device to monitor the back posture of the user and provide feedback when the participant is performing a possible hurtful movement. In this study, a group of participants was asked to wear the device while performing three of the most common activities performed by nurses. The study was divided into three sessions: In the first session, the participants performed the activities without feedback (baseline). During the second session, the participants received feedback from the wearable device (training) while performing the three tasks. Finally, for the third session, the participants performed the three tasks again, but the haptic feedback was turned off (validation). We found an improvement in the posture of more than 40% for the pitch (lateral bending) and roll (forward/backward bending) axes and 7% for the yaw (twisting) axis when comparing to the results from session 1 and session 2. The comparison between session 1 and session 3 showed an overall improvement of more than 50% for the pitch (lateral bending) and roll (forward/backward bending) axes and more than 20% for the yaw axis. These results hinted at the impact of the haptic feedback on the participants to correct their posture.

Description: Tool forces are a decisive parameter for manual grinding with hand-held power tools, which can be used to determine the productivity, quality of the work result, vibration exposition, and tool lifetime. One approach to tool force determination is the prediction of tool forces via measured operating parameters of a hand-held power tool. The problem is that the accuracy of tool force prediction with consumer-grade sensors remains unclear in manual grinding. Therefore, the accuracy of tool force prediction using Gaussian process regression is examined in a study for two hand-held angle grinders in four different applications in three directions using measurement data from an inertial measurement unit, a current sensor, and a voltage sensor. The prediction of the grinding normal force (rMAE = 11.44% and r = 0.84) and the grinding tangential force (rMAE = 18.21% and r = 0.82) for three tested applications, as well as the radial force for the application cutting with a cut-off wheel (rMAE = 19.67% and r = 0.80) is shown to be feasible. The prediction of the guiding force (rMAE = 87.02% and r = 0.37) for three tested applications is only possible to a limited extent. This study supports data acquisition and evaluation of hand-held power tools using consumer-grade sensors, such as an inertial measurement unit, in real-world applications, resulting in new potentials for product use and product development.

Description: Some bands in the frequency spectrum have become overloaded and others underutilized due to the considerable increase in demand and user allocation policy. Cognitive radio applies detection techniques to dynamically allocate unlicensed users. Cooperative spectrum sensing is currently showing promising results. Therefore, in this work, we propose a cooperative spectrum detection system based on a residual neural network architecture combined with feature extractor and random forest classifier. The objective of this paper is to propose a cooperative spectrum sensing approach that can achieve high accuracy in higher levels of noise power density with less unlicensed users cooperating in the system. Therefore, we propose to extract features of the sensing information of each unlicensed user, then we use a random forest to classify if there is a presence of a licensed user in each band analyzed by the unlicensed user. Then, information from several unlicensed users are shared to a fusion center, where the decision about the presence or absence of a licensed user is accomplished by a model trained by a residual neural network. In our work, we achieved a high level of accuracy even when the noise power density is high, which means that our proposed approach is able to recognize the presence of a licensed user in 98% of the cases when the evaluated channel suffers a high level of noise power density (−134 dBm/Hz). This result was achieved with the cooperation of 10 unlicensed users.

Description: The utilization of groundwater is becoming increasingly popular for heating and cooling buildings, as well as to regulate the temperature needs of industrial processes. Groundwater has excellent energy potential from various factors, of which environmental acceptability stands out, as groundwater is considered a source of renewable energy. Due to the water table depth below the surface, atmospheric conditions have a negligible effect on the temperature of groundwater, resulting only in minor annual temperature variations, thus also making groundwater a source of reliable renewable energy. This paper presents some aspects of the groundwater heat pump (GWHP) system’s design and addresses a particular problem on the influence of recharge temperature field as well as local utility lines on the pumping well water temperature. An example is given of a system designed for a production hall in the northern part of Croatia. Geological and hydrogeological conditions at the site are highly favourable regarding the groundwater temperature and aquifer parameters. For the needs of this research, precise electronic sensors with data loggers were installed inside the wells. Probe type GSR 120 NT manufactured by Eltratec, Slovenia, is capable of monitoring level, temperature, and electrical conductivity, including telemetric data transfer to the remote server. Mapping the obtained data revealed significant temperature breakthroughs from the recharge wells, as well as local temperature field deviation near the sanitary and precipitation drainage collectors. Utility installation seepage influence was differentiated by the increase in groundwater electrical conductivity measured at the pumping wells. Results show that not only distance between the wells, as the main parameter that affects the system, but also industrial utility lines can have an influence on thermal field breakthrough.

Description: The position calibration of inertial measurement units (IMUs) is an important part of human motion capture, especially in wearable systems. In realistic applications, static calibration is quickly invalid during the motions for IMUs loosely mounted on the body. In this paper, we propose a dynamic position calibration algorithm for IMUs mounted on the waist, upper leg, lower leg, and foot based on joint constraints. To solve the problem of IMUs’ position displacement, we introduce the Gauss–Newton (GN) method based on the Jacobian matrix, the dynamic weight particle swarm optimization (DWPSO), and the grey wolf optimizer (GWO) to realize IMUs’ position calibration. Furthermore, we establish the coordinate system of human lower limbs to estimate each joint angle and use the fusion algorithm in the field of quaternions to improve the attitude calibration performance of a single IMU. The performances of these three algorithms are analyzed and evaluated by gait tests on the human body and comparisons with a high-precision IMU-Mocap reference device. The simulation results show that the three algorithms can effectively calibrate the IMU’s position for human lower limbs. Additionally, when the degree of freedom (DOF) of a certain dimension is limited, the performances of the DWPSO and GWO may be better than GN, when the joint changes sufficiently, the performances of the three are close. The results confirm that the dynamic calibration algorithm based on joint constraints can effectively reduce the position offset errors of IMUs on upper or lower limbs in practical applications.