Sensors, Volume 22, Issue 4 (February-2 2022) – 393 articles

Damage detection in structural health monitoring of metallic or composite structures depends on several factors, including the sensor technology and the type of defect that is under the spotlight. Commercial devices generally used to obtain these data neither allow for their installation on board nor permit their scalability when several structures or sensors need to be monitored. This paper introduces self-developed equipment designed to create ultrasonic guided waves and a methodology for the detection of progressive damage, such as corrosion damage in aircraft structures, i.e., algorithms for monitoring such damage. To create slowly changing conditions, aluminum- and carbon-reinforced polymer plates were placed together with seawater to speed up the corrosion process. The setup was completed by an array of 10 piezoelectric transducers driven and sensed by a structural health monitoring ultrasonic system, which generated 100 waveforms per test. The hardware was able to pre-process the raw acquisition to minimize the transmitted data. The experiment was conducted over eight weeks. Three different processing stages were followed to extract information on the degree of corrosion: hardware algorithm, pattern matching, and pattern recognition. The proposed methodology allows for the detection of trends in the progressive degradation of structures. Full article

The composition of gas mixtures may be determined via changes of the speed of sound. As this affects the resonance frequency of the gas inside a tube, indirect measurements through a frequency analysis are also possible. It is demonstrated that this may be carried out with unprecedented simplicity by the novel employment of a piezoelectric tube which serves at the same time as a resonance tube and as transducer into the electronic domain. Experiments were run using a simple diecast aluminum box as the measuring cell, inside which the piezoelectric tube made from lead zirconium titanate with 30-mm length and 5.35-mm inner diameter was suspended. A small loudspeaker placed into the cell served for excitation of the resonance. Peak frequencies between 3910 and 14,590 Hz (for pure CO₂ and He, respectively) were obtained. Two component mixtures of O₂/N₂, CO₂/N₂, and He/N₂ at various composition were tested. A linear frequency change from 4790 to 5100 Hz was observed when going from pure O₂ to pure N₂. Full article

Wrist velocity is an important risk factor for work-related musculoskeletal disorders in the elbow/hand, which is also difficult to assess by observation or self-reports. This study aimed to evaluate a new convenient and low-cost inertial measurement unit (IMU)-based method using gyroscope signals against an electrogoniometer for measuring wrist flexion velocity. Twelve participants performed standard wrist movements and simulated work tasks while equipped with both systems. Two computational algorithms for the IMU-based system, i.e., IMU_norm and IMU_flex, were used. For wrist flexion/extension, the mean absolute errors (MAEs) of median wrist flexion velocity compared to the goniometer were <10.1°/s for IMU_norm and <4.1°/s for IMU_flex. During wrist deviation and pronation/supination, all methods showed errors, where the IMU_norm method had the largest overestimations. For simulated work tasks, the IMU_flex method had small bias and better accuracy than the IMU_norm method compared to the goniometer, with the MAEs of median wrist flexion velocity <5.8°/s. The results suggest that the IMU-based method can be considered as a convenient method to assess wrist motion for occupational studies or ergonomic evaluations for the design of workstations and tools by both researchers and practitioners, and the IMU_flex method is preferred. Future studies need to examine algorithms to further improve the accuracy of the IMU-based method in tasks of larger variations, as well as easy calibration procedures. Full article

This paper attempts to uncover one possible method for the IMR (indoor mobile robot) to perform indoor exploration associated with SLAM (simultaneous localization and mapping) using LiDAR. Specifically, the IMR is required to construct a map when it has landed on an unexplored floor of a building. We had implemented the e-SLAM (exploration-based SLAM) using the coordinate transformation and the navigation prediction techniques to achieve that purpose in the engineering school building which consists of many 100-m² labs, corridors, elevator waiting space and the lobby. We first derive the LiDAR mesh for the orthogonal walls and filter out the static furniture and dynamic humans in the same space as the IMR. Then, we define the LiDAR pose frame including the translation and rotation from the orthogonal walls. According to the MSC (most significant corner) obtained from the intersection of the orthogonal walls, we calculate the displacement of the IMR. The orientation of the IMR is calculated from the alignment of orthogonal walls in the consecutive LiDAR pose frames, which is also assisted by the LQE (linear quadratic estimation) method. All the computation can be done in a single processor machine in real-time. The e-SLAM technique leads to a potential for the in-house service robot to start operation without having pre-scan LiDAR maps, which can save the installation time of the service robot. In this study, we use only the LiDAR and compared our result with the IMU to verify the consistency between the two navigation sensors in the experiments. The scenario of the experiment consists of rooms, corridors, elevators, and the lobby, which is common to most office buildings. Full article

Parkinson’s disease (PD) and progressive supranuclear palsy (PSP) are neurodegenerative movement disorders associated with cognitive dysfunction. The Luria’s Alternating Series Test (LAST) is a clinical tool sensitive to both graphomotor problems and perseverative tendencies that may suggest the dysfunction of prefrontal and/or frontostriatal areas and may be used in PD and PSP assessment. It requires the participant to draw a series of alternating triangles and rectangles. In the study, two clinical groups—51 patients with PD and 22 patients with PSP—were compared to 32 neurologically intact seniors. Participants underwent neuropsychological assessment. The LAST was administered in a paper and pencil version, then scanned and preprocessed. The series was automatically divided into characters, and the shapes were recognized as rectangles or triangles. In the feature extraction step, each rectangle and triangle was regarded both as an image and a two-dimensional signal, separately and as a part of the series. Standard and novel features were extracted and normalized using characters written by the examiner. Out of 71 proposed features, 51 differentiated the groups (p < 0.05). A classifier showed an accuracy of 70.5% for distinguishing three groups. Full article

The inertial navigation system (INS) is a basic component to obtain a continuous navigation solution in various applications. The INS suffers from a growing error over time. In particular, its navigation solution depends mainly on the quality and grade of the inertial measurement unit (IMU), which provides the INS with both accelerations and angular rates. However, low-cost small micro-electro-mechanical systems (MEMSs) suffer from huge error sources such as bias, the scale factor, scale factor instability, and highly non-linear noise. Therefore, MEMS-IMU measurements lead to drifts in the solutions when used as a control input to the INS. Accordingly, several approaches have been introduced to model and mitigate the errors associated with the IMU. In this paper, a machine-learning-based adaptive neuro-fuzzy inference system (ML-based-ANFIS) is proposed to leverage the performance of low-grade IMUs in two phases. The first phase was training 50% of the low-grade IMU measurements with a high-end IMU to generate a suitable error model. The second phase involved testing the developed model on the remaining low-grade IMU measurements. A real road trajectory was used to evaluate the performance of the proposed algorithm. The results showed the effectiveness of utilizing the proposed ML-ANFIS algorithm to remove the errors and improve the INS solution compared to the traditional one. An improvement of 70% in the 2D positioning and of 92% in the 2D velocity of the INS solution were attained when the proposed algorithm was applied compared to the traditional INS solution. Full article

In this research, we analyse data obtained from sensors when a user handwrites or draws on a tablet to detect whether the user is in a specific mood state. First, we calculated the features based on the temporal, kinematic, statistical, spectral and cepstral domains for the tablet pressure, the horizontal and vertical pen displacements and the azimuth of the pen’s position. Next, we selected features using a principal component analysis (PCA) pipeline, followed by modified fast correlation–based filtering (mFCBF). PCA was used to calculate the orthogonal transformation of the features, and mFCBF was used to select the best PCA features. The EMOTHAW database was used for depression, anxiety and stress scale (DASS) assessment. The process involved the augmentation of the training data by first augmenting the mood states such that all the data were the same size. Then, 80% of the training data was randomly selected, and a small random Gaussian noise was added to the extracted features. Automated machine learning was employed to train and test more than ten plain and ensembled classifiers. For all three moods, we obtained 100% accuracy results when detecting two possible grades of mood severities using this architecture. The results obtained were superior to the results obtained by using state-of-the-art methods, which enabled us to define the three mood states and provide precise information to the clinical psychologist. The accuracy results obtained when detecting these three possible mood states using this architecture were 82.5%, 72.8% and 74.56% for depression, anxiety and stress, respectively. Full article

Osseointegrated prostheses are widely used following transfemoral amputation. However, this technique requires sufficient implant stability before and during the rehabilitation period to mitigate the risk of implant breakage and loosening. Hence, reliable assessment methods for the osseointegration process are essential to ensure initial and long–term implant stability. This paper researches the feasibility of a vibration analysis technique for the osseointegration (OI) process by investigating the change in the dynamic response of the residual femur with a novel implant design during a simulated OI process. The paper also proposes a concept of an energy index (the E–index), which is formulated based on the normalized magnitude. To illustrate the potential of the E–index, this paper reports on changes in the vibrational behaviors of a 133 mm long amputated artificial femur model and implant system, with epoxy adhesives applied at the interface to simulate the OI process. The results show a significant variation in the magnitude of the colormap against curing time. The study also shows that the E–index was sensitive to the interface stiffness change, especially during the early curing process. These findings highlight the feasibility of using the vibration analysis technique and the E–index to quantitatively monitor the osseointegration process for future improvement on the efficiency of human health monitoring and patient rehabilitation. Full article

We present an overview of a beam-based approach to ultra-wide band (UWB) tomographic inverse scattering, where beam-waves are used for local data-processing and local imaging, as an alternative to the conventional plane-wave and Green’s function approaches. Specifically, the method utilizes a phase–space set of iso-diffracting beam-waves that emerge from a discrete set of points and directions in the source domain. It is shown that with a proper choice of parameters, this set constitutes a frame (an overcomplete generalization of a basis), termed “beam frame”, over the entire propagation domain. An important feature of these beam frames is that they need to be calculated once and then used for all frequencies, hence the method can be implemented either in the multi-frequency domain (FD), or directly in the time domain (TD). The algorithm consists of two phases: in the processing phase, the scattering data is transformed to the beam domain using windowed phase–space transformations, while in the imaging phase, the beams are backpropagated to the target domain to form the image. The beam-domain data is not only localized and compressed, but it is also physically related to the local Radon transform (RT) of the scatterer via a local Snell’s reflection of the beam-waves. This expresses the imaging as an inverse local RT that can be applied to any local domain of interest (DoI). In previous publications, the emphasis has been set on TD data processing using a special class of localized space–time beam-waves (wave-packets). The goal of the present paper is to present the imaging scheme in the UWB FD, utilizing simpler Fourier-based data-processing tools in the space and time domains. Full article

The state estimation problem is ubiquitous in many fields, and the common state estimation method is the Kalman filter. However, the Kalman filter is based on the mean square error criterion, which can only capture the second-order statistics of the noise and is sensitive to large outliers. In many areas of engineering, the noise may be non-Gaussian and outliers may arise naturally. Therefore, the performance of the Kalman filter may deteriorate significantly in non-Gaussian noise environments. To improve the accuracy of the state estimation in this case, a novel filter named Student’s t kernel-based maximum correntropy Kalman filter is proposed in this paper. In addition, considering that the fixed-point iteration method is used to solve the optimal estimated state in the filtering algorithm, the convergence of the algorithm is also analyzed. Finally, comparative simulations are conducted and the results demonstrate that with the proper parameters of the kernel function, the proposed filter outperforms the other conventional filters, such as the Kalman filter, Huber-based filter, and maximum correntropy Kalman filter. Full article

Trajectory data represent an essential source of information on travel behaviors and human mobility patterns, assuming a central role in a wide range of services related to transportation planning, personalized recommendation strategies, and resource management plans. The main issue when dealing with trajectory recordings, however, is characterized by temporary losses in the data collection, causing possible spatial–temporal gaps and missing trajectory segments. This is especially critical in those use cases based on non-repetitive individual motion traces, when the user’s missing information cannot be directly reconstructed due to the absence of historical individual repetitive routes. Inserted in the context of location-based trajectory modeling, we tackle the problem by proposing a technical parallelism with the natural language processing domain. Specifically, we introduce the use of the Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art language representation model, into the trajectory processing research field. By training deep bidirectional representations from unlabeled location sequences, jointly conditioned on both left and right context, we derive an explicit predicted estimation of the missing locations along the trace. The proposed framework, named TraceBERT, was tested on a real-world large-scale trajectory dataset of short-term tourists, exploring an effective attempt of adapting advanced language modeling approaches into mobility-based applications and demonstrating a prominent potential on trajectory reconstruction over traditional statistical approaches. Full article

Distributed array radar provides new prospects for three-dimensional (3D) inverse synthetic aperture radar (ISAR) imaging. The accuracy of image registration, as an essential part of 3D ISAR imaging, affects the performance of 3D reconstruction. In this paper, the imaging process of distributed array ISAR is proposed according to the imaging model. The ISAR images of distributed array radar at different APCs have different distribution of scatters. When the local distribution of scatters for the same target are quite different, the performance of the existing ISAR image registration methods may not be optimal. Therefore, an image registration method is proposed by integrating the feature-based method and the area-based method. The proposed method consists of two stages: coarse registration and fine registration. In the first stage, a dominant scatters model is established based on scale-invariant feature transform (SIFT). In the second stage, sub-pixel precision registration is achieved using the local correlation matching method. The effectiveness of the proposed method is verified by comparison with other image registration methods. The 3D reconstruction of the registered experimental data is carried out to assess the practicability of the proposed method. Full article

This paper proposes a novel method for physical fatigue assessment that can be applied in wearable systems, by utilizing a set of real-time measurable cardiovascular parameters. Daylength measurements, including a morning test set, physical exercise during the day, and an afternoon test set were conducted on 16 healthy subjects (8 female and 8 male). To analyze cardiovascular parameters for physical fatigue assessment, electrocardiography, pulse wave and blood pressure were measured during the test sets. The fatigue assessment questionnaire score, reaction time, countermovement jump height and hand grip strength were also measured and used as reference parameters. This study demonstrates that (i) the compiled test battery can selectively assess the rested vs. physically-fatigued states; (ii) the obtained linear support-vector machine, trained using the heart rate variability based parameter (F-score 0.842, accuracy 0.813) and pulse arrival time based parameter (F-score 0.875, accuracy 0.875) shows a promising ability to classify between the physically mildly fatigued and significantly fatigued states. Despite the somewhat limited study group size, the results of the study are unique and provide a significant advancement on the existing physical fatigue assessment methods towards a personalized and continuous real-time fatigue monitoring system with wearable sensors. Full article

This work presents polarization property studies of water clouds using a circular polarization lidar through a simulation approach. The simulation approach is based on a polarized, semianalytic Monte Carlo method under multiple-scattering conditions and considers three types of water clouds (namely homogeneous, inhomogeneous and partially inhomogeneous). The simulation results indicate that the layer-integrated circular depolarization ratios show similar variation trends as those of layer-integrated linear depolarization ratios. The Mishchenko–Hovenier relationship is validated to correlate the simulated layer-integrated circular and linear depolarization ratios. In addition, the cloud droplet effective radius, extinction coefficient, lidar field-of-view (FOV) and height of the cloud bottom are all found to affect the layer-integrated depolarization ratio. The current work theoretically indicates that a circular polarization lidar can efficiently perform measurements of water clouds, enjoying the advantage of higher sensitivity compared to a traditional linear polarization lidar. Hence, it should be of interest to researchers in fields of polarization lidar applications. Full article

Stride length estimation is one of the most crucial aspects of Pedestrian Dead Reckoning (PDR). Due to the measurement noise of inertial sensors, individual variances of pedestrians, and the uncertainty in pedestrians walking, there is a substantial error in the assessment of stride length, which causes the accumulated deviation of Pedestrian Dead Reckoning (PDR). With the help of multi-gait analysis, which decomposes strides in time and space with greater detail and accuracy, a novel and revolutionary stride estimating model or scheme could improve the performance of PDR on different users. This paper presents a diverse stride gait dataset by using inertial sensors that collect foot movement data from people of different genders, heights, and walking speeds. The dataset contains 4690 walking strides data and 19,083 gait labels. Based on the dataset, we propose a threshold-independent stride segmentation algorithm called SDATW and achieve an F-measure of 0.835. We also provide the detailed results of recognizing four gaits under different walking speeds, demonstrating the utility of our dataset for helping train stride segmentation algorithms and gait detection algorithms. Full article

The most common filters used to determine the angular position of quadrotors are the Kalman filter and the complementary filter. The problem of angular position estimation consist is a result of the absence of direct data. The most common sensors on board UAVs are micro electro mechanical system (MEMS) type sensors. The data acquired from the sensors are processed using digital filters. In the literature, the results of research conducted on the effectiveness of Kalman and complementary filters are known. A significant problem in evaluating the performance of the studied filters was the lack of an arbitrarily determined UAV position. The authors of this paper undertook the task of determining the best filter for a real object. The main objective of this research was to improve the stability of the physical quadrotor. For this purpose, we developed a research method using a laboratory station for testing quadrotor drones. Moreover, using the MATLAB environment, they determined the optimal parameters for the real filter applied using the PX4 software, which is new and has not been considered before in the available scientific literature. It should be mentioned that the authors of this work focused on the analysis of filters most commonly used for flight stabilization, without modifying the structure of these filters. By not modifying the filter structure, it is possible to optimize the existing flight controllers. The main contribution of this study lies in finding the most optimal filter, among those available in flight controllers, for angular position estimation. The special emphasis of our work was to develop a procedure for selecting the filter coefficients for a real object. The algorithm was designed so that other researchers could use it, provided they collected arbitrary data for their objects. Selected results of the research are presented in graphical form. The proposed procedure for improving the embedded filter can be used by other researchers on their subjects. Full article

Brain-computer interface performance may be reduced over time, but adapting the classifier could reduce this problem. Error-related potentials (ErrPs) could label data for continuous adaptation. However, this has scarcely been investigated in populations with severe motor impairments. The aim of this study was to detect ErrPs from single-trial EEG in offline analysis in participants with cerebral palsy, an amputation, or stroke, and determine how much discriminative information different brain regions hold. Ten participants with cerebral palsy, eight with an amputation, and 25 with a stroke attempted to perform 300–400 wrist and ankle movements while a sham BCI provided feedback on their performance for eliciting ErrPs. Pre-processed EEG epochs were inputted in a multi-layer perceptron artificial neural network. Each brain region was used as input individually (Frontal, Central, Temporal Right, Temporal Left, Parietal, and Occipital), the combination of the Central region with each of the adjacent regions, and all regions combined. The Frontal and Central regions were most important, and adding additional regions only improved performance slightly. The average classification accuracies were 84 ± 4%, 87± 4%, and 85 ± 3% for cerebral palsy, amputation, and stroke participants. In conclusion, ErrPs can be detected in participants with motor impairments; this may have implications for developing adaptive BCIs or automatic error correction. Full article

Background: Adding new approaches to teaching curriculums can be both expensive and complex to learn. The aim of this research was to gain insight into students’ literacy and confidence in learning sports science with new wearable technologies, specifically a novel program known as STEMfit. Methods: A three-phase design was carried out, with 36 students participating and exposed to wearable devices and associated software. This was to determine whether the technology hardware (phase one) and associated software (phase two) were used in a positive way that demonstrated user confidence. Results: Hardware included choosing a scalable wearable device that worked in conjunction with familiar and readily available software (Microsoft Excel) that extracted data through VBA coding. This allowed for students to experience and provide survey feedback on the usability and confidence gained when interacting with the STEMfit program. Outcomes indicated strong acceptance of the program, with high levels of motivation, resulting in a positive uptake of wearable technology as a teaching tool by students. The initial finding of this study offers an opportunity to further test the STEMfit program on other student cohorts as well as testing the scalability of the system into other year groups at the university level. Full article

The search algorithm based on symbiotic organisms’ interactions is a relatively recent bio-inspired algorithm of the swarm intelligence field for solving numerical optimization problems. It is meant to optimize applications based on the simulation of the symbiotic relationship among the distinct species in the ecosystem. The task scheduling problem is NP complete, which makes it hard to obtain a correct solution, especially for large-scale tasks. This paper proposes a modified symbiotic organisms search-based scheduling algorithm for the efficient mapping of heterogeneous tasks to access cloud resources of different capacities. The significant contribution of this technique is the simplified representation of the algorithm’s mutualism process, which uses equity as a measure of relationship characteristics or efficiency of species in the current ecosystem to move to the next generation. These relational characteristics are achieved by replacing the original mutual vector, which uses an arithmetic mean to measure the mutual characteristics with a geometric mean that enhances the survival advantage of two distinct species. The modified symbiotic organisms search algorithm (G_SOS) aims to minimize the task execution time (makespan), cost, response time, and degree of imbalance, and improve the convergence speed for an optimal solution in an IaaS cloud. The performance of the proposed technique was evaluated using a CloudSim toolkit simulator, and the percentage of improvement of the proposed G_SOS over classical SOS and PSO-SA in terms of makespan minimization ranges between 0.61–20.08% and 1.92–25.68% over a large-scale task that spans between 100 to 1000 Million Instructions (MI). The solutions are found to be better than the existing standard (SOS) technique and PSO. Full article

The seamless operation of inter-connected smart devices in Internet of Things (IoT) wireless sensor networks (WSNs) requires consistently available end-to-end routes. However, the sensor nodes that rely on a very limited power source tend to cause disconnection in multi-hop routes due to power shortages in the WSNs, which eventually results in the inefficiency of the overall IoT network. In addition, the density of the available sensor nodes affects the existence of feasible routes and the level of path multiplicity in the WSNs. Therefore, an efficient routing mechanism is expected to extend the lifetime of the WSNs by adaptively selecting the best routes for the data transfer between interconnected IoT devices. In this work, we propose a novel routing mechanism to balance the energy consumption among all the nodes and elongate the WSN lifetime, which introduces a score value assigned to each node along a path as the combination of evaluation metrics. Specifically, the scoring scheme considers the information of the node density at a certain area and the node energy levels in order to represent the importance of individual nodes in the routes. Furthermore, our routing mechanism allows for incorporating non-cooperative nodes. The simulation results show that the proposed work gives comparatively better results than some other experimented protocols. Full article

The existing federated learning framework is based on the centralized model coordinator, which still faces serious security challenges such as device differentiated computing power, single point of failure, poor privacy, and lack of Byzantine fault tolerance. In this paper, we propose an asynchronous federated learning system based on permissioned blockchains, using permissioned blockchains as the federated learning server, which is composed of a main-blockchain and multiple sub-blockchains, with each sub-blockchain responsible for partial model parameter updates and the main-blockchain responsible for global model parameter updates. Based on this architecture, a federated learning asynchronous aggregation protocol based on permissioned blockchain is proposed that can effectively alleviate the synchronous federated learning algorithm by integrating the learned model into the blockchain and performing two-order aggregation calculations. Therefore, the overhead of synchronization problems and the reliability of shared data is also guaranteed. We conducted some simulation experiments and the experimental results showed that the proposed architecture could maintain good training performances when dealing with a small number of malicious nodes and differentiated data quality, which has good fault tolerance, and can be applied to edge computing scenarios. Full article

Due to increased exposure to ultraviolet radiation caused by increased outdoor activities, the incidence of skin cancer is increasing. Incision is the most typical method for treating skin cancer, and various treatments that can minimize the risks of incision surgery are being investigated. Among them, photothermal therapy is garnering attention because it does not cause bleeding and affords rapid recovery. In photothermal therapy, tumor death is induced via temperature increase. In this study, a numerical study based on heat transfer theory was conducted to investigate the death of squamous cell carcinoma located in the skin layer based on various shapes of gold nanoparticles (AuNPs) used in photothermal therapy. The quantitative correlation between the conditions of various AuNPs and the laser intensity that yields the optimal photothermal treatment effect was derived using the effective apoptosis ratio. It was confirmed that optimal conditions exist for maximizing apoptosis within a tumor tissue and minimizing the thermal damage to surrounding normal tissues when using AuNPs under various conditions. Furthermore, it is envisioned that research result will be utilized as a standard for photothermal treatment in the future. Full article

The key point on analyzing the data stream measured by fiber optic distributed acoustic sensing (DAS) is signal activity detection separating measured signals from environmental noise. The inability to calculate the threshold for signal activity detection accurately and efficiently without affecting the measured signals is a bottleneck problem for current methods. In this article, a novel signal activity detection method with the adaptive-calculated threshold is proposed to solve the problem. With the analysis of the time-varying random noise’s statistical commonality and the short-term energy (STE) of real-time data stream, the top range of the total STE distribution of the noise is found accurately for real-time data stream’s ascending STE, thus the adaptive dividing level of signals and noise is obtained as the threshold. Experiments are implemented with simulated database and urban field database with complex noise. The average detection accuracies of the two databases are 97.34% and 90.94% only consuming 0.0057 s for a data stream of 10 s, which demonstrates the proposed method is accurate and high efficiency for signal activity detection. Full article

Single image depth estimation works fail to separate foreground elements because they can easily be confounded with the background. To alleviate this problem, we propose the use of a semantic segmentation procedure that adds information to a depth estimator, in this case, a 3D Convolutional Neural Network (CNN)—segmentation is coded as one-hot planes representing categories of objects. We explore 2D and 3D models. Particularly, we propose a hybrid 2D–3D CNN architecture capable of obtaining semantic segmentation and depth estimation at the same time. We tested our procedure on the SYNTHIA-AL dataset and obtained ${\sigma }_3=0.95$, which is an improvement of 0.14 points (compared with the state of the art of ${\sigma }_3=0.81$) by using manual segmentation, and ${\sigma }_3=0.89$ using automatic semantic segmentation, proving that depth estimation is improved when the shape and position of objects in a scene are known. Full article

Based on the coupling effect of contact electrification and electrostatic induction, the triboelectric nanogenerator (TENG) as an emerging energy technology can effectively harvest mechanical energy from the ambient environment. However, due to its inherent property of large impedance, the TENG shows high voltage, low current and limited output power, which cannot satisfy the stable power supply requirements of conventional electronics. As the interface unit between the TENG and load devices, the power management circuit can perform significant functions of voltage and impedance conversion for efficient energy supply and storage. Here, a review of the recent progress of switching power management for TENGs is introduced. Firstly, the fundamentals of the TENG are briefly introduced. Secondly, according to the switch types, the existing power management methods are summarized and divided into four categories: travel switch, voltage trigger switch, transistor switch of discrete components and integrated circuit switch. The switch structure and power management principle of each type are reviewed in detail. Finally, the advantages and drawbacks of various switching power management circuits for TENGs are systematically summarized, and the challenges and development of further research are prospected. Full article

Human beings tend to incrementally learn from the rapidly changing environment without comprising or forgetting the already learned representations. Although deep learning also has the potential to mimic such human behaviors to some extent, it suffers from catastrophic forgetting due to which its performance on already learned tasks drastically decreases while learning about newer knowledge. Many researchers have proposed promising solutions to eliminate such catastrophic forgetting during the knowledge distillation process. However, to our best knowledge, there is no literature available to date that exploits the complex relationships between these solutions and utilizes them for the effective learning that spans over multiple datasets and even multiple domains. In this paper, we propose a continual learning objective that encompasses mutual distillation loss to understand such complex relationships and allows deep learning models to effectively retain the prior knowledge while adapting to the new classes, new datasets, and even new applications. The proposed objective was rigorously tested on nine publicly available, multi-vendor, and multimodal datasets that span over three applications, and it achieved the top-1 accuracy of 0.9863% and an F1-score of 0.9930. Full article

In this paper, the field distribution and effective refractive index of transmission modes in single-core six-hole optical fiber were researched by modeling and simulation experiments. Based on the simulation results, a new type of sensor for axial strain, curvature, and temperature applications measurement was designed and fabricated. The experimental results showed that the axial strain sensitivities at different dips were −0.97 pm/με and −1.05 pm/με in the range from 0 to 2000 με, and the temperature sensitivities were 35.17 pm/°C and 47.27 pm/°C in the range from 25 to 75 °C. In addition, the proposed sensor also detected the curvature change with sensitivities of 7.36 dB/m⁻¹ and 20.08 dB/m⁻¹ from −2.582 m⁻¹ to −1.826 m⁻¹, respectively. Finally, through theoretical analysis, it can be deduced that this has potential application in the field of simultaneous measurement of strain and temperature. Full article

Nocturnal hypoglycemia (NH) is one of the most challenging events for multiple dose insulin therapy (MDI) in people with type 1 diabetes (T1D). The goal of this study is to design a method to reduce the incidence of NH in people with T1D under MDI therapy, providing a decision-support system and improving confidence toward self-management of the disease considering the dataset used by Bertachi et al. Different machine learning (ML) algorithms, data sources, optimization metrics and mitigation measures to predict and avoid NH events have been studied. In addition, we have designed population and personalized models and studied the generalizability of the models and the influence of physical activity (PA) on them. Obtaining 30 g of rescue carbohydrates (CHO) is the optimal value for preventing NH, so it can be asserted that this is the value with which the time under 70 mg/dL decreases the most, with almost a 35% reduction, while increasing the time in the target range by 1.3%. This study supports the feasibility of using ML techniques to address the prediction of NH in patients with T1D under MDI therapy, using continuous glucose monitoring (CGM) and a PA tracker. The results obtained prove that BG predictions can not only be critical in achieving safer diabetes management, but also assist physicians and patients to make better and safer decisions regarding insulin therapy and their day-to-day lives. Full article

Herein, we present the syntheses of a novel coordination polymer (CP) based on the perylene-3,4,9,10-tetracarboxylate (pery) linkers and sodium metal ions. We have chosen sodium metal center with the aim of surmising the effect that the modification of the metal ion may have on the relative humidity (RH) experimental measurements of the material. We confirm the role of the ions in the functionalization of the deposited layer by modifying their selectivity towards moisture content, paving the way to the generation of sensitive and selective chemical sensors. Full article

One of the primary tasks undertaken by autonomous vehicles (AVs) is object detection, which comes ahead of object tracking, trajectory estimation, and collision avoidance. Vulnerable road objects (e.g., pedestrians, cyclists, etc.) pose a greater challenge to the reliability of object detection operations due to their continuously changing behavior. The majority of commercially available AVs, and research into them, depends on employing expensive sensors. However, this hinders the development of further research on the operations of AVs. In this paper, therefore, we focus on the use of a lower-cost single-beam LiDAR in addition to a monocular camera to achieve multiple 3D vulnerable object detection in real driving scenarios, all the while maintaining real-time performance. This research also addresses the problems faced during object detection, such as the complex interaction between objects where occlusion and truncation occur, and the dynamic changes in the perspective and scale of bounding boxes. The video-processing module works upon a deep-learning detector (YOLOv3), while the LiDAR measurements are pre-processed and grouped into clusters. The output of the proposed system is objects classification and localization by having bounding boxes accompanied by a third depth dimension acquired by the LiDAR. Real-time tests show that the system can efficiently detect the 3D location of vulnerable objects in real-time scenarios. Full article