Sensors, Volume 23, Issue 21 (November-1 2023) – 357 articles

Unmanned aerial vehicles (UAV) can be controlled in diverse ways. One of the most common is through artificial intelligence (AI), which comprises different methods, such as reinforcement learning (RL). The article aims to provide a comparison of three RL algorithms—DQN as the benchmark, SARSA as a same-family algorithm, and A2C as a different-structure one—to address the problem of a UAV navigating from departure point A to endpoint B while avoiding obstacles and, simultaneously, using the least possible time and flying the shortest distance. Under fixed premises, this investigation provides the results of the performances obtained for this activity. A neighborhood environment was selected because it is likely one of the most common areas of use for commercial drones. Taking DQN as the benchmark and not having previous knowledge of the behavior of SARSA or A2C in the employed environment, the comparison outcomes showed that DQN was the only one achieving the target. At the same time, SARSA and A2C did not. However, a deeper analysis of the results led to the conclusion that a fine-tuning of A2C could overcome the performance of DQN under certain conditions, demonstrating a greater speed at maximum finding with a more straightforward structure. Full article

Wearable 2.0 research has been conducted on the manufacture of smart fitness wear that collects bio-signals through the wearing of a textile-based electrode. Among them, the electromyography (EMG) suit measures the electrical signals generated by the muscles to check their activity, such as contraction and relaxation. General gel-type electrodes have been reported to cause skin diseases due to an uncomfortable feel and skin irritation when attached to the skin for a long time. Dry electrodes of various materials are being developed to solve this problem. Previous research has reported EMG detectio performance and conducted economic comparisons according to the size and shape of the embroidery electrode. On the other hand, these embroidery electrodes still have foreign body sensations. In this study, a moss sEMG electrode was produced with various shapes (W3 and WF) and loop lengths (1–5 mm). The optimized conditions of the embroidery-based electrodes were derived and analyzed with the tactile comfort factors and sensing performances. As the loop length of the electrode increased, MIU and Qmax increased, but the SMD decreased due to the free movement of the threads constituting the loop. Impedance and sEMG detection performance showed different trends depending on the electrode type. Full article

In an integral imaging (II) display system, the self-adjustment ability of the human eye can result in blurry observations when viewing 3D targets outside the focal plane within a specific range. This can impact the overall imaging quality of the II system. This research examines the visual characteristics of the human eye and analyzes the path of light from a point source to the eye in the process of capturing and reconstructing the light field. Then, an overall depth of field (DOF) model of II is derived based on the human visual system (HVS). On this basis, an II system based on the human visual distance (HVD) perception model is proposed, and an interactive II display system is constructed. The experimental results confirm the effectiveness of the proposed method. The display system improves the viewing distance range, enhances spatial resolution and provides better stereoscopic display effects. When comparing our method with three other methods, it is clear that our approach produces better results in optical experiments and objective evaluations: the cumulative probability of blur detection (CPBD) value is 38.73%, the structural similarity index (SSIM) value is 86.56%, and the peak signal-to-noise ratio (PSNR) value is 31.12. These values align with subjective evaluations based on the characteristics of the human visual system. Full article

In this work, the impact of implementing Deep Reinforcement Learning (DRL) in predicting the channel parameters for user devices in a Power Domain Non-Orthogonal Multiple Access system (PD-NOMA) is investigated. In the channel prediction process, DRL based on deep Q networks (DQN) algorithm will be developed and incorporated into the NOMA system so that this developed DQN model can be employed to estimate the channel coefficients for each user device in NOMA system. The developed DQN scheme will be structured as a simplified approach to efficiently predict the channel parameters for each user in order to maximize the downlink sum rates for all users in the system. In order to approximate the channel parameters for each user device, this proposed DQN approach is first initialized using random channel statistics, and then the proposed DQN model will be dynamically updated based on the interaction with the environment. The predicted channel parameters will be utilized at the receiver side to recover the desired data. Furthermore, this work inspects how the channel estimation process based on the simplified DQN algorithm and the power allocation policy, can both be integrated for the purpose of multiuser detection in the examined NOMA system. Simulation results, based on several performance metrics, have demonstrated that the proposed simplified DQN algorithm can be a competitive algorithm for channel parameters estimation when compared to different benchmark schemes for channel estimation processes such as deep neural network (DNN) based long-short term memory (LSTM), RL based Q algorithm, and channel estimation scheme based on minimum mean square error (MMSE) procedure. Full article

Hydrogen has emerged as a promising carbon-neutral fuel source, spurring research and development efforts to facilitate its widespread adoption. However, the safe handling of hydrogen requires precise leak detection sensors due to its low activation energy and explosive potential. Various detection methods exist, with thermal conductivity measurement being a prominent technique for quantifying hydrogen concentrations. However, challenges remain in achieving high measurement sensitivity at low hydrogen concentrations below 1% for thermal-conductivity-based hydrogen sensors. Recent research explores the 3ω method’s application for measuring hydrogen concentrations in ambient air, offering high spatial and temporal resolutions. This study aims to enhance hydrogen leak detection sensitivity using the 3ω method by conducting thermal analyses on sensor design variables. Factors including substrate material, type, and sensor geometry significantly impact the measurement sensitivity. Comparative evaluations consider the minimum detectable hydrogen concentration while accounting for the uncertainty of the 3ω signal. The proposed suspended-type 3ω sensor is capable of detecting hydrogen leaks in ambient air and provides real-time measurements that are ideal for monitoring hydrogen diffusion. This research serves to bridge the gap between precision and real-time monitoring of hydrogen leak detection, promising significant advancements in the related safety applications. Full article

The assessment of cranial deformation is relevant in the field of medicine dealing with infants, especially in paediatric neurosurgery and paediatrics. To address this demand, the smartphone-based solution PhotoMeDAS has been developed, harnessing mobile devices to create three-dimensional (3D) models of infants’ heads and, from them, automatic cranial deformation reports. Therefore, it is crucial to examine the accuracy achievable with different mobile devices under similar conditions so prospective users can consider this aspect when using the smartphone-based solution. This study compares the linear accuracy obtained from three smartphone models (Samsung Galaxy S22 Ultra, S22, and S22+). Twelve measurements are taken with each mobile device using a coded cap on a head mannequin. For processing, three different bundle adjustment implementations are tested with and without self-calibration. After photogrammetric processing, the 3D coordinates are obtained. A comparison is made among spatially distributed distances across the head with PhotoMeDAS vs. ground truth established with a Creaform ACADEMIA 50 while-light 3D scanner. With a homogeneous scale factor for all the smartphones, the results showed that the average accuracy for the S22 smartphone is −1.15 ± 0.53 mm, for the S22+, 0.95 ± 0.40 mm, and for the S22 Ultra, −1.8 ± 0.45 mm. Worth noticing is that a substantial improvement is achieved regardless of whether the scale factor is introduced per device. Full article

Whispering-gallery mode microresonators have gained wide popularity as experimental platforms for different applications, ranging from biosensing to nonlinear optics. Typically, the resonant modes of dielectric microresonators are stimulated via evanescent wave coupling, facilitated using tapered optical fibers or coupling prisms. However, this method poses serious shortcomings due to fabrication and access-related limitations, which could be elegantly overcome by implementing a free-space coupling approach; although additional alignment procedures are needed in this case. To address this issue, we have developed a new algorithm to excite the microresonator automatically. Here, we show the working mechanism and the preliminary results of our experimental method applied to a home-made silica microsphere, using a visible laser beam with a spatial light modulator and a software control. Full article

This paper presents a cooperative control method for connected and automated vehicle (CAV) platooning, thus specifically addressing the challenge of sensor measurement errors that can disrupt the stability of the CAV platoon. Initially, the state-space equation of the CAV platooning system was formulated, thereby taking into account the measurement error of onboard sensors. The superposition effect of the sensor measurement errors was statistically analyzed, thereby elucidating its impact on cooperative control in CAV platooning. Subsequently, the application of a Kalman filter was proposed as a means to mitigate the adverse effects of measurement errors. Additionally, the CAV formation control problem was transformed into an optimal control decision problem by introducing an optimal control decision strategy that does not impose pure state variable inequality constraints. The proposed method was evaluated through simulation experiments utilizing real vehicle trajectory data from the Next Generation Simulation (NGSIM). The results demonstrate that the method presented in this study effectively mitigates the influence of measurement errors, thereby enabling coordinated vehicle-following behavior, achieving smooth acceleration and deceleration throughout the platoon, and eliminating traffic oscillations. Overall, the proposed method ensures the stability and comfort of the CAV platooning formation. Full article

In this work, we report on the implementation of a multi-quantum cascade laser (QCL) module as an innovative light source for quartz-enhanced photoacoustic spectroscopy (QEPAS) sensing. The source is composed of three different QCLs coupled with a dichroitic beam combiner module that provides an overlapping collimated beam output for all three QCLs. The 3λ-QCL QEPAS sensor was tested for detection of NO₂, SO₂, and NH₃ in sequence in a laboratory environment. Sensitivities of 19.99 mV/ppm, 19.39 mV/ppm, and 73.99 mV/ppm were reached for NO₂, SO₂, and NH₃ gas detection, respectively, with ultimate detection limits of 9 ppb, 9.3 ppb, and 2.4 ppb for these three gases, respectively, at an integration time of 100 ms. The detection limits were well below the values of typical natural abundance of NO₂, SO₂, and NH₃ in air. Full article

Wearable sensors provide a tool for at-home monitoring of motor impairment progression in neurological conditions such as Parkinson’s disease (PD). This study examined the ability of deep learning approaches to grade the motor impairment severity in a modified version of the Movement Disorders Society-sponsored revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) using low-cost wearable sensors. We hypothesized that expanding training datasets with motion data from healthy older adults (HOAs) and initializing classifiers with weights learned from unsupervised pre-training would lead to an improvement in performance when classifying lower vs. higher motor impairment relative to a baseline deep learning model (XceptionTime). This study evaluated the change in classification performance after using expanded training datasets with HOAs and transferring weights from unsupervised pre-training compared to a baseline deep learning model (XceptionTime) using both upper extremity (finger tapping, hand movements, and pronation–supination movements of the hands) and lower extremity (toe tapping and leg agility) tasks consistent with the MDS-UPDRS. Overall, we found a 12.2% improvement in accuracy after expanding the training dataset and pre-training using max-vote inference on hand movement tasks. Moreover, we found that the classification performance improves for every task except toe tapping after the addition of HOA training data. These findings suggest that learning from HOA motion data can implicitly improve the representations of PD motion data for the purposes of motor impairment classification. Further, our results suggest that unsupervised pre-training can improve the performance of motor impairment classifiers without any additional annotated PD data, which may provide a viable solution for a widely deployable telemedicine solution. Full article

With the development of science and technology, people are trying to use robots to assist in stroke rehabilitation training. This study aims to analyze the result of the formative test to provide the orientation of upper limb rehabilitation robot design optimization. We invited 21 physical therapists (PTs) and eight occupational therapists (OTs) who had no experience operating any upper limb rehabilitation robots before, and 4 PTs and 1 OT who had experience operating upper limb rehabilitation robots. Data statistics use the Likert scale. The general group scored 3.5 for safety-related topics, while the experience group scored 4.5. In applicability-related questions, the main function score was 2.3 in the general group and 2.4 in the experience group; and the training trajectory score was 3.5 in the general group and 5.0 in the experience group. The overall ease of use score was 3.1 in the general group and 3.6 in the experience group. There was no statistical difference between the two groups. The methods to retouch the trajectory can be designed through the feedback collected in the formative test and gathering further detail in the next test. Further details about the smooth trajectory must be confirmed in the next test. The optimization of the recording process is also important to prevent users from making additional effort to know it well. Full article

In this paper, self-modulated ghost imaging (SMGI) in a surrounded scattering medium is proposed. Different from traditional ghost imaging, SMGI can take advantage of the dynamic scattering medium that originally affects the imaging quality and generate pseudo-thermal light through the dynamic scattering of free particles’ Brownian motion in the scattering environment for imaging. Theoretical analysis and simulation were used to establish the relationship between imaging quality and particle concentration. An experimental setup was also built to verify the feasibility of the SMGI. Compared with the reconstructed image quality and evaluation indexes of traditional ghost imaging, SMGI has better image quality, which demonstrates a promising future in dynamic high-scattering media such as dense fog and turbid water. Full article

In recent times the escalating pollution within densely populated metropolitan areas has emerged as a significant and pressing concern. Authorities are actively grappling with the challenge of devising solutions to promote a cleaner and more environmentally friendly urban landscapes. This paper outlines the potential of establishing a LoRa node network within a densely populated urban environment. Each LoRa node in this network is equipped with an air quality measurement sensor. This interconnected system efficiently transmits all the analyzed data to a gateway, which subsequently sends it to a server or database in real time. These data are then harnessed to create a pollution map for the corresponding area, providing users with the opportunity to assess local pollution levels and their recent variations. Furthermore, this information proves valuable when determining the optimal route between two points in the city, enabling users to select the path with the lowest pollution levels, thus enhancing the overall quality of the urban environment. This advantage contributes to alleviating congestion and reducing excessive pollution often concentrated behind buildings or on adjacent streets. Full article

This paper proposes a non-contact continuous respiration monitoring method based on Fringe Projection Profilometry (FPP). This method aims to overcome the limitations of traditional intrusive techniques by providing continuous monitoring without interfering with normal breathing. The FPP sensor captures three-dimensional (3D) respiratory motion from the chest wall and abdomen, and the analysis algorithms extract respiratory parameters. The system achieved a high Signal-to-Noise Ratio (SNR) of 37 dB with an ideal sinusoidal respiration signal. Experimental results demonstrated that a mean correlation of 0.95 and a mean Root-Mean-Square Error (RMSE) of 0.11 breaths per minute (bpm) were achieved when comparing to a reference signal obtained from a spirometer. Full article

A visual camera system combined with the unmanned aerial vehicle (UAV) onboard edge computer should deploy an efficient object detection ability, increase the frame per second rate of the object of interest, and the wide searching ability of the gimbal camera for finding the emergent landing platform and for future reconnaissance area missions. This paper proposes an approach to enhance the visual capabilities of this system by using the You Only Look Once (YOLO)-based object detection (OD) with Tensor RT^TM acceleration technique, an automated visual tracking gimbal camera control system, and multithread programing for image transmission to the ground station. With lightweight edge computing (EC), the mean average precision (mAP) was satisfied and we achieved a higher frame per second (FPS) rate via YOLO accelerated with TensorRT for an onboard UAV. The OD compares four YOLO models to recognize objects of interest for landing spots at the home university first. Then, the trained dataset with YOLOv4-tiny was successfully applied to another field with a distance of more than 100 km. The system’s capability to accurately recognize a different landing point in new and unknown environments is demonstrated successfully. The proposed approach substantially reduces the data transmission and processing time to ground stations with automated visual tracking gimbal control, and results in rapid OD and the feasibility of using NVIDIA Jetson^TM Xavier NX by deploying YOLOs with more than 35 FPS for the UAV. The enhanced visual landing and future reconnaissance mission capabilities of real-time UAVs were demonstrated. Full article

We propose a new concept image sensor suitable for viewing and sensing applications. This is a report of a CMOS image sensor with a pixel architecture consisting of a 1.5 μm pixel with four-floating-diffusions-shared pixel structures and a 3.0 μm pixel with an in-pixel capacitor. These pixels are four small quadrate pixels and one big square pixel, also called quadrate–square pixels. They are arranged in a staggered pitch array. The 1.5 μm pixel pitch allows for a resolution high enough to recognize distant road signs. The 3 μm pixel with intra-pixel capacitance provides two types of signal outputs: a low-noise signal with high conversion efficiency and a highly saturated signal output, resulting in a high dynamic range (HDR). Two types of signals with long exposure times are read out from the vertical pixel, and four types of signals are read out from the horizontal pixel. In addition, two signals with short exposure times are read out again from the square pixel. A total of eight different signals are read out. This allows two rows to be read out simultaneously while reducing motion blur. This architecture achieves both an HDR of 106 dB and LED flicker mitigation (LFM), as well as being motion-artifact-free and motion-blur-less. As a result, moving subjects can be accurately recognized and detected with good color reproducibility in any lighting environment. This allows a single sensor to deliver the performance required for viewing and sensing applications. Full article

Force-based human posture estimation (FPE) provides a valuable alternative when camera-based human motion capturing is impractical. It offers new opportunities for sensor integration in smart products for patient monitoring, ergonomic optimization and sports science. Due to the interdisciplinary research on the topic, an overview of existing methods and the required expertise for their utilization is lacking. This paper presents a systematic review by the PRISMA 2020 review process. In total, 82 studies are selected (59 machine learning (ML)-based and 23 digital human model (DHM)-based posture estimation methods). The ML-based methods use input data from hardware sensors—mostly pressure mapping sensors—and trained ML models for estimating human posture. The ML-based human posture estimation algorithms mostly reach an accuracy above 90%. DHMs, which represent the structure and kinematics of the human body, adjust posture to minimize physical stress. The required expert knowledge for the utilization of these methods and their resulting benefits are analyzed and discussed. DHM-based methods have shown their general applicability without the need for application-specific training but require expertise in human physiology. ML-based methods can be used with less domain-specific expertise, but an application-specific training of these models is necessary. Full article

In this paper, a low-cost resin-coated commercial-photo-paper substrate is used to design a printed reconfigurable multiband antenna. The two PIN diodes are used mainly to redistribute the surface current that provides reconfigurable properties to the proposed antenna. The antenna size of 40 mm × 40 mm × 0.44 mm with a partial ground, covers wireless and mobile bands ranging from 1.91 GHz to 6.75 GHz. The parametric analysis is performed to achieve optimized design parameters of the antenna. The U-shaped and C-shaped emitters are meant to function at 2.4 GHz and 5.9 GHz, respectively, while the primary emitter is designed to operate at 3.5 GHz. The proposed antenna achieved peak gain and radiation efficiency of 3.4 dBi and 90%, respectively. Simulated and measured results of the reflection coefficient, radiation pattern, gain, and efficiency show that the antenna design is in favorable agreement. Since the proposed antenna achieved wideband (1.91–6.75 GHz) using PIN diode configuration, using this technique the need for numerous electronic components to provide multiband frequency is avoided. Full article

Quadrotors play a crucial role in the national economy. The control technology for quadrotor-slung load transportation systems has become a research hotspot. However, the underactuated load’s swing poses significant challenges to the stability of the system. In this paper, we propose a Lyapunov-based control strategy, to ensure the stability of the quadrotor-slung load transportation system while satisfying the constraints of the load’s swing angles. Firstly, a position controller without swing angle constraints is proposed, to ensure the stability of the system. Then, a barrier Lyapunov function based on the load’s swing angle constraints is constructed, and an anti-swing controller is designed to guarantee the states’ asymptotic stability. Finally, a PD controller is designed, to drive the actual angles to the virtual ones, which are extracted from the position controller. The effectiveness of the control method is verified by comparing it to the results of the LQR algorithm. The proposed control method not only guarantees the payload’s swing angle constraints but also reduces energy consumption. Full article

In the target-controlled infusion (TCI) of propofol and remifentanil intravenous anesthesia, accurate prediction of the depth of anesthesia (DOA) is very challenging. Patients with different physiological characteristics have inconsistent pharmacodynamic responses during different stages of anesthesia. For example, in TCI, older adults transition smoothly from the induction period to the maintenance period, while younger adults are more prone to anesthetic awareness, resulting in different DOA data distributions among patients. To address these problems, a deep learning framework that incorporates domain adaptation and knowledge distillation and uses propofol and remifentanil doses at historical moments to continuously predict the bispectral index (BIS) is proposed in this paper. Specifically, a modified adaptive recurrent neural network (AdaRNN) is adopted to address data distribution differences among patients. Moreover, a knowledge distillation pipeline is developed to train the prediction network by enabling it to learn intermediate feature representations of the teacher network. The experimental results show that our method exhibits better performance than existing approaches during all anesthetic phases in the TCI of propofol and remifentanil intravenous anesthesia. In particular, our method outperforms some state-of-the-art methods in terms of root mean square error and mean absolute error by 1 and 0.8, respectively, in the internal dataset as well as in the publicly available dataset. Full article

Atmospheric drag is an important influencing factor in precise orbit determination and the prediction of low-orbit space debris. It has received widespread attention. Currently, calculating atmospheric drag mainly relies on different atmospheric density models. This experiment was designed to explore the impact of different atmospheric density models on the orbit prediction of space debris. In the experiment, satellite laser ranging data published by the ILRS (International Laser Ranging Service) were used as the basis for the precise orbit determination for space debris. The prediction error of space debris orbits at different orbital heights using different atmospheric density models was used as a criterion to evaluate the impact of atmospheric density models on the determination of space-target orbits. Eight atmospheric density models, DTM78, DTM94, DTM2000, J71, RJ71, JB2006, MSIS86, and NRLMSISE00, were compared in the experiment. The experimental results indicated that the DTM2000 atmospheric density model is best for determining and predicting the orbits of LEO (low-Earth-orbit) targets. Full article

In healthcare, wireless body area networks (WBANs) can be used to constantly collect patient body data and assist in real-time medical services for patients from physicians. In such security- and privacy-critical systems, the user authentication mechanism can be fundamentally expected to prevent illegal access and privacy leakage occurrences issued by hacker intrusion. Currently, a significant quantity of new WBAN-oriented authentication protocols have been designed to verify user identity and ensure that body data are accessed only with a session key. However, those newly published protocols still unavoidably affect session key security and user privacy due to the lack of forward secrecy, mutual authentication, user anonymity, etc. To solve this problem, this paper designs a robust user authentication protocol. By checking the integrity of the message sent by the other party, the communication entity verifies the other party’s identity validity. Compared with existing protocols, the presented protocol enhances security and privacy while maintaining the efficiency of computation. Full article

Currently, Convolutional Neural Networks (CNN) are widely used for processing and analyzing image or video data, and an essential part of state-of-the-art studies rely on training different CNN architectures. They have broad applications, such as image classification, semantic segmentation, or face recognition. Regardless of the application, one of the important factors influencing network performance is the use of a reliable, well-labeled dataset in the training stage. Most of the time, especially if we talk about semantic classification, labeling is time and resource-consuming and must be done manually by a human operator. This article proposes an automatic label generation method based on the Gaussian mixture model (GMM) unsupervised clustering technique. The other main contribution of this paper is the optimization of the hyperparameters of the traditional U-Net model to achieve a balance between high performance and the least complex structure for implementing a low-cost system. The results showed that the proposed method decreased the resources needed, computation time, and model complexity while maintaining accuracy. Our methods have been tested in a deforestation monitoring application by successfully identifying forests in aerial imagery. Full article

This paper proposes a fast direction of arrival (DOA) estimation method based on positive incremental modified Cholesky decomposition atomic norm minimization (PI-CANM) for augmented coprime array sensors. The approach incorporates coprime sampling on the augmented array to generate a non-uniform, discontinuous virtual array. It then utilizes interpolation to convert this into a uniform, continuous virtual array. Based on this, the problem of DOA estimation is equivalently formulated as a gridless optimization problem, which is solved via atomic norm minimization to reconstruct a Hermitian Toeplitz covariance matrix. Furthermore, by positive incremental modified Cholesky decomposition, the covariance matrix is transformed from positive semi-definite to positive definite, which simplifies the constraint of optimization problem and reduces the complexity of the solution. Finally, the Multiple Signal Classification method is utilized to carry out statistical signal processing on the reconstructed covariance matrix, yielding initial DOA angle estimates. Experimental outcomes highlight that the PI-CANM algorithm surpasses other algorithms in estimation accuracy, demonstrating stability in difficult circumstances such as low signal-to-noise ratios and limited snapshots. Additionally, it boasts an impressive computational speed. This method enhances both the accuracy and computational efficiency of DOA estimation, showing potential for broad applicability. Full article

Recent advances in the field of collaborative robotics aim to endow industrial robots with prediction and anticipation abilities. In many shared tasks, the robot’s ability to accurately perceive and recognize the objects being manipulated by the human operator is crucial to make predictions about the operator’s intentions. In this context, this paper proposes a novel learning-based framework to enable an assistive robot to recognize the object grasped by the human operator based on the pattern of the hand and finger joints. The framework combines the strengths of the commonly available software MediaPipe in detecting hand landmarks in an RGB image with a deep multi-class classifier that predicts the manipulated object from the extracted keypoints. This study focuses on the comparison between two deep architectures, a convolutional neural network and a transformer, in terms of prediction accuracy, precision, recall and F1-score. We test the performance of the recognition system on a new dataset collected with different users and in different sessions. The results demonstrate the effectiveness of the proposed methods, while providing valuable insights into the factors that limit the generalization ability of the models. Full article

This paper presents a machine vision system that performs the automatic positioning of optical components in LED modules of automotive headlamps. The automatic adjustment of the module is a process of great interest at the industrial level, as it allows us to reduce reworks, increasing the company profits. We propose a machine vision system with a flexible hardware–software structure that allows it to adapt to a wide range of LED modules. Its hardware is composed of image-capturing devices, which enable us to obtain the LED module light pattern, and mechanisms for manipulating and holding the module to be adjusted. Its software design follows a component-based approach which allows us to increase the reusage of the code, decreasing the time required for configuring any type of LED module. To assess the efficiency and robustness of the industrial system, a series of tests, using three commercial models of LED modules, have been performed. In all cases, the automatically adjusted LED modules followed the ECE R112 regulation for automotive lighting. Full article

Wearable devices have become ubiquitous, collecting rich temporal data that offers valuable insights into human activities, health monitoring, and behavior analysis. Leveraging these data, researchers have developed innovative approaches to classify and predict time-based patterns and events in human life. Time-based techniques allow the capture of intricate temporal dependencies, which is the nature of the data coming from wearable devices. This paper focuses on predicting well-being factors, such as stress, anxiety, and positive and negative affect, on the Tesserae dataset collected from office workers. We examine the performance of different methodologies, including deep-learning architectures, LSTM, ensemble techniques, Random Forest (RF), and XGBoost, and compare their performances for time-based and non-time-based versions. In time-based versions, we investigate the effect of previous records of well-being factors on the upcoming ones. The overall results show that time-based LSTM performs the best among conventional (non-time-based) RF, XGBoost, and LSTM. The performance even increases when we consider a more extended previous period, in this case, 3 past-days rather than 1 past-day to predict the next day. Furthermore, we explore the corresponding biomarkers for each well-being factor using feature ranking. The obtained rankings are compatible with the psychological literature. In this work, we validated them based on device measurements rather than subjective survey responses. Full article

This manuscript describes the design, development, and implementation of a prototype system based on seismogeodetic techniques, consisting of a low-cost MEMS seismometer/accelerometer, a biaxial inclinometer, a multi-frequency GNSS receiver, and a meteorological sensor, installed at the Doñana Biological Station (Huelva, Spain) that transmits multiparameter data in real and/or deferred time to the control center at the University of Cadiz. The main objective of this system is to know, detect, and monitor the tectonic activity in the Gulf of Cadiz region and adjacent areas in which important seismic events occur produced by the interaction of the Eurasian and African plates, in addition to the ability to integrate into a regional early warning system (EWS) to minimize the consequences of dangerous geological phenomena. Full article

We developed a shoe sole sensor system with four high-capacity, compact triaxial force sensors using a nitrogen added chromium strain-sensitive thin film mounted on the sole of a shoe. Walking experiments were performed, including straight walking and turning (side-step and cross-step turning), in six healthy young male participants and two healthy young female participants wearing the sole sensor system. A regression model to predict three-directional ground reaction forces (GRFs) from force sensor outputs was created using multiple linear regression and Gaussian process regression (GPR). The predicted GRF values were compared with the GRF values measured with a force plate. In the model trained on data from the straight walking and turning trials, the percent root-mean-square error (%RMSE) for predicting the GRFs in the anteroposterior and vertical directions was less than 15%, except for the GRF in the mediolateral direction. The model trained separately for straight walking, side-step turning, and cross-step turning showed a %RMSE of less than 15% in all directions in the GPR model, which is considered accurate for practical use. Full article

Acoustic sensing provides crucial data for anomalous sound detection (ASD) in condition monitoring. However, building a robust acoustic-sensing-based ASD system is challenging due to the unsupervised nature of training data, which only contain normal sound samples. Recent discriminative models based on machine identity (ID) classification have shown excellent ASD performance by leveraging strong prior knowledge like machine ID. However, such strong priors are often unavailable in real-world applications, limiting these models. To address this, we propose utilizing the imbalanced and inconsistent attribute labels from acoustic sensors, such as machine running speed and microphone model, as weak priors to train an attribute classifier. We also introduce an imbalanced compensation strategy to handle extremely imbalanced categories and ensure model trainability. Furthermore, we propose a score fusion method to enhance anomaly detection robustness. The proposed algorithm was applied in our DCASE2023 Challenge Task 2 submission, ranking sixth internationally. By exploiting acoustic sensor data attributes as weak prior knowledge, our approach provides an effective framework for robust ASD when strong priors are absent. Full article