Search Results (153)

Gait is a sensitive marker of mobility decline and fall risk, motivating unobtrusive sensing methods that can extract spatiotemporal parameters outside specialized gait laboratories. This paper presents a physics-based comparison of two millimeter-wave frequency-modulated continuous-wave (FMCW) radar deployment paradigms using a low-cost, system-on-chip (SoC) 60 GHz Infineon BGT60TR13C radar sensor: (i) a fixed (tripod-mounted) corridor observer and (ii) a shoe-mounted body-centric configuration attached to the medial side of the left shoe. Four healthy adult author-participants performed repeated 30 s corridor trials under five gait styles (regular, slow, fast, simulated festination, and simulated freezing-of-gait), including brief pauses during turns; an empty-corridor recording was acquired to characterize static clutter. Step events were detected using peak-picking on foot-related velocity envelopes with adaptive thresholds, and step count, cadence, step time, and step-time variability were derived. Performance of the fixed and shoe-mounted configurations was quantitatively compared to video ground truth using mean absolute percentage error (MAPE) for step count estimation. Across all gait styles, the shoe-mounted FMCW radar consistently reduced step-count error relative to the fixed corridor-mounted configuration, with the largest gains under irregular patterns (e.g., festination: 37.1% fixed vs. 9.6% shoe-mounted). These findings highlight the advantages of body-centric millimeter-wave radar sensing and support low-cost SoC radar as a pathway toward wearable, privacy-preserving gait monitoring in real-world environments. Full article

Diabetes, projected to affect over 1.3 billion people by 2050, presents significant healthcare burdens and environmental challenges, necessitating innovative and sustainable solutions to manage complications effectively. This study applies life cycle assessment to evaluate the environmental impacts of two semiconductor-enabled diabetes care devices: (1) a single-use urine-based C-peptide measurement strip aligned with the reduce strategy and (2) a reusable smart wound dressing for chronic wound monitoring under the reuse strategy. Integrating green electricity reduced the total lifecycle global warming potential by 16.2% for the urine strip and 0.4% for the smart wound dressing. The results emphasize the importance of tailored design strategies, showing that the impact of green integrated circuits is substantial for single-use reduce systems, while long-term treatments benefit more from reuse strategies paired with durable, complex designs that extend component lifespan and limit new manufacturing burdens. Full article

We introduce a novel Bayesian approach for feature (variable) selection using Gaussian process regression, which is crucial for enhancing interpretability and model regularization. Our method employs nearest neighbor Gaussian processes as scalable approximations to classical Gaussian processes. Feature selection is performed by conditioning the process mean and covariance function on a random set representing the indices of relevant variables. A priori beliefs regarding this set control the feature selection, while reference priors are assigned to the remaining model parameters, ensuring numerical robustness in the process covariance matrix. For model inference, we propose a Metropolis-within-Gibbs algorithm. The effectiveness of the proposed feature selection approach is demonstrated through evaluation on simulated data, a computer experiment approximation, and two real-world data sets. Full article

Bidirectional switches are highly required power electronics units for the design of power converters, especially for direct matrix converters. This article presents the design and implementation of a compact bidirectional switch based on SiC-MOSFET technology, aimed at high-efficiency, high-density power electronics applications. The proposed architecture employs surface-mount components, optimizing both the occupied area and electrical performance. The selected switching device is the IMBG120R053M2H from Infineon, a SiC-MOSFET known for its low on-resistance, high reverse-voltage blocking capability, and excellent switching speed. To drive the power devices, the UCC21521 gate driver integrates two independent isolated outputs in a single package, enabling precise control and reduced electromagnetic interference (EMI). The developed design supports bidirectional current conduction and voltage blocking, offering a robust and scalable solution for next-generation power converters. Design criteria, simulation results, and experimental validations are discussed. Full article

The CoolMOS^TM (Infineon Technologies AG, Munich, Germany) has been regarded as a device that alleviates high-voltage limitations of unipolar power devices. However, although the theoretical considerations seem to confirm this possibility, this expectation has not been fulfilled to date. It appears that there are some limitations in the CoolMOS^TM concept, and the paper deals with their identification. Part I concentrated on the theory of high-voltage superjunction and its implementation into a power VDMOS transistor, which resulted in the CoolMOS^TM structure. This part is aimed at the physical and technological limitations that have been identified, taking advantage of numerical investigations of CoolMOS^TM structures developed on the basis of a typical VDMOS one. Full article

The CoolMOS™ (Infineon Technologies AG, Munich, Germany) has been considered a device that alleviates high-voltage limitations of unipolar power devices, but although the theoretical considerations seem to confirm such a possibility, this expectation has not been fulfilled until now. This paper identifies limitations of the CoolMOS™ concept. The analysis was carried out in two steps. The first step aimed at the theory of high-voltage superjunction and its implementation into a power VDMOS transistor, which resulted in the modified construction called CoolMOS™. The investigations have shown that the superjunction effect is not an inherent feature of high voltage junctions formed as a characteristic meander-like p-n junction. Such a junction starts to work in SuperJunction Mode (SJM) just when the electric field strength reaches the magnitude of the threshold electric field E_th. Also, other theoretical constraints concerning the SJ diode and CoolMOS™ design have been presented. The second step aimed at the physical and technological limitations that have been identified, taking advantage of numerical investigations for CoolMOS™ structures developed on the basis of a typical VDMOS one. Full article

Accurate identification of rear light signals in preceding vehicles is pivotal for Advanced Driver Assistance Systems (ADAS), enabling early detection of driver intentions and thereby improving road safety. In this work, we present a novel approach that leverages a meta-learning-enhanced YOLOv8 model to detect left and right turn indicators, as well as brake signals. Traditional radar and LiDAR provide robust geometry, range, and motion cues that can indirectly suggest driver intent (e.g., deceleration or lane drift). However, they do not directly interpret color-coded rear signals, which limits early intent recognition from the taillights. We therefore focus on a camera-based approach that complements ranging sensors by decoding color and spatial patterns in rear lights. This approach to detecting vehicle signals poses additional challenges due to factors such as high reflectivity and the subtle visual differences between directional indicators. We address these by training a YOLOv8 model with a meta-learning strategy, thus enhancing its capability to learn from minimal data and rapidly adapt to new scenarios. Furthermore, we developed a post-processing layer that classifies signals by the geometric properties of detected objects, employing mathematical principles such as distance, area calculation, and Intersection over Union (IoU) metrics. Our approach increases adaptability and performance compared to traditional deep learning techniques, supporting the conclusion that integrating meta-learning into real-time object detection frameworks provides a scalable and robust solution for intelligent vehicle perception, significantly enhancing situational awareness and road safety through reliable prediction of vehicular behavior. Full article

Assessing the driver’s state in real time is a critical challenge in modern vehicle safety systems, as human factors account for the vast majority of traffic accidents. Heart rate (HR) is a key physiological indicator of the driver’s condition, yet contactless measurements in dynamic in-vehicle environments remain difficult due to motion artifacts, vibrations, and varying operational conditions. This paper presents a novel two-stage method for HR estimation using a commercial 60 GHz frequency-modulated continuous wave (FMCW) radar sensor, specifically designed and validated for in-vehicle applications. In the first stage, coarse HR estimation is performed using the discrete wavelet transform (DWT) and autoregressive (AR) spectral analysis. The second stage refines the estimate using an inverse application of the relevance vector machine (RVM) approach, leveraging a narrowed frequency window derived from Stage 1. Final HR estimates are stabilized through sequential Kalman filtering (SKF) across time segments. The system was implemented using an Infineon BGT60TR13C radar module installed in the sun visor of a passenger vehicle. Extensive data collection was conducted during real-world driving across diverse traffic scenarios. The results demonstrate robust HR estimations with an accuracy comparable to that of commercial wearable devices, validated against a Polar H10 chest strap. This method offers several advantages over prior work, including short measurement windows (5 s), operation under varying lighting and clothing conditions, and validation in realistic driving environments. In this sense, the method contributes to the field of biomimetics by transferring the biological principles of continuous vital sign perception to technical sensorics in the automotive domain. Future work will explore the fusion of sensors with visual methods and potential extension to heart rate variability (HRV) estimations to enhance driver monitoring systems (DMSs) further. Full article

Background: Artificial Intelligence (AI) techniques have been extensively deployed in sensor-based Human Activity Recognition (HAR) systems. Recent advances in deep learning, especially Convolutional Neural Networks (CNNs), have advanced HAR by enabling automatic feature extraction from raw sensor data. However, these models often struggle to capture multiscale patterns in human activity, limiting recognition accuracy. Additionally, traditional centralized learning approaches raise data privacy concerns, as personal sensor data must be transmitted to a central server, increasing the risk of privacy breaches. Methods: To address these challenges, this paper introduces Conv-ScaleNet, a CNN-based model designed for multiscale feature learning and compatibility with federated learning (FL) environments. Conv-ScaleNet integrates a Pyramid Pooling Module to extract both fine-grained and coarse-grained features and employs sequential Global Average Pooling layers to progressively capture abstract global representations from inertial sensor data. The model supports federated learning by training locally on user devices, sharing only model updates rather than raw data, thus preserving user privacy. Results: Experimental results demonstrate that the proposed Conv-ScaleNet achieves approximately 98% and 96% F1-scores on the WISDM and UCI-HAR datasets, respectively, confirming its competitiveness in FL environments for activity recognition. Conclusions: The proposed Conv-ScaleNet model addresses key limitations of existing HAR systems by combining multiscale feature learning with privacy-preserving training. Its strong performance, data protection capability, and adaptability to decentralized environments make it a robust and scalable solution for real-world HAR applications. Full article

As Industry 5.0 emerges as a human-centric evolution of industrial systems, this study investigates the effectiveness of training interventions in companies aimed at supporting the transition to Industry 5.0, emphasizing human-centric and resilient skill development. Drawing from multiple case studies involving engineers and operators, the research applies both meta-analysis and meta-regression to assess the added value of experiential learning approaches such as Teaching and Learning Factories. In addition, a novel methodology combining quantitative analyses with qualitative interpretation of emerging competences is presented. Principal Component Analysis and classification frameworks are employed to identify and organize key competence clusters along technological, organizational, and social dimensions. Special attention is given to the emergence of human-centered competences such as decision empowerment, which are shown to complement traditional operational capabilities. The findings confirm that experiential training interventions enhance both self-efficacy and adaptive operational readiness, while the use of fusion techniques enables the generalization of results across heterogeneous corporate settings. This work contributes to ongoing discourse on Industry 5.0 readiness by linking training design to strategic company incentives and highlights the role of structured evaluation in informing future policy and implementation pathways. Full article

Automotive interior lighting has progressed from basic functional illumination to sophisticated aesthetic systems emphasizing chromatic stability under thermal variations. This study enhances an RGB temperature compensation algorithm for LEDs, extending it to an RGBW solution. While several approaches for LED temperature compensation have been proposed in the literature, none have addressed a complete RGBW solution where the white channel is derived and actively adjusted on thermal variations. This research aims to fill this gap by extending an RGB algorithm to RGBW and validating it under realistic automotive conditions. While the proposed compensation strategies are general and may be applied to other LED systems, the automotive interior lighting domain has been selected as a representative case study because it combines stringent chromatic stability requirements ($\Delta u^{\prime }{v}^{\prime }\le 0.01$) and high industrial relevance. Leveraging Infineon’s LITIX™ LED drivers, experimental results show that the algorithm maintains chromatic stability with deviations below $\Delta u^{\prime }{v}^{\prime }=0.00562$ in RGB mode and $\Delta u^{\prime }{v}^{\prime }=0.0067$ in RGBW mode across the tested temperature range. The addition of the white channel improves the color rendering index (CRI) by up to 58.9 points (from 19.7 to 78.6) while preserving color quality. Compared to previous works limited to RGB systems, our approach provides the first practical RGBW compensation algorithm experimentally validated under realistic automotive conditions. Full article

High-frequency (h. f.) harmonic distortion (HD) of advanced SiGe heterojunction bipolar transistor (HBT)-based power cells (PwCs), featuring optimized metallization interconnections between individual HBTs, was investigated. Single tone input power (P_in) excitations at 1, 2, 5, and 10 GHz frequencies were employed. The output power (P_out) of the fundamental tone and its harmonics were analyzed in both the frequency and time domains. A rapid increase in the third harmonic of P_out was observed at input powers exceeding −8 dBm for a fundamental frequency of 10 GHz in two different PwC technologies. This increase in the third harmonic was analyzed in terms of nonlinear current waveforms, the nonlinearity of the HBT p-n junction diffusion capacitances, substrate current behavior versus P_in, and avalanche multiplication current. To assess the RF power performance of the PwCs, scalar and vectorial load-pull (LP) measurements were conducted and analyzed. Under matched conditions, the SiGe PwCs demonstrated good linearity, particularly at high frequencies. The key power performance of the PwCs was measured and simulated as follows: input power 1 dB compression point (P_{in_1dB}) of −3 dBm, transducer power gain (G_T) of 15 dB, and power added efficiency (PAE) of 50% at 30 GHz. All measured data were corroborated with simulations using the compact model HiCuM L2. Full article

Many radar applications rely primarily on visual classification for their evaluations. However, new research is integrating textual descriptions alongside visual input and showing that such multimodal fusion improves contextual understanding. A critical issue in this area is the effective alignment of coded text with corresponding images. To this end, our paper presents an adversarial training framework that generates descriptive text from the latent space of a visual radar classifier. Our quantitative evaluations show that this dual-task approach maintains a robust classification accuracy of 98.3% despite the inclusion of Gaussian-distributed latent spaces. Beyond these numerical validations, we conduct a qualitative study of the text output in relation to the classifier’s predictions. This analysis highlights the correlation between the generated descriptions and the assigned categories and provides insight into the classifier’s visual interpretation processes, particularly in the context of normally uninterpretable radar data. Full article

A new control system implemented with a single-stage DC-DC controller to power an LED headlamp for automotive applications is presented in this work. Daytime running light (DRL), low beam (LB), high beam (HB) and adaptive driving beam (ADB) are typical functions requiring a dedicated LED driver solution to fulfill car maker requirements for front-light applications. Single-stage drivers often exhibit a significant overshoot in LED current during transitions from driving a higher number of LEDs to a lower number. To maintain LED reliability, this current overshoot must remain below the maximum current rating of the LEDs. If the overshoot overcomes this limit, it can cause permanent damage to the LEDs or reduce their lifespan. To preserve LED reliability, a comprehensive system has been proposed to minimize the peak of LED current overshoots, especially during transitions between different operating modes or LED string configurations. A key feature of the proposed system is the implementation of a parallel discharging path to be activated only when the current flowing in the LEDs is higher than a predefined threshold. A prototype incorporating an integrated test chip has been developed to validate this approach. Measurement results and comparison with state-of-the-art solutions available in the market are shown. Furthermore, a critical aspect to be considered is the proper dimensioning of the discharging path. It requires careful considerations about the gate driver capabilities, the discharging resistor values, and the thermal management of the dumping element. For this purpose, an extensive study on how to size the relative components is also presented. Full article

The paper aims to provide a flood prediction system in the Philippines to increase flood awareness, which may help reduce property damage and save lives. Real-time flood status can significantly increase community awareness and preparedness. A flood model will simulate the flood level with secured data flow from the sensor to the cloud. The algorithms embedded in the flood predicting model include fuzzy logic, LSTM neural network, and genetic algorithm. The project used the Infineon security module (Infineon Technologies Philippines Inc., Metro Manila, Philippines) to create a secure connection from the setup to the AWS. All data transmitted were encrypted when being sent to AWS IoT Core, Timestream, and Grafana. After training and testing, the neuro-fuzzy LSTM network with genetic algorithm solution showed improved flood prediction accuracy of 92.91% compared to the ADAM solver that predicts every 2 h using an 0.02 initial learning rate, 1000 LSTM hidden layers, and 1000 epochs. The best solution predicts a flood every 3 h using an ADAM solver, a 0.01 initial learning rate, and 244 LSTM hidden layers for 158 epochs. Full article