Sensors

20 pages, 1240 KiB

Open AccessArticle

Continuous Monitoring of Recruits During Military Basic Training to Mitigate Attrition

by Robbe Decorte, Jelle Vanhaeverbeke, Sarah VanDen Berghe, Maarten Slembrouck and Steven Verstockt

Sensors 2025, 25(6), 1828; https://doi.org/10.3390/s25061828 - 14 Mar 2025

This paper explores the use of wearable technology (Garmin Fenix 7) to monitor physiological and psychological factors contributing to attrition during basic military training. Attrition, or the voluntary departure of recruits from the military, often results from physical and psychological challenges, such as [...] Read more.

This paper explores the use of wearable technology (Garmin Fenix 7) to monitor physiological and psychological factors contributing to attrition during basic military training. Attrition, or the voluntary departure of recruits from the military, often results from physical and psychological challenges, such as fatigue, injury, and stress, which lead to significant costs for the military. To better understand and mitigate attrition, we designed and implemented a comprehensive and continuous data-capturing methodology to monitor 63 recruits during their basic infantry training. It’s optimized for military use by being minimally invasive (for both recruits and operators), preventing data leakage, and being built for scale. We analysed data collected from two test phases, focusing on seven key psychometric and physical features derived from baseline questionnaires and physiological measurements from wearable devices. The preliminary results revealed that recruits at risk of attrition tend to cluster in specific areas of the feature space in both Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA). Key indicators of attrition included low motivation, low resilience, and a stress mindset. Furthermore, we developed a predictive model using physiological data, such as sleep scores and step counts from Garmin devices, achieving a macro mean absolute error (MAE) of 0.74. This model suggests the potential to reduce the burden of daily wellness questionnaires by relying on continuous, unobtrusive monitoring. Full article

(This article belongs to the Special Issue Sports Sensors for Athlete Motion Tracking and Physiological Monitoring: Second Edition)

► Show Figures

Figure 1

22 pages, 20768 KiB

Open AccessArticle

Enhancing EEG-Based Emotion Detection with Hybrid Models: Insights from DEAP Dataset Applications

by Badr Mouazen, Ayoub Benali, Nouh Taha Chebchoub, El Hassan Abdelwahed and Giovanni De Marco

Sensors 2025, 25(6), 1827; https://doi.org/10.3390/s25061827 - 14 Mar 2025

Abstract

Emotion detection using electroencephalogram (EEG) signals is a rapidly evolving field with significant applications in mental health diagnostics, affective computing, and human–computer interaction. However, existing approaches often face challenges related to accuracy, interpretability, and real-time feasibility. This study leverages the DEAP dataset to [...] Read more.

Emotion detection using electroencephalogram (EEG) signals is a rapidly evolving field with significant applications in mental health diagnostics, affective computing, and human–computer interaction. However, existing approaches often face challenges related to accuracy, interpretability, and real-time feasibility. This study leverages the DEAP dataset to explore and evaluate various machine learning and deep learning techniques for emotion recognition, aiming to address these challenges. To ensure reproducibility, we have made our code publicly available . Extensive experimentation was conducted using K-Nearest Neighbors (KNN), Support Vector Machines (SVMs), Decision Tree (DT), Random Forest (RF), Bidirectional Long Short-Term Memory (BiLSTM), Gated Recurrent Units (GRUs), Convolutional Neural Networks (CNNs), autoencoders, and transformers. Our hybrid approach achieved a peak accuracy of 85–95%, demonstrating the potential of advanced neural architectures in decoding emotional states from EEG signals. While this accuracy is slightly lower than some state-of-the-art methods, our approach offers advantages in computational efficiency and real-time applicability, making it suitable for practical deployment. Furthermore, we employed SHapley Additive exPlanations (SHAP) to enhance model interpretability, offering deeper insights into the contribution of individual features to classification decisions. A comparative analysis with existing methods highlights the novelty and advantages of our approach, particularly in terms of accuracy, interpretability, and computational efficiency. A key contribution of this study is the development of a real-time emotion detection system, which enables instantaneous classification of emotional states from EEG signals. We provide a detailed analysis of its computational efficiency and compare it with existing methods, demonstrating its feasibility for real-world applications. Our findings highlight the effectiveness of hybrid deep learning models in improving accuracy, interpretability, and real-time processing capabilities. These contributions have significant implications for applications in neurofeedback, mental health monitoring, and affective computing. Future work will focus on expanding the dataset, testing the system on a larger and more diverse participant pool, and further optimizing the system for broader clinical and industrial applications. Full article

(This article belongs to the Section Biomedical Sensors)

15 pages, 11135 KiB

Open AccessArticle

Resilient Communication for Software Defined Radio: Machine Reasoning and Electromagnetic Spectrum Evaluation

by Sergey Edward Lyshevski, Richard Buckley and Christopher Feuerstein

Sensors 2025, 25(6), 1826; https://doi.org/10.3390/s25061826 - 14 Mar 2025

Abstract

This paper investigates evaluation methodologies and machine reasoning schemes to analyze dynamic electromagnetic spectrum. We research practical and scalable classification of radio frequency signals across high frequency, very high frequency, ultra high frequency and super high frequency bands. The multi-band software defined radio, [...] Read more.

This paper investigates evaluation methodologies and machine reasoning schemes to analyze dynamic electromagnetic spectrum. We research practical and scalable classification of radio frequency signals across high frequency, very high frequency, ultra high frequency and super high frequency bands. The multi-band software defined radio, software defined mobile networks, and global navigation system receivers accomplish reconfigurable communication. Resilient communication, as well as high-fidelity analysis of extreme and congested electromagnetic spectra, are open problems due to challenges in classification of interference, distortions and adaptive jamming from spatially distributed transmitters and jammers. This paper documents high-fidelity characterization and dynamically reconfigured machine reasoning schemes to ensure the cognitive capabilities of communication systems. Low-fidelity experimental studies substantiate the spectrum evaluation methodology and demonstrate results. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

20 pages, 4396 KiB

Open AccessArticle

Squeeze-EnGAN: Memory Efficient and Unsupervised Low-Light Image Enhancement for Intelligent Vehicles

by Haegyo In, Juhum Kweon and Changjoo Moon

Sensors 2025, 25(6), 1825; https://doi.org/10.3390/s25061825 - 14 Mar 2025

Abstract

Intelligent vehicles, such as autonomous cars, drones, and robots, rely on sensors to gather environmental information and respond accordingly. RGB cameras are commonly used due to their low cost and high resolution but are limited in low-light conditions. While employing LiDAR or specialized [...] Read more.

Intelligent vehicles, such as autonomous cars, drones, and robots, rely on sensors to gather environmental information and respond accordingly. RGB cameras are commonly used due to their low cost and high resolution but are limited in low-light conditions. While employing LiDAR or specialized cameras can address this issue, these solutions often incur high costs. Deep learning-based low-light image enhancement (LLIE) methods offer an alternative, but existing models struggle to adapt to road scenes. Furthermore, most LLIE models rely on supervised training but are heavily constrained by the lack of low-light and normal-light paired datasets. In particular, obtaining paired datasets for driving scenes is extremely challenging. To address these issues, this paper proposes Squeeze-EnGAN, a memory-efficient, GAN-based LLIE method capable of unsupervised learning without paired image datasets. Squeeze-EnGAN incorporates a fire module into a U-net architecture, substantially reducing the number of parameters and Multiply-Accumulate Operations (MACs) compared to its base model, EnlightenGAN. Additionally, Squeeze-EnGAN achieves real-time performance on devices like Jetson Xavier (0.061 s). Significantly, enhanced images improve object detection performance over original images, demonstrating the model’s potential to aid high-level vision tasks in intelligent vehicles. Full article

(This article belongs to the Section Vehicular Sensing)

► Show Figures

Figure 1

18 pages, 979 KiB

Open AccessArticle

TipSegNet: Fingertip Segmentation in Contactless Fingerprint Imaging

by Laurenz Ruzicka, Bernhard Kohn and Clemens Heitzinger

Sensors 2025, 25(6), 1824; https://doi.org/10.3390/s25061824 - 14 Mar 2025

Abstract

Contactless fingerprint recognition systems offer a hygienic, user-friendly, and efficient alternative to traditional contact-based methods. However, their accuracy heavily relies on precise fingertip detection and segmentation, particularly under challenging background conditions. This paper introduces TipSegNet, a novel deep learning model that achieves state-of-the-art [...] Read more.

Contactless fingerprint recognition systems offer a hygienic, user-friendly, and efficient alternative to traditional contact-based methods. However, their accuracy heavily relies on precise fingertip detection and segmentation, particularly under challenging background conditions. This paper introduces TipSegNet, a novel deep learning model that achieves state-of-the-art performance in segmenting fingertips directly from grayscale hand images. TipSegNet leverages a ResNeXt-101 backbone for robust feature extraction, combined with a Feature Pyramid Network (FPN) for multi-scale representation, enabling accurate segmentation across varying finger poses and image qualities. Furthermore, we employ an extensive data augmentation strategy to enhance the model’s generalizability and robustness. This model was trained and evaluated using a combined dataset of 2257 labeled hand images. TipSegNet outperforms existing methods, achieving a mean intersection over union (mIoU) of 0.987 and an accuracy of 0.999, representing a significant advancement in contactless fingerprint segmentation. This enhanced accuracy has the potential to substantially improve the reliability and effectiveness of contactless biometric systems in real-world applications. Full article

(This article belongs to the Special Issue AI-Based Computer Vision Sensors & Systems)

31 pages, 2073 KiB

Open AccessArticle

Single Fringe Phase Retrieval for Translucent Object Measurements Using a Deep Convolutional Generative Adversarial Network

by Jiayan He, Yuanchang Huang, Juhao Wu, Yadong Tang and Wenlong Wang

Sensors 2025, 25(6), 1823; https://doi.org/10.3390/s25061823 - 14 Mar 2025

Abstract

Fringe projection profilometry (FPP) is a measurement technique widely used in the field of 3D reconstruction. However, it faces issues of phase shift and reduced fringe modulation depth when measuring translucent objects, leading to decreased measurement accuracy. To reduce the impact of surface [...] Read more.

Fringe projection profilometry (FPP) is a measurement technique widely used in the field of 3D reconstruction. However, it faces issues of phase shift and reduced fringe modulation depth when measuring translucent objects, leading to decreased measurement accuracy. To reduce the impact of surface scattering effects on the wrapped phase during actual measurement, we propose a single-frame phase retrieval method named GAN-PhaseNet to improve the subsequent measurement accuracy for translucent objects. The network primarily relies on a generative adversarial network framework, with significant enhancements implemented in the generator network, including integrating the U-net++ architecture, Resnet101 as the backbone network for feature extraction, and a multilevel attention module for fully utilizing the high-level features of the source image. The results of the ablation and comparison experiment show that the proposed method has superior phase retrieval results, not only achieving the accuracy of the conventional method on objects with no scattering effect and a slight scattering effect but also obtaining the lowest errors on objects with severe scattering effects when compared with other phase retrieval convolution neural networks (CDLP, Unet-Phase, and DCFPP). Under varying noise levels and fringe frequencies, the proposed method demonstrates excellent robustness and generalization capabilities. It can be applied to computational imaging techniques in the fringe projection field, introducing new ideas for the measurement of translucent objects. Full article

(This article belongs to the Special Issue Convolutional Neural Network Technology for 3D Imaging and Sensing)

17 pages, 14201 KiB

Open AccessArticle

Displacement Sensing Using Bimodal Resonance in Over-Coupled Inductors

by Alexis Hernandez Arroyo, George Overton, Anthony J. Mulholland and Robert R. Hughes

Sensors 2025, 25(6), 1822; https://doi.org/10.3390/s25061822 - 14 Mar 2025

Abstract

This paper presents the theory and key experimental findings for investigating the generation of bimodal resonance (frequency-splitting) phenomena in mutually over-coupled inductive sensors and its exploitation to evaluate relative separation and angular displacement between coils. This innovative measurement technique explores the bimodal resonant [...] Read more.

This paper presents the theory and key experimental findings for investigating the generation of bimodal resonance (frequency-splitting) phenomena in mutually over-coupled inductive sensors and its exploitation to evaluate relative separation and angular displacement between coils. This innovative measurement technique explores the bimodal resonant phenomena observed between two coil designs—solenoid and planar coil geometries. The proposed sensors are evaluated against first-order analytical functions and finite element models, before experimentally validating the predicted phenomenon for the different sensor configurations. The simulated and experimental results show excellent agreement, and first-order best-fit functions are employed to predict displacement variables experimentally. Co-planar separation and angular displacement are shown to be experimentally predictable to within

\pm 1 mm

and

\pm 1^{\circ}

using this approach. This study validates the first-order physics-based models employed and demonstrates the first proof of principle for using resonant phenomena in inductive array sensors for evaluating relative displacement between array elements. Full article

(This article belongs to the Special Issue Electromagnetic Non-destructive Testing and Evaluation)

42 pages, 8059 KiB

Open AccessArticle

Internet of Things-Cloud Control of a Robotic Cell Based on Inverse Kinematics, Hardware-in-the-Loop, Digital Twin, and Industry 4.0/5.0

by Dan Ionescu, Adrian Filipescu, Georgian Simion and Adriana Filipescu

Sensors 2025, 25(6), 1821; https://doi.org/10.3390/s25061821 - 14 Mar 2025

Abstract

The main task of the research involves creating a Digital Twin (DT) application serving as a framework for Virtual Commissioning (VC) with Supervisory Control and Data Acquisition (SCADA) and Cloud storage solutions. An Internet of Things (IoT) integrated automation system with Virtual Private [...] Read more.

The main task of the research involves creating a Digital Twin (DT) application serving as a framework for Virtual Commissioning (VC) with Supervisory Control and Data Acquisition (SCADA) and Cloud storage solutions. An Internet of Things (IoT) integrated automation system with Virtual Private Network (VPN) remote control for assembly and disassembly robotic cell (A/DRC) equipped with a six-Degree of Freedom (6-DOF) ABB 120 industrial robotic manipulator (IRM) is presented in this paper. A three-dimensional (3D) virtual model is developed using Siemens NX Mechatronics Concept Designer (MCD), while the Programmable Logic Controller (PLC) is programmed in the Siemens Totally Integrated Automation (TIA) Portal. A Hardware-in-the-Loop (HIL) simulation strategy is primarily used. This concept is implemented and executed as part of a VC approach, where the designed PLC programs are integrated and tested against the physical controller. Closed loop control and RM inverse kinematics model are validated and tested in PLC, following HIL strategy by integrating Industry 4.0/5.0 concepts. A SCADA application is also deployed, serving as a DT operator panel for process monitoring and simulation. Cloud data collection, analysis, supervising, and synchronizing DT tasks are also integrated and explored. Additionally, it provides communication interfaces via PROFINET IO to SCADA and Human Machine Interface (HMI), and through Open Platform Communication—Unified Architecture (OPC-UA) for Siemens NX-MCD with DT virtual model. Virtual A/DRC simulations are performed using the Synchronized Timed Petri Nets (STPN) model for control strategy validation based on task planning integration and synchronization with other IoT devices. The objective is to obtain a clear and understandable representation layout of the A/DRC and to validate the DT model by comparing process dynamics and robot motion kinematics between physical and virtual replicas. Thus, following the results of the current research work, integrating digital technologies in manufacturing, like VC, IoT, and Cloud, is useful for validating and optimizing manufacturing processes, error detection, and reducing the risks before the actual physical system is built or deployed. Full article

(This article belongs to the Special Issue Integrating Cloud Computing, Sensing Technologies, and Digital Twins in IoT Applications)

18 pages, 997 KiB

Open AccessArticle

A Positioning System Design Based on Tunnel Magnetoresistance Sensors for Rapid Zoom Optical Lens

by Junqiang Gong, Dameng Liu and Jianbin Luo

Sensors 2025, 25(6), 1820; https://doi.org/10.3390/s25061820 - 14 Mar 2025

Abstract

In response to the accurate positioning issue for high-speed moving lens groups in rapid zoom optical lenses with voice coil motors (VCMs), we demonstrate a positioning system design based on tunnel magnetoresistance sensors. The equivalent magnetic charge method and finite element method (FEM) [...] Read more.

In response to the accurate positioning issue for high-speed moving lens groups in rapid zoom optical lenses with voice coil motors (VCMs), we demonstrate a positioning system design based on tunnel magnetoresistance sensors. The equivalent magnetic charge method and finite element method (FEM) simulations were utilized to compute the magnetic field distribution of the magnetic grating encoder. Based on analytical computation, the optimal air gap δ_S between the sensor and magnetic grating is determined to be δ_S = 0.15 mm, which balances magnetic flux density amplitude and total harmonic distortion. In addition, a simplified fitting model is proposed to reduce computational complexity. We quantify the magnetic interference of VCM through three-dimensional flux leakage mapping by FEM analysis, deriving an optimal sensor position O_S, with a 24 mm y-offset and 20 mm z-offset relative to the VCM’s origin O_V. The position error caused by interference remains below 5 μm with maximum deviations at trajectory endpoints of the moving group. The original signal output is processed and corrected, and eventually, the measured displacement exhibits a linear relationship with actual displacement. Our study provides a comprehensive framework for the design and optimization of magnetic positioning systems in optical applications with electromagnetic motors. Full article

(This article belongs to the Special Issue Magnetic Sensors and Systems for Scientific and Industrial Applications)

27 pages, 3338 KiB

Open AccessArticle

Person Re-Identification with Attribute-Guided, Robust-to-Low-Resolution Drone Footage Considering Fog/Edge Computing

by Bongjun Kim, Sunkyu Kim, Seokwon Park and Junho Jeong

Sensors 2025, 25(6), 1819; https://doi.org/10.3390/s25061819 - 14 Mar 2025

Abstract

In aerial surveillance using drones, person re-identification (ReID) is crucial for public safety. However, low resolutions in drone footage often leads to a significant drop in ReID performance of subjects. To investigate this issue, rather than relying solely on real-world datasets, we employed [...] Read more.

In aerial surveillance using drones, person re-identification (ReID) is crucial for public safety. However, low resolutions in drone footage often leads to a significant drop in ReID performance of subjects. To investigate this issue, rather than relying solely on real-world datasets, we employed a synthetic dataset that systematically captures variations in drone altitude and distance. We also utilized an eXplainable Artificial Intelligence (XAI) framework to analyze how low resolutions affect ReID. Based on our findings, we propose a method that improves ReID accuracy by filtering out attributes that are not robust in low-resolution environments and retaining only those features that remain reliable. Experiments on the Market1501 dataset show a 6.59% percentage point improvement in accuracy at a 16% resolution scale. We further discuss the effectiveness of our approach in drone-based aerial surveillance systems under Fog/Edge Computing paradigms. Full article

(This article belongs to the Special Issue Integration of Edge/Fog Artificial Intelligence into Smart Distributed Systems)

21 pages, 8076 KiB

Open AccessArticle

Adaptive Communication Model for QoS in Vehicular IoT Systems Using CTMC

by Adeel Iqbal, Tahir Khurshaid, Ali Nauman and Sung Won Kim

Sensors 2025, 25(6), 1818; https://doi.org/10.3390/s25061818 - 14 Mar 2025

Abstract

Vehicular Internet of Things (V-IoT) systems will be critical in advancing intelligent transportation networks because of the easy communication they make possible between vehicles, roadside infrastructure, and other network entities. Integrating adaptive IoT-based communication models will increase resource utilization and allow multiple communications [...] Read more.

Vehicular Internet of Things (V-IoT) systems will be critical in advancing intelligent transportation networks because of the easy communication they make possible between vehicles, roadside infrastructure, and other network entities. Integrating adaptive IoT-based communication models will increase resource utilization and allow multiple communications in vehicular networks. This work proposes an Adaptive Multi-mode Spectrum Access (AMSA) approach for optimal Quality of Service (QoS) in multi-class V-IoT networks. Unlike traditional static spectrum access methods, AMSA switches between interweave, underlay, and coexistence modes based on network conditions. Our results indicate that AMSA improves spectrum usage by 56% over static spectrum access improves throughput by 110%, and reduces delay for low-priority traffic by up to 47.5%. This new integration offers robust vehicular communication with optimal resource allocation under different network scenarios Full article

(This article belongs to the Special Issue Multi-Agent Sensors Systems and Their Applications)

14 pages, 1219 KiB

Open AccessArticle

Shallow Sea Mobile Channel Estimation Method Based on Iterative Cancellation

by Cheng He, Tao Song, Lifangzheng Wang and Danying Zhang

Sensors 2025, 25(6), 1817; https://doi.org/10.3390/s25061817 - 14 Mar 2025

Abstract

The estimation of channels in shallow sea mobile communication systems presents significant challenges due to multipath propagation and non-uniform Doppler effects. Traditional channel estimation methods, such as least squares and least mean squares, fail to accurately handle these issues, leading to errors. To [...] Read more.

The estimation of channels in shallow sea mobile communication systems presents significant challenges due to multipath propagation and non-uniform Doppler effects. Traditional channel estimation methods, such as least squares and least mean squares, fail to accurately handle these issues, leading to errors. To address these limitations, this study proposes a high-precision channel estimation method based on iterative cancellation. The method uses cross-correlation of complex signals to identify Doppler shifts, select the most prominent shifts, and subtract corresponding reference signal components. This iterative process allows for precise separation of multipath signals and accurate estimation of the channel impulse response. Simulation and sea trial results show that the proposed method provides high temporal and amplitude resolution, robust noise immunity, and effective compensation for non-uniform Doppler effects, even under high-speed mobility. The method significantly improves channel estimation accuracy compared to traditional techniques, particularly in dynamic shallow sea environments. These findings contribute to enhancing the reliability and efficiency of underwater communication systems, which is critical for both military and civilian applications such as underwater navigation and environmental monitoring. Full article

(This article belongs to the Section Physical Sensors)

33 pages, 2118 KiB

Open AccessArticle

An Improved Software Source Code Vulnerability Detection Method: Combination of Multi-Feature Screening and Integrated Sampling Model

by Xin He, Asiya, Daoqi Han, Shuncheng Zhou, Xueliang Fu and Honghui Li

Sensors 2025, 25(6), 1816; https://doi.org/10.3390/s25061816 - 14 Mar 2025

Abstract

Vulnerability detection in software source code is crucial in ensuring software security. Existing models face challenges with dataset class imbalance and long training times. To address these issues, this paper introduces a multi-feature screening and integrated sampling model (MFISM) to enhance vulnerability detection [...] Read more.

Vulnerability detection in software source code is crucial in ensuring software security. Existing models face challenges with dataset class imbalance and long training times. To address these issues, this paper introduces a multi-feature screening and integrated sampling model (MFISM) to enhance vulnerability detection efficiency and accuracy. The key innovations include (i) utilizing abstract syntax tree (AST) representation of source code to extract potential vulnerability-related features through multiple feature screening techniques; (ii) conducting analysis of variance (ANOVA) and evaluating feature selection techniques to identify representative and discriminative features; (iii) addressing class imbalance by applying an integrated over-sampling strategy to create synthetic samples from vulnerable code to expand the minority class sample size; (iv) employing outlier detection technology to filter out abnormal synthetic samples, ensuring high-quality synthesized samples. The model employs a bidirectional long short-term memory network (Bi-LSTM) to accurately identify vulnerabilities in the source code. Experimental results demonstrate that MFISM improves the F1 score performance by approximately 10% compared to existing DeepBalance methods and reduces the training time to 2–3 h. These results confirm the effectiveness and superiority of MFISM in source code vulnerability detection tasks. Full article

(This article belongs to the Section Intelligent Sensors)

19 pages, 847 KiB

Open AccessArticle

The Newer, the More Secure? Standards-Compliant Bluetooth Low Energy Man-in-the-Middle Attacks on Fitness Trackers

by Hannah Greß, Björn Krüger and Elmar Tischhauser

Sensors 2025, 25(6), 1815; https://doi.org/10.3390/s25061815 - 14 Mar 2025

Abstract

The trend in self-tracking devices has remained unabated for years. Even if they record a large quantity of sensitive data, most users are not concerned about their data being transmitted and stored in a secure way from the device via the companion app [...] Read more.

The trend in self-tracking devices has remained unabated for years. Even if they record a large quantity of sensitive data, most users are not concerned about their data being transmitted and stored in a secure way from the device via the companion app to the vendor’s server. However, the secure implementation of this chain from the manufacturer is not always given, as various publications have already shown. Therefore, we first provide an overview of attack vectors within the ecosystem of self-tracking devices. Second, we evaluate the data security of eight contemporary fitness trackers from leading vendors by applying four still partly standards-compliant Bluetooth Low-Energy Man-in-the-Middle (MitM) attacks. Our results show that the examined devices are partially vulnerable against the attacks. For most of the trackers, the manufacturers put different security measures in place. These include short and user-initiated visibility and connectivity or app-level authentication to limit the attack surface. Interestingly, newer models are more likely to be attackable, underlining the constant need for verifying the security of BLE devices, reporting found vulnerabilities, and also strengthening standards and improving security awareness among manufacturers and users. Therefore, we finish our work with recommendations and best practices for law- and regulation-makers, vendors, and users on how to strengthen the security of BLE devices. Full article

(This article belongs to the Special Issue Cybersecurity in IoT-Based Applications)

18 pages, 1122 KiB

Open AccessArticle

Multi-Scale Convolutional Attention and Structural Re-Parameterized Residual-Based 3D U-Net for Liver and Liver Tumor Segmentation from CT

by Ziwei Song, Weiwei Wu and Shuicai Wu

Sensors 2025, 25(6), 1814; https://doi.org/10.3390/s25061814 - 14 Mar 2025

Abstract

Accurate segmentation of the liver and liver tumors is crucial for clinical diagnosis and treatment. However, the task poses significant challenges due to the complex morphology of tumors, indistinct features of small targets, and the similarity in grayscale values between the liver and [...] Read more.

Accurate segmentation of the liver and liver tumors is crucial for clinical diagnosis and treatment. However, the task poses significant challenges due to the complex morphology of tumors, indistinct features of small targets, and the similarity in grayscale values between the liver and surrounding organs. To address these issues, this paper proposes an enhanced 3D UNet architecture, named ELANRes-MSCA-UNet. By incorporating a structural re-parameterized residual module (ELANRes) and a multi-scale convolutional attention module (MSCA), the network significantly improves feature extraction and boundary optimization, particularly excelling in segmenting small targets. Additionally, a two-stage strategy is employed, where the liver region is segmented first, followed by the fine-grained segmentation of tumors, effectively reducing false positive rates. Experiments conducted on the LiTS2017 dataset demonstrate that the ELANRes-MSCA-UNet achieved Dice scores of 97.2% and 72.9% for liver and tumor segmentation tasks, respectively, significantly outperforming other state-of-the-art methods. These results validate the accuracy and robustness of the proposed method in medical image segmentation and highlight its potential for clinical applications. Full article

(This article belongs to the Section Sensor Networks)

18 pages, 648 KiB

Open AccessArticle

Proposal for a Battery to Evaluate Functional Capacity in Older Adults with Disabilities

by Josu Ascondo, Iñaki Llodio, Bingen Marcos-Rivero, Cristina Granados, Sheila Romero, Aitor Iturricastillo and Javier Yanci

Sensors 2025, 25(6), 1813; https://doi.org/10.3390/s25061813 - 14 Mar 2025

Abstract

The purpose was to design and validate a battery of physical tests, called EFEPD-1.0, adapted to assess functionality in people with disabilities. In addition, we sought to analyze the validity and reliability of this battery both for the total group and differentiated by [...] Read more.

The purpose was to design and validate a battery of physical tests, called EFEPD-1.0, adapted to assess functionality in people with disabilities. In addition, we sought to analyze the validity and reliability of this battery both for the total group and differentiated by sex. A total of 43 adults with disabilities (32 women and 11 men) participated (57.11 ± 10.12 years). The battery was composed of five blocks of functionality: neuromuscular, combined actions, acceleration, balance, and cardiovascular. The neuromuscular functionality was measured by the vertical and horizontal jump test using the optical system (Opto Jump Next^®, Microgate, Bolzano, Italy) as well as the Hand Grip (HG) test using a (5030J1, Jamar^®, Sammons Preston, Inc, Nottinghamshire, UK) hand dynamometer. The combined actions and balance functionality were assessed with the Time Up and Go (TUG) test, the 30 s Chair Stand (30CTS) test, and the One-Leg Stance (OLS) test measured by a manual stopwatch (HS-80TW-1EF, Casio^®, Tokyo, Japan). The acceleration functionality was evaluated through 20 m sprints and the 505 change of direction (COD505) test, using the (Microgate, Witty^®, Bolzano, Italy) photocell system. The cardiovascular functionality was evaluated with the Six-Minute Walking Test (6MWT), where heart rate was monitored using the (Polar Team Sport System^®, Polar Electro Oy, Kempele, Finland), and additional walking mechanics were recorded with Stryd (Stryd Everest 12 Firmware 1.18 Software 3, Stryd Inc., Boulder, CO, USA). The results showed that the intraclass correlation coefficients (ICCs) ranged from moderate to almost perfect (ICC = 0.65–0.98) between test repetitions. Some tests could significantly differentiate (p < 0.05) men and women, highlighting better neuromuscular capacity in men and better balance in women. The correlations between tests showed significant convergent validity. The Evaluation of Functionality in the Disabled Population (EFEPD-1.0) battery not only consistently measures functional capacities in people with disabilities, but it can also discriminate between different subgroups within this population. Full article

(This article belongs to the Collection Sensors for Globalized Healthy Living and Wellbeing)

33 pages, 1203 KiB

Open AccessReview

Recent Advances in Vehicle Driver Health Monitoring Systems

by Lauris Melders, Ruslans Smigins and Aivars Birkavs

Sensors 2025, 25(6), 1812; https://doi.org/10.3390/s25061812 - 14 Mar 2025

Abstract

The need for creative solutions in the real-time monitoring of health is rapidly increasing, especially in light of health incidents in relation to drivers of motor vehicles. A sensor-based health monitoring system provides an integrated mechanism for diagnosing and managing in real time, [...] Read more.

The need for creative solutions in the real-time monitoring of health is rapidly increasing, especially in light of health incidents in relation to drivers of motor vehicles. A sensor-based health monitoring system provides an integrated mechanism for diagnosing and managing in real time, enabling the detection, prediction, and recommendation of treatment and the prevention of disease onset. The real-time monitoring of driver’s health represents a significant advancement in the assurance of driver safety and well-being. From fitness trackers to advanced biosensors, these devices have not only made healthcare more accessible but have also transformed how people interact with their health data. The purpose of this scoping review is to systematically collect and evaluate information from publications on driver health monitoring systems to provide a comprehensive overview of the current state of research on wearable or remote sensor technologies for driver health monitoring. It aims to identify knowledge gaps that need to be addressed and suggest future research directions that will help to fill these gaps. This approach involves the topic of vehicle safety and healthcare and will contribute to the advancement of this field. By focusing on the real-time monitoring of health parameters in an automotive context, this review highlights the potential of different types of technologies to bridge the gap between health monitoring and driver safety. Full article

(This article belongs to the Special Issue Wearable Sensors for Continuous Health Monitoring and Analysis)

19 pages, 3440 KiB

Open AccessArticle

Experimental Demonstration of Sensing Using Hybrid Reconfigurable Intelligent Surfaces

by Idban Alamzadeh and Mohammadreza F. Imani

Sensors 2025, 25(6), 1811; https://doi.org/10.3390/s25061811 - 14 Mar 2025

Abstract

Acquiring information about the surrounding environment is crucial for reconfigurable intelligent surfaces (RISs) to effectively manipulate radio wave propagation. This operation can be fully automated by incorporating an integrated sensing mechanism, leading to a hybrid configuration known as a hybrid reconfigurable intelligent surface [...] Read more.

Acquiring information about the surrounding environment is crucial for reconfigurable intelligent surfaces (RISs) to effectively manipulate radio wave propagation. This operation can be fully automated by incorporating an integrated sensing mechanism, leading to a hybrid configuration known as a hybrid reconfigurable intelligent surface (HRIS). Several HRIS geometries have been studied in previous works, with full-wave simulations used to showcase their sensing capabilities. However, these simulated models often fail to address the practical design challenges associated with HRISs. This paper presents an experimental proof-of-concept for an HRIS, focusing on the design considerations that have been neglected in simulations but are vital for experimental validation. The HRIS prototype comprises two types of elements: a conventional element designed for reconfigurable reflection and a hybrid one for sensing and reconfigurable reflection. The metasurface can carry out the required sensing operations by utilizing signals coupled to several hybrid elements. This paper outlines the design considerations necessary to create a practical HRIS configuration that can be fabricated using standard PCB technology. The sensing capabilities of the HRIS are demonstrated experimentally through angle of arrival (AoA) detection. The proposed HRIS has the potential to facilitate smart, autonomous wireless communication networks, wireless power transfer, and sensing systems. Full article

(This article belongs to the Special Issue Advanced Massive MIMO Antenna Arrays, Metasurfaces and Reconfigurable Intelligent Surfaces for Sensing, Localization, and Wireless Communications: 2nd Edition)

► Show Figures

Figure 1

19 pages, 13145 KiB

Open AccessArticle

AI-Powered Noninvasive Electrocardiographic Imaging Using the Priori-to-Attention Network (P2AN) for Wearable Health Monitoring

by Shijie He, Hanrui Dong, Xianbin Zhang, Richard Millham, Lin Xu and Wanqing Wu

Sensors 2025, 25(6), 1810; https://doi.org/10.3390/s25061810 - 14 Mar 2025

Abstract

The rapid development of smart wearable devices has significantly advanced noninvasive, continuous health monitoring, enabling real-time collection of vital biosignals. Electrocardiographic imaging (ECGI), a noninvasive technique that reconstructs transmembrane potential (TMP) from body surface potential, has emerged as a promising method for reflecting [...] Read more.

The rapid development of smart wearable devices has significantly advanced noninvasive, continuous health monitoring, enabling real-time collection of vital biosignals. Electrocardiographic imaging (ECGI), a noninvasive technique that reconstructs transmembrane potential (TMP) from body surface potential, has emerged as a promising method for reflecting cardiac electrical activity. However, the ECG inverse problem’s inherent instability has hindered its practical application. To address this, we introduce a novel Priori-to-Attention Network (P2AN) that enhances the stability of ECGI solutions. By leveraging the one-dimensional nature of electrical signals and the body’s electrical propagation properties, P2AN uses small-scale convolutions for attention computation, integrating a priori physiological knowledge via cross-attention mechanisms. This approach eliminates the need for clinical TMP measurements and improves solution accuracy through normalization constraints. We evaluate the method’s effectiveness in diagnosing myocardial ischemia and ventricular hypertrophy, demonstrating significant improvements in TMP reconstruction and lesion localization. Moreover, P2AN exhibits high robustness in noisy environments, making it highly suitable for integration with wearable electrocardiographic clothing. By improving spatiotemporal accuracy and noise resilience, P2AN offers a promising solution for noninvasive, real-time cardiovascular monitoring using AI-powered wearable devices. Full article

(This article belongs to the Special Issue Advances in ECG/EEG Monitoring)

► Show Figures

Figure 1

Journal Description

Sensors

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI