Next Issue
Volume 25, October-2
Previous Issue
Volume 25, September-2
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.2
3.5
Journals
Sensors
Volume 25
Issue 19
sensors-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Sensors, Volume 25, Issue 19 (October-1 2025) – 327 articles

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Cover Story (view full-size image):
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
17 pages, 1758 KB  
Review
A Guide to Recognizing Your Electrochemical Impedance Spectra: Revisions of the Randles Circuit in (Bio)sensing
by Alexandros Lazanas and Beatriz Prieto Simón
Sensors 2025, 25(19), 6260; https://doi.org/10.3390/s25196260 - 9 Oct 2025
Viewed by 326
Abstract
Electrochemical impedance spectroscopy (EIS) is a highly versatile electrochemical technique capable of discretizing each electrochemical parameter in complex systems by employing a broad frequency spectrum. When EIS is employed in (bio)sensing applications, the electrochemical parameters are usually fitted into a relatively limited equivalent [...] Read more.
Electrochemical impedance spectroscopy (EIS) is a highly versatile electrochemical technique capable of discretizing each electrochemical parameter in complex systems by employing a broad frequency spectrum. When EIS is employed in (bio)sensing applications, the electrochemical parameters are usually fitted into a relatively limited equivalent circuit model regardless of the system at hand. This work thoroughly discusses the meaning of each physical parameter in the Randles circuit, the most common equivalent circuit to model (bio)sensing systems based on EIS transduction. Additionally, it pinpoints the most suitable modifications to the Randles circuit for modern-day electrodes, where coatings of non-biological and/or biological materials can radically impact the measured impedance compared to that of unmodified electrodes. The discussion is supported by simulations that clearly exhibit the effect of each examined parameter, providing guidance for experimentalists to improve the accuracy of their work. Full article
(This article belongs to the Special Issue Advances in Electrochemical Sensors for Biomarker Detection, Biomolecular Interaction Analysis and Nanomaterial-Enhanced Sensing Platforms)
►▼ Show Figures

Figure 1

30 pages, 5986 KB  
Article
Attention-Aware Graph Neural Network Modeling for AIS Reception Area Prediction
by Ambroise Renaud, Clément Iphar and Aldo Napoli
Sensors 2025, 25(19), 6259; https://doi.org/10.3390/s25196259 - 9 Oct 2025
Viewed by 514
Abstract
Accurately predicting the reception area of the Automatic Identification System (AIS) is critical for ship tracking and anomaly detection, as errors in signal interpretation may lead to incorrect vessel localization and behavior analysis. However, traditional propagation models, whether they are deterministic, empirical, or [...] Read more.
Accurately predicting the reception area of the Automatic Identification System (AIS) is critical for ship tracking and anomaly detection, as errors in signal interpretation may lead to incorrect vessel localization and behavior analysis. However, traditional propagation models, whether they are deterministic, empirical, or semi-empirical, face limitations when applied to dynamic environments due to their reliance on detailed atmospheric and terrain inputs. Therefore, to address these challenges, we propose a data-driven approach based on graph neural networks (GNNs) to model AIS reception as a function of environmental and geographic variables. Specifically, inspired by attention mechanisms that power transformers in large language models, our framework employs the SAmple and aggreGatE (GraphSAGE) framework convolutions to aggregate neighborhood features, then combines layer outputs through Jumping Knowledge (JK) with Bidirectional Long Short-Term Memory (BiLSTM)-derived attention coefficients and integrates an attentional pooling module at the graph-level readout. Moreover, trained on real-world AIS data enriched with terrain and meteorological features, the model captures both local and long-range reception patterns. As a result, it outperforms classical baselines—including ITU-R P.2001 and XGBoost in F1-score and accuracy. Ultimately, this work illustrates the value of deep learning and AIS sensor networks for the detection of positioning anomalies in ship tracking and highlights the potential of data-driven approaches in modeling sensor reception. Full article
(This article belongs to the Special Issue Transformer Applications in Target Tracking)
►▼ Show Figures

Figure 1

24 pages, 4574 KB  
Article
Design and Implementation of an Inductive Proximity Sensor with Embedded Systems
by Septimiu Sever Pop, Alexandru-Florin Flutur and Alexandra Fodor
Sensors 2025, 25(19), 6258; https://doi.org/10.3390/s25196258 - 9 Oct 2025
Viewed by 316
Abstract
Non-mechanical contact distance measurement solutions are becoming more and more necessary in various industries, including building monitoring, automotive, and aviation industries. Inductive proximity sensor (IPS) technology is becoming a more popular solution in the field of short distances. Because of its small size, [...] Read more.
Non-mechanical contact distance measurement solutions are becoming more and more necessary in various industries, including building monitoring, automotive, and aviation industries. Inductive proximity sensor (IPS) technology is becoming a more popular solution in the field of short distances. Because of its small size, dependability, and measurement capabilities, IPS is a good option. Separate circuits are used in the classical structures to generate the excitation signal for the sensor coil and measure the response signal. The response signal’s amplitude is typically measured. This article proposes an IPS model that uses frequency response as its basis for operation. A microcontroller and embedded technology are used to implement a small IPS structure. This includes the circuit for determining distance, as well as the signal generator used to excite the sensor coil. In essence, an LC circuit is employed, which at the unit step has a damped oscillatory response by nature. Periodically injecting energy into the LC circuit, however, causes it to enter a persistent oscillatory state. The full experimental model is implemented and presented in the article, illustrating how the distance can be measured with a 33 µm accuracy within the 10 mm range with the help of the nonlinear relationship between frequency and distance and the linear drift of frequency with temperature. Full article
(This article belongs to the Section Electronic Sensors)
►▼ Show Figures

Figure 1

13 pages, 2092 KB  
Article
Energy-Expenditure Estimation During Aerobic Training Sessions for Badminton Players
by Xinke Yan, Jingmin Yang, Jin Dai and Kuan Tao
Sensors 2025, 25(19), 6257; https://doi.org/10.3390/s25196257 - 9 Oct 2025
Viewed by 303
Abstract
This study investigated differences in energy-expenditure (EE) modeling between badminton players of varying competitive levels during aerobic training. It evaluated the impact of sensor quantity and sample size on prediction model accuracy and generalizability, providing evidence for personalized training-load monitoring. Fifty badminton players [...] Read more.
This study investigated differences in energy-expenditure (EE) modeling between badminton players of varying competitive levels during aerobic training. It evaluated the impact of sensor quantity and sample size on prediction model accuracy and generalizability, providing evidence for personalized training-load monitoring. Fifty badminton players (25 elite, 25 enthusiasts) performed treadmill running, cycling, rope skipping, and stair walking. Data were collected using accelerometers (waist, wrists, ankles), a heart rate monitor, and indirect calorimetry (criterion EE). Multiple machine learning models (Linear Regression, Bayesian Ridge Regression, Random Forest, Gradient Boosting) were employed to develop EE prediction models. Performance was assessed using R2, mean absolute percentage error (MAPE), and root mean square error (RMSE), with further evaluation via the Triple-E framework (Effectiveness, Efficiency, Extension). Elite athletes demonstrated stable, coordinated movement patterns, achieving the best values for R2 and the smallest errors using minimal core sensors (typically dominant side). Enthusiasts required multi-site sensors to compensate for greater execution variability. Increasing sensors beyond three yielded no performance gains; optimal configurations involved 2–3 core accelerometers combined with heart rate data. Expanding sample size significantly enhanced model stability and generalizability (e.g., running task R2 increased from 0.49 (N = 20) to 0.95 (N = 40)). Triple-E evaluation indicated that strategic sensor minimization coupled with sufficient sample size maximized predictive performance while reducing computational cost and deployment burden. Competitive level significantly influences EE modeling requirements. Elite athletes are suited to a “low-sensor, small-sample” scenario, whereas enthusiasts necessitate a “multi-sensor, large-sample” strategy. Full article
(This article belongs to the Section Wearables)
►▼ Show Figures

Figure 1

26 pages, 52162 KB  
Article
ASFT-Transformer: A Fast and Accurate Framework for EEG-Based Pilot Fatigue Recognition
by Jiming Liu, Yi Zhou, Qileng He and Zhenxing Gao
Sensors 2025, 25(19), 6256; https://doi.org/10.3390/s25196256 - 9 Oct 2025
Viewed by 454
Abstract
Objective evaluation of pilot fatigue is crucial for enhancing aviation safety. Although electroencephalography (EEG) is regarded as an effective tool for recognizing pilot fatigue, the direct application of deep learning models to raw EEG signals faces significant challenges due to issues such as [...] Read more.
Objective evaluation of pilot fatigue is crucial for enhancing aviation safety. Although electroencephalography (EEG) is regarded as an effective tool for recognizing pilot fatigue, the direct application of deep learning models to raw EEG signals faces significant challenges due to issues such as massive data volume, excessively long training time, and model overfitting. Moreover, existing feature-based methods often suffer from data redundancy due to the lack of effective feature and channel selections, which compromises the model’s recognition efficiency and accuracy. To address these issues, this paper proposes a framework, named ASFT-Transformer, for fast and accurate detection of pilot fatigue. This framework first extracts time-domain and frequency-domain features from the four EEG frequency bands. Subsequently, it introduces a feature and channel selection strategy based on one-way analysis of variance and support vector machine (ANOVA-SVM) to identify the most fatigue-relevant features and pivotal EEG channels. Finally, the FT-Transformer (Feature Tokenizer + Transformer) model is employed for classification based on the selected features, transforming the fatigue recognition problem into a tabular data classification task. EEG data is collected from 32 pilots before and after actual simulator training to validate the proposed method. The results show that ASFT-Transformer achieved average accuracies of 97.24% and 87.72% based on cross-clip data partitioning and cross-subject data partitioning, which were significantly superior to several mainstream machine learning and deep learning models. Under the two types of cross-validation, the proposed feature and channel selection strategy not only improved the average accuracy by 2.45% and 8.07%, respectively, but also drastically reduced the average training time from above 1 h to under 10 min. This study offers civil aviation authorities and airline operators a tool to manage pilot fatigue objectively and effectively, thereby contributing to flight safety. Full article
(This article belongs to the Section Biomedical Sensors)
►▼ Show Figures

Figure 1

19 pages, 12575 KB  
Article
MLG-STPM: Meta-Learning Guided STPM for Robust Industrial Anomaly Detection Under Label Noise
by Yu-Hang Huang, Sio-Long Lo, Zhen-Qiang Chen and Jing-Kai Wang
Sensors 2025, 25(19), 6255; https://doi.org/10.3390/s25196255 - 9 Oct 2025
Viewed by 308
Abstract
Industrial image anomaly detection (IAD) is crucial for quality control, but its performance often degrades when training data contain label noise. To circumvent the reliance on potentially flawed labels, unsupervised methods that learn from the data distribution itself have become a mainstream approach. [...] Read more.
Industrial image anomaly detection (IAD) is crucial for quality control, but its performance often degrades when training data contain label noise. To circumvent the reliance on potentially flawed labels, unsupervised methods that learn from the data distribution itself have become a mainstream approach. Among various unsupervised techniques, student–teacher frameworks have emerged as a highly effective paradigm. Student–Teacher Feature Pyramid Matching (STPM) is a powerful method within this paradigm, yet it is susceptible to such noise. Inspired by STPM and aiming to solve this issue, this paper introduces Meta-Learning Guided STPM (MLG-STPM), a novel framework that enhances STPM’s robustness by incorporating a guidance mechanism inspired by meta-learning. This guidance is achieved through an Evolving Meta-Set (EMS), which dynamically maintains a small high-confidence subset of training samples identified by their low disagreement between student and teacher networks. By training the student network on a combination of the current batch and the EMS, MLG-STPM effectively mitigates the impact of noisy labels without requiring an external clean dataset or complex re-weighting schemes. Comprehensive experiments on the MVTec AD and VisA benchmark datasets with synthetic label noise (0% to 20%) demonstrate that MLG-STPM significantly improves anomaly detection and localization performance compared to the original STPM, especially under higher noise conditions, and achieves competitive results against other relevant approaches. Full article
(This article belongs to the Section Industrial Sensors)
►▼ Show Figures

Figure 1

30 pages, 5285 KB  
Article
A Mixed Gas Component Identification and Concentration Estimation Method for Unbalanced Gas Sensor Array Samples
by Yuheng Lin, Jinlong Shi, Wanyu Xia, Mingjun Zhou and Yunpeng Gao
Sensors 2025, 25(19), 6254; https://doi.org/10.3390/s25196254 - 9 Oct 2025
Viewed by 293
Abstract
Component identification and concentration estimation of a gas mixture component are important for gas detection. However, the accuracy of traditional gas identification will decrease if the sample is not balanced or the number of samples is too few. In this paper, a method [...] Read more.
Component identification and concentration estimation of a gas mixture component are important for gas detection. However, the accuracy of traditional gas identification will decrease if the sample is not balanced or the number of samples is too few. In this paper, a method based on sample expansion is proposed to solve the aforementioned problem. Firstly, the ADASYN-ELM method is proposed to identify the composition of a gas mixture component. The KPCA is used to extract the feature of the sensor signal and the ADASYN method is used to expand the samples. The PSO and GA algorithms were used to optimize the parameters of the ELM classification model to complete the qualitative analysis. Secondly, the S-SMOTE-MLSSVR method was put forward to quantitatively estimate. The S-SMOTE method was used to expand the samples, and the regression model MLSSVR was optimized by PSO and GA algorithms to complete the quantitative analysis. The results show that the accuracy rate after sample expansion is generally higher and the MAPE and RMSE are generally lower than before sample expansion, indicating that the sample expansion method has a positive effect on classification and concentration estimation of mixed gases with extremely unbalanced samples and too few samples. Full article
(This article belongs to the Special Issue Gas Sensing for Air Quality Monitoring)
►▼ Show Figures

Figure 1

17 pages, 306 KB  
Article
Physical Workload Patterns in U-18 Basketball Using LPS and MEMS Data: A Principal Component Analysis by Quarter and Playing Position
by Sergio J. Ibáñez, Markel Rico-González, Carlos D. Gómez-Carmona and José Pino-Ortega
Sensors 2025, 25(19), 6253; https://doi.org/10.3390/s25196253 - 9 Oct 2025
Viewed by 480
Abstract
Basketball is a high-intensity, intermittent sport in which physical demands fluctuate depending on different contextual variables. Most studies addressed these demands in isolation without integrative approaches. Therefore, the present study aimed to identify key variables explaining players’ physical workload across game quarters and [...] Read more.
Basketball is a high-intensity, intermittent sport in which physical demands fluctuate depending on different contextual variables. Most studies addressed these demands in isolation without integrative approaches. Therefore, the present study aimed to identify key variables explaining players’ physical workload across game quarters and playing positions through principal component analysis (PCA). Ninety-four elite U18 male basketball players were registered during the EuroLeague Basketball ANGT Finals using WIMU PRO™ multi-sensor wearable devices that integrate local positioning systems (LPS) and microelectromechanical systems (MEMS). From over 250 recorded variables, 31 were selected and analyzed by PCA for dimensionality reduction, analyzing the effects of game quarter and playing position. Five to eight principal components explained 61–73% of the variance per game quarter, while between four and seven components explained 64–69% per playing position. High-intensity variables showed strong component loadings in early quarters, with explosive distance (loading = 0.898 in total game, 0.645 in Q1) progressively declining to complete absence in Q4. Position-based analysis revealed specific workload profiles: guards required seven components to explain 69.25% of the variance, with complex movement patterns, forwards showed the highest explosive distance loading (0.810) among all positions, and centers demonstrated concentrated power demands, with PC1 explaining 34.12% of the variance, dominated by acceleration distance (loading = 0.887). These findings support situational and individualized training approaches, allowing coaches to design individual training programs, adjust rotation strategies during games, and replicate demanding scenarios in training while minimizing injury risk. Full article
(This article belongs to the Special Issue Sports Sensors for Athlete Motion Tracking and Physiological Monitoring: Second Edition)
14 pages, 2096 KB  
Article
Attention-Enhanced Semantic Segmentation for Substation Inspection Robot Navigation
by Changqing Cai, Yongkang Yang, Kaiqiao Tian, Yuxin Yan, Kazuyuki Kobayashi and Ka C. Cheok
Sensors 2025, 25(19), 6252; https://doi.org/10.3390/s25196252 - 9 Oct 2025
Viewed by 349
Abstract
Outdoor substations present complex conditions such as uneven terrain, strong illumination variations, and frequent occlusions, which pose significant challenges for autonomous robotic inspection. To address these issues, we develop an embedded inspection robot that integrates attention-enhanced semantic segmentation with GPS-assisted navigation for reliable [...] Read more.
Outdoor substations present complex conditions such as uneven terrain, strong illumination variations, and frequent occlusions, which pose significant challenges for autonomous robotic inspection. To address these issues, we develop an embedded inspection robot that integrates attention-enhanced semantic segmentation with GPS-assisted navigation for reliable operation. A lightweight DeepLabV3+ model is improved with ECA-SimAM and CBAM attention modules and further extended with a GPS-guided attention component that incorporates coarse location priors to refine feature focus and improve boundary recognition under challenging lighting and occlusion. The segmentation outputs are used to generate real-time road masks and navigation lines via center-of-mass and least-squares fitting, while RTK-GPS provides global positioning and triggers waypoint-based behaviors such as turning and stopping. Experimental results show that the proposed method achieves 85.26% mean IoU and 89.45% mean pixel accuracy, outperforming U-Net, PSPNet, HRNet, and standard DeepLabV3+. Deployed on an embedded platform and validated in real substations, the system demonstrates both robustness and scalability for practical infrastructure inspection tasks. Full article
(This article belongs to the Section Sensors and Robotics)
►▼ Show Figures

Figure 1

16 pages, 3235 KB  
Article
Delay-Compensated Lane-Coordinate Vehicle State Estimation Using Low-Cost Sensors
by Minsu Kim, Weonmo Kang and Changsun Ahn
Sensors 2025, 25(19), 6251; https://doi.org/10.3390/s25196251 - 9 Oct 2025
Viewed by 383
Abstract
Accurate vehicle state estimation in a lane coordinate system is essential for safe and reliable operation of Advanced Driver Assistance Systems (ADASs) and autonomous driving. However, achieving robust lane-based state estimation using only low-cost sensors, such as a camera, an IMU, and a [...] Read more.
Accurate vehicle state estimation in a lane coordinate system is essential for safe and reliable operation of Advanced Driver Assistance Systems (ADASs) and autonomous driving. However, achieving robust lane-based state estimation using only low-cost sensors, such as a camera, an IMU, and a steering angle sensor, remains challenging due to the complexity of vehicle dynamics and the inherent signal delays in vision systems. This paper presents a lane-coordinate-based vehicle state estimator that addresses these challenges by combining a vehicle dynamics-based bicycle model with an Extended Kalman Filter (EKF) and a signal delay compensation algorithm. The estimator performs real-time estimation of lateral position, lateral velocity, and heading angle, including the unmeasurable lateral velocity about the lane, by predicting the vehicle’s state evolution during camera processing delays. A computationally efficient camera processing pipeline, incorporating lane segmentation via a pre-trained network and lane-based state extraction, is implemented to support practical applications. Validation using real vehicle driving data on straight and curved roads demonstrates that the proposed estimator provides continuous, high-accuracy, and delay-compensated lane-coordinate-based vehicle states. Compared to conventional camera-only methods and estimators without delay compensation, the proposed approach significantly reduces estimation errors and phase lag, enabling the reliable and real-time acquisition of vehicle-state information critical for ADAS and autonomous driving applications. Full article
(This article belongs to the Special Issue Applications of Machine Learning in Automotive Engineering)
►▼ Show Figures

Figure 1

16 pages, 1182 KB  
Article
Anomaly Detection and Objective Security Evaluation Using Autoencoder, Isolation Forest, and Multi-Criteria Decision Methods
by Hongbin Zhang and Haibin Zhang
Sensors 2025, 25(19), 6250; https://doi.org/10.3390/s25196250 - 9 Oct 2025
Viewed by 332
Abstract
With the rapid development of cybersecurity technologies, cybersecurity testing has played an increasingly critical role in scientific research, new technology validation, system performance evaluation, and talent development. A central challenge in this domain lies in efficiently and rapidly constructing testing environments while ensuring [...] Read more.
With the rapid development of cybersecurity technologies, cybersecurity testing has played an increasingly critical role in scientific research, new technology validation, system performance evaluation, and talent development. A central challenge in this domain lies in efficiently and rapidly constructing testing environments while ensuring the reliability and reproducibility of test results. To address this issue, this paper proposes an integrated evaluation method specifically designed for cybersecurity testing, combining anomaly detection and predictive analysis techniques. The method first employs an autoencoder (AE) to perform dimensionality reduction on the raw data collected from a testbed environment, followed by anomaly detection using the Isolation Forest (IF) algorithm. To assess the impact of cyberattacks on the stability of the testbed system, the steady-state data of the environment was treated as the ideal reference. The degree of disruption was then quantified by calculating the Euclidean distance between the dimensionally reduced experimental data and the reference state. Finally, a specific case study was conducted to validate the feasibility and effectiveness of the proposed method, and a percentage-based scoring mechanism was introduced to quantitatively evaluate the security level of the system. Full article
(This article belongs to the Section Internet of Things)
►▼ Show Figures

Figure 1

18 pages, 568 KB  
Article
Design of Partial Mueller-Matrix Polarimeters for Application-Specific Sensors
by Brian G. Hoover and Martha Y. Takane
Sensors 2025, 25(19), 6249; https://doi.org/10.3390/s25196249 - 9 Oct 2025
Viewed by 260
Abstract
At a particular frequency, most materials and objects of interest exhibit a polarization signature, or Mueller matrix, of limited dimensionality, with many matrix elements either negligibly small or redundant due to symmetry. Robust design of a polarization sensor for a particular material or [...] Read more.
At a particular frequency, most materials and objects of interest exhibit a polarization signature, or Mueller matrix, of limited dimensionality, with many matrix elements either negligibly small or redundant due to symmetry. Robust design of a polarization sensor for a particular material or object of interest, or for an application with a limited set of materials or objects, will adapt to the signature subspace, as well as the available modulators, in order to avoid unnecessary measurements and hardware and their associated budgets, errors, and artifacts. At the same time, measured polarization features should be expressed in the Stokes–Mueller basis to allow use of known phenomenology for data interpretation and processing as well as instrument calibration and troubleshooting. This approach to partial Mueller-matrix polarimeter (pMMP) design begins by defining a vector space of reduced Mueller matrices and an instrument vector representing the polarization modulators and other components of the sensor. The reduced-Mueller vector space is proven to be identical to R15 and to provide a completely linear description constrained to the Mueller cone. The reduced irradiance, the inner product of the reduced instrument and target vectors, is then applied to construct classifiers and tune modulator parameters, for instance to maximize representation of a specific target in a fixed number of measured channels. This design method eliminates the use of pseudo-inverses and reveals the optimal channel compositions to capture a particular signature feature, or a limited set of features, under given hardware constraints. Examples are given for common optical division-of-amplitude (DoA) 2-channel passive and serial/DoT-DoA 4-channel active polarimeters with rotating crystal modulators for classification of targets with diattenuation and depolarization characteristics. Full article
(This article belongs to the Section Optical Sensors)
►▼ Show Figures

Figure 1

22 pages, 1443 KB  
Article
AI and IoT-Driven Monitoring and Visualisation for Optimising MSP Operations in Multi-Tenant Networks: A Modular Approach Using Sensor Data Integration
by Adeel Rafiq, Muhammad Zeeshan Shakir, David Gray, Julie Inglis and Fraser Ferguson
Sensors 2025, 25(19), 6248; https://doi.org/10.3390/s25196248 - 9 Oct 2025
Viewed by 814
Abstract
Despite the widespread adoption of network monitoring tools, Managed Service Providers (MSPs), specifically small- and medium-sized enterprises (SMEs), continue to face persistent challenges in achieving predictive, multi-tenant-aware visibility across distributed client networks. Existing monitoring systems lack integrated predictive analytics and edge intelligence. To [...] Read more.
Despite the widespread adoption of network monitoring tools, Managed Service Providers (MSPs), specifically small- and medium-sized enterprises (SMEs), continue to face persistent challenges in achieving predictive, multi-tenant-aware visibility across distributed client networks. Existing monitoring systems lack integrated predictive analytics and edge intelligence. To address this, we propose an AI- and IoT-driven monitoring and visualisation framework that integrates edge IoT nodes (Raspberry Pi Prometheus modules) with machine learning models to enable predictive anomaly detection, proactive alerting, and reduced downtime. This system leverages Prometheus, Grafana, and Mimir for data collection, visualisation, and long-term storage, while incorporating Simple Linear Regression (SLR), K-Means clustering, and Long Short-Term Memory (LSTM) models for anomaly prediction and fault classification. These AI modules are containerised and deployed at the edge or centrally, depending on tenant topology, with predicted risk metrics seamlessly integrated back into Prometheus. A one-month deployment across five MSP clients (500 nodes) demonstrated significant operational benefits, including a 95% reduction in downtime and a 90% reduction in incident resolution time relative to historical baselines. The system ensures secure tenant isolation via VPN tunnels and token-based authentication, while providing GDPR-compliant data handling. Unlike prior monitoring platforms, this work introduces a fully edge-embedded AI inference pipeline, validated through live deployment and operational feedback. Full article
(This article belongs to the Special Issue Scalable Blockchain and AI-Based Embedded IoT Systems for Smart Spaces (3rd Edition))
►▼ Show Figures

Figure 1

23 pages, 6989 KB  
Article
Images Versus Videos in Contrast-Enhanced Ultrasound for Computer-Aided Diagnosis
by Marina Adriana Mercioni, Cătălin Daniel Căleanu and Mihai-Eronim-Octavian Ursan
Sensors 2025, 25(19), 6247; https://doi.org/10.3390/s25196247 - 9 Oct 2025
Viewed by 349
Abstract
The background of the article refers to the diagnosis of focal liver lesions (FLLs) through contrast-enhanced ultrasound (CEUS) based on the integration of spatial and temporal information. Traditional computer-aided diagnosis (CAD) systems predominantly rely on static images, which limits the characterization of lesion [...] Read more.
The background of the article refers to the diagnosis of focal liver lesions (FLLs) through contrast-enhanced ultrasound (CEUS) based on the integration of spatial and temporal information. Traditional computer-aided diagnosis (CAD) systems predominantly rely on static images, which limits the characterization of lesion dynamics. This study aims to assess the effectiveness of Transformer-based architectures in enhancing CAD performance within the realm of liver pathology. The methodology involved a systematic comparison of deep learning models for the analysis of CEUS images and videos. For image-based classification, a Hybrid Transformer Neural Network (HTNN) was employed. It combines Vision Transformer (ViT) modules with lightweight convolutional features. For video-based tasks, we evaluated a custom spatio-temporal Convolutional Neural Network (CNN), a CNN with Long Short-Term Memory (LSTM), and a Video Vision Transformer (ViViT). The experimental results show that the HTNN achieved an outstanding accuracy of 97.77% in classifying various types of FLLs, although it required manual selection of the region of interest (ROI). The video-based models produced accuracies of 83%, 88%, and 88%, respectively, without the need for ROI selection. In conclusion, the findings indicate that Transformer-based models exhibit high accuracy in CEUS-based liver diagnosis. This study highlights the potential of attention mechanisms to identify subtle inter-class differences, thereby reducing the reliance on manual intervention. Full article
(This article belongs to the Special Issue Selected Papers from International Symposium on Electronics and Telecommunications ISETC 2024)
►▼ Show Figures

Figure 1

29 pages, 7823 KB  
Article
Real-Time Detection Sensor for Unmanned Aerial Vehicle Using an Improved YOLOv8s Algorithm
by Fuhao Lu, Chao Zeng, Hangkun Shi, Yanghui Xu and Song Fu
Sensors 2025, 25(19), 6246; https://doi.org/10.3390/s25196246 - 9 Oct 2025
Viewed by 654
Abstract
This study advances the unmanned aerial vehicle (UAV) localization technology within the framework of a low-altitude economy, with particular emphasis on the accurate and real-time identification and tracking of unauthorized (“black-flying”) drones. Conventional YOLOv8s-based target detection algorithms often suffer from missed detections due [...] Read more.
This study advances the unmanned aerial vehicle (UAV) localization technology within the framework of a low-altitude economy, with particular emphasis on the accurate and real-time identification and tracking of unauthorized (“black-flying”) drones. Conventional YOLOv8s-based target detection algorithms often suffer from missed detections due to their reliance on single-frame features. To address this limitation, this paper proposes an improved detection algorithm that integrates a long-short-term memory (LSTM) network into the YOLOv8s framework. By incorporating time-series modeling, the LSTM module enables the retention of historical features and dynamic prediction of UAV trajectories. The loss function combines bounding box regression loss with binary cross-entropy and is optimized using the Adam algorithm to enhance training convergence. The training data distribution is validated through Monte Carlo random sampling, which improves the model’s generalization to complex scenes. Simulation results demonstrate that the proposed method significantly enhances UAV detection performance. In addition, when deployed on the RK3588-based embedded system, the method achieves a low false negative rate and exhibits robust detection capabilities, indicating strong potential for practical applications in airspace management and counter-UAV operations. Full article
(This article belongs to the Special Issue Smart Sensing and Control for Autonomous Intelligent Unmanned Systems)
►▼ Show Figures

Figure 1

20 pages, 4284 KB  
Article
An Adaptive Deep Ensemble Learning for Specific Emitter Identification
by Peng Shang, Lishu Guo, Decai Zou, Xue Wang, Pengfei Liu and Shuaihe Gao
Sensors 2025, 25(19), 6245; https://doi.org/10.3390/s25196245 - 9 Oct 2025
Viewed by 334
Abstract
Specific emitter identification (SEI), which classifies radio transmitters by extracting hardware-intrinsic radio frequency fingerprints (RFFs), faces critical challenges in noise robustness, generalization under limited training data and class imbalance. To address these limitations, we propose adaptive deep ensemble learning (ADEL)—a framework that integrates [...] Read more.
Specific emitter identification (SEI), which classifies radio transmitters by extracting hardware-intrinsic radio frequency fingerprints (RFFs), faces critical challenges in noise robustness, generalization under limited training data and class imbalance. To address these limitations, we propose adaptive deep ensemble learning (ADEL)—a framework that integrates heterogeneous neural networks including convolutional neural networks (CNN), multilayer perception (MLP) and transformer for hierarchical feature extraction. Crucially, ADEL also adopts adaptive weighted predictions of the three base classifiers based on reconstruction errors and hybrid losses for robust classification. The methodology employs (1) three heterogeneous neural networks for robust feature extraction; (2) the hybrid losses refine feature space structure and preserve feature integrity for better feature generalization; and (3) collaborative decision-making via adaptive weighted reconstruction errors of the base learners for precise inference. Extensive experiments are performed to validate the effectiveness of ADEL. The results indicate that the proposed method significantly outperforms other competing methods. ADEL establishes a new SEI paradigm through robust feature extraction and adaptive decision integrity, enabling potential deployment in space target identification and situational awareness under limited training samples and imbalanced classes conditions. Full article
(This article belongs to the Section Electronic Sensors)
►▼ Show Figures

Figure 1

25 pages, 6336 KB  
Article
U-AttentionFlow: A Multi-Scale Invertible Attention Network for OLTC Anomaly Detection Using Acoustic Signals
by Donghyun Kim, Hoseong Hwang and Hochul Kim
Sensors 2025, 25(19), 6244; https://doi.org/10.3390/s25196244 - 9 Oct 2025
Viewed by 304
Abstract
The On-Load Tap Changer (OLTC) in power transformers is a critical component responsible for regulating the output voltage, and the early detection of OLTC faults is essential for maintaining power grid stability. In this paper, we propose a one-class deep learning anomaly detection [...] Read more.
The On-Load Tap Changer (OLTC) in power transformers is a critical component responsible for regulating the output voltage, and the early detection of OLTC faults is essential for maintaining power grid stability. In this paper, we propose a one-class deep learning anomaly detection model named “U-AttentionFlow” based on acoustic signals from the OLTC operation. The proposed model is trained exclusively on normal operating data to accurately model normal patterns and identify anomalies when new signals deviate from the learned patterns. To enhance the ability of the model to focus on significant features, we integrate the squeeze-and-excitation (SE) block and Convolutional Block Attention Module (CBAM) into the network architecture. Furthermore, static positional encoding and multihead self-attention (MHSA) are employed to effectively learn the temporal characteristics of time-series acoustic signals. We also adopted a U-Flow-style invertible multiscale coupling structure, which integrates features across multiple scales while ensuring the invertibility of the model. Experimental validation was conducted using acoustic data collected under realistic voltage and load conditions from actual ECOTAP VPD OLTC equipment, resulting in an anomaly detection accuracy of 99.15%. These results demonstrate the outstanding performance and practical applicability of the U-AttentionFlow model for OLTC anomaly detection. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
►▼ Show Figures

Figure 1

17 pages, 2986 KB  
Article
Physics-Aware Ensemble Learning for Superior Crop Recommendation in Smart Agriculture
by Hemalatha Gunasekaran, Krishnamoorthi Ramalakshmi, Saswati Debnath and Deepa Kanmani Swaminathan
Sensors 2025, 25(19), 6243; https://doi.org/10.3390/s25196243 - 9 Oct 2025
Viewed by 338
Abstract
Agriculture remains the backbone of many countries; it plays a pivotal role in shaping a country’s overall economy. Accurate prediction in agriculture practices, particularly crop recommendations, can greatly enhance productivity and resource management. IoT and AI technologies have great potential for enhancing precision [...] Read more.
Agriculture remains the backbone of many countries; it plays a pivotal role in shaping a country’s overall economy. Accurate prediction in agriculture practices, particularly crop recommendations, can greatly enhance productivity and resource management. IoT and AI technologies have great potential for enhancing precision farming; traditional machine learning (ML) and ensemble learning (EL) models rely primarily on the training data for predictions. When the training data is noisy or limited, these models can result in inaccurate or unrealistic predictions. These limitations are addressed by incorporating physical laws into the ML framework, thereby ensuring that the predictions remain physically plausible. In this study, we conducted a detailed analysis of ML and EL models, both with and without optimization, and compared their performance against a physics-informed ML model. In the proposed stacking physics-informed ML model, the optimal temperature and the pH for each crop (physics law) are provided as input during the training process in addition to the training data. The physics-informed model was trained to simultaneously satisfy two objectives: (1) fitting the data, and (2) adhering to the physics law. This was achieved by including a penalty term within its total loss function, forcing the model to make predictions that are both accurate and physically feasible. Our findings indicate that the proposed novel stacking physics-informed model achieved a highest accuracy of 99.50% when compared to ML and EL models with optimization. Full article
(This article belongs to the Special Issue Selected Papers from the 11th International Electronic Conference on Sensors and Applications)
►▼ Show Figures

Figure 1

34 pages, 3834 KB  
Article
PINN-DT: Optimizing Energy Consumption in Smart Building Using Hybrid Physics-Informed Neural Networks and Digital Twin Framework with Blockchain Security
by Hajar Kazemi Naeini, Roya Shomali, Abolhassan Pishahang, Hamidreza Hasanzadeh, Saeed Asadi and Ahmad Gholizadeh Lonbar
Sensors 2025, 25(19), 6242; https://doi.org/10.3390/s25196242 - 9 Oct 2025
Viewed by 528
Abstract
The advancement of smart grid technologies necessitates the integration of cutting-edge computational methods to enhance predictive energy optimization. This study proposes a multi-faceted approach by incorporating (1) Deep Reinforcement Learning (DRL) agents trained using data from digital twins (DTs) to optimize energy consumption [...] Read more.
The advancement of smart grid technologies necessitates the integration of cutting-edge computational methods to enhance predictive energy optimization. This study proposes a multi-faceted approach by incorporating (1) Deep Reinforcement Learning (DRL) agents trained using data from digital twins (DTs) to optimize energy consumption in real time, (2) Physics-Informed Neural Networks (PINNs) to seamlessly embed physical laws within the optimization process, ensuring model accuracy and interpretability, and (3) blockchain (BC) technology to facilitate secure and transparent communication across the smart grid infrastructure. The model was trained and validated using comprehensive datasets, including smart meter energy consumption data, renewable energy outputs, dynamic pricing, and user preferences collected from IoT devices. The proposed framework achieved superior predictive performance with a Mean Absolute Error (MAE) of 0.237 kWh, Root Mean Square Error (RMSE) of 0.298 kWh, and an R-squared (R2) value of 0.978, indicating a 97.8% explanation of data variance. Classification metrics further demonstrated the model’s robustness, achieving 97.7% accuracy, 97.8% precision, 97.6% recall, and an F1 Score of 97.7%. Comparative analysis with traditional models like Linear Regression, Random Forest, SVM, LSTM, and XGBoost revealed the superior accuracy and real-time adaptability of the proposed method. In addition to enhancing energy efficiency, the model reduced energy costs by 35%, maintained a 96% user comfort index, and increased renewable energy utilization to 40%. This study demonstrates the transformative potential of integrating PINNs, DT, and blockchain technologies to optimize energy consumption in smart grids, paving the way for sustainable, secure, and efficient energy management systems. Full article
(This article belongs to the Special Issue IoT and Big Data Analytics for Smart Cities)
►▼ Show Figures

Figure 1

14 pages, 1927 KB  
Article
Effects of Transcranial Electrical Stimulation on Intermuscular Coherence in WuShu Sprint and KAN-Based EMG–Performance Function Fitting
by Lan Li, Haojie Li and Qianqian Fan
Sensors 2025, 25(19), 6241; https://doi.org/10.3390/s25196241 - 9 Oct 2025
Viewed by 472
Abstract
Objective: The aim of this study was to examine how transcranial electrical stimulation (tES) modulates intermuscular coherence (IMC) in sprinters and develop an interpretable neural network model for performance prediction. Methods: Thirty elite sprinters completed a randomized crossover trial involving three tES conditions: [...] Read more.
Objective: The aim of this study was to examine how transcranial electrical stimulation (tES) modulates intermuscular coherence (IMC) in sprinters and develop an interpretable neural network model for performance prediction. Methods: Thirty elite sprinters completed a randomized crossover trial involving three tES conditions: motor cortex stimulation (C1/C2), prefrontal stimulation (F3), and sham. Sprint performance metrics (0–100 m phase analysis) and lower-limb sEMG signals were collected. A Kolmogorov–Arnold Network (KAN) was trained to decode neuromuscular coordination–sprint performance relationships using IMC and time–frequency sEMG features. Results: Motor cortex tDCS increased 30–60 m sprint velocity by 2.2% versus sham (p < 0.05, η2 = 0.25). γ-band IMC in key muscle pairs (rectus femoris–biceps femoris, tibialis anterior–gastrocnemius) significantly heightened under motor cortex stimulation (F > 4.2, p < 0.03). The KAN model achieved high predictive accuracy (R2 = 0.83) through cross-validation, with derived symbolic equations mapping neuromuscular features to performance. Conclusions: Targeted tDCS enhances neuromuscular coordination and sprint velocity, while KAN provides a transparent framework for performance modeling in elite sports. Full article
(This article belongs to the Special Issue Biosignal Sensing Analysis (EEG, EMG, ECG, PPG) (2nd Edition))
►▼ Show Figures

Figure 1

28 pages, 5254 KB  
Article
IoT-Enabled Fog-Based Secure Aggregation in Smart Grids Supporting Data Analytics
by Hayat Mohammad Khan, Farhana Jabeen, Abid Khan, Muhammad Waqar and Ajung Kim
Sensors 2025, 25(19), 6240; https://doi.org/10.3390/s25196240 - 8 Oct 2025
Viewed by 635
Abstract
The Internet of Things (IoT) has transformed multiple industries, providing significant potential for automation, efficiency, and enhanced decision-making. The incorporation of IoT and data analytics in smart grid represents a groundbreaking opportunity for the energy sector, delivering substantial advantages in efficiency, sustainability, and [...] Read more.
The Internet of Things (IoT) has transformed multiple industries, providing significant potential for automation, efficiency, and enhanced decision-making. The incorporation of IoT and data analytics in smart grid represents a groundbreaking opportunity for the energy sector, delivering substantial advantages in efficiency, sustainability, and customer empowerment. This integration enables smart grids to autonomously monitor energy flows and adjust to fluctuations in energy demand and supply in a flexible and real-time fashion. Statistical analytics, as a fundamental component of data analytics, provides the necessary tools and techniques to uncover patterns, trends, and insights within datasets. Nevertheless, it is crucial to address privacy and security issues to fully maximize the potential of data analytics in smart grids. This paper makes several significant contributions to the literature on secure, privacy-aware aggregation schemes in smart grids. First, we introduce a Fog-enabled Secure Data Analytics Operations (FESDAO) scheme which offers a distributed architecture incorporating robust security features such as secure aggregation, authentication, fault tolerance and resilience against insider threats. The scheme achieves privacy during data aggregation through a modified Boneh-Goh-Nissim cryptographic scheme along with other mechanisms. Second, FESDAO also supports statistical analytics on metering data at the cloud control center and fog node levels. FESDAO ensures reliable aggregation and accurate data analytical results, even in scenarios where smart meters fail to report data, thereby preserving both analytical operation computation accuracy and latency. We further provide comprehensive security analyses to demonstrate that the proposed approach effectively supports data privacy, source authentication, fault tolerance, and resilience against false data injection and replay attacks. Lastly, we offer thorough performance evaluations to illustrate the efficiency of the suggested scheme in comparison to current state-of-the-art schemes, considering encryption, computation, aggregation, decryption, and communication costs. Moreover, a detailed security analysis has been conducted to verify the scheme’s resistance against insider collusion attacks, replay attack, and false data injection (FDI) attack. Full article
(This article belongs to the Section Internet of Things)
►▼ Show Figures

Figure 1

19 pages, 5137 KB  
Article
An Accessible AI-Assisted Rehabilitation System for Guided Upper Limb Therapy
by Kevin Hou, Md Mahafuzur Rahaman Khan and Mohammad H. Rahman
Sensors 2025, 25(19), 6239; https://doi.org/10.3390/s25196239 - 8 Oct 2025
Viewed by 576
Abstract
Conventional upper limb rehabilitation methods often encounter significant obstacles, including high costs, limited accessibility, and reduced patient adherence. Emerging technological solutions, such as telerehabilitation, virtual reality (VR), and wearable sensor-based systems, address some of these challenges but still face issues concerning supervision quality, [...] Read more.
Conventional upper limb rehabilitation methods often encounter significant obstacles, including high costs, limited accessibility, and reduced patient adherence. Emerging technological solutions, such as telerehabilitation, virtual reality (VR), and wearable sensor-based systems, address some of these challenges but still face issues concerning supervision quality, affordability, and usability. To overcome these limitations, this study presents an innovative and cost-effective rehabilitation system based on advanced computer vision techniques and artificial intelligence (AI). Developed using Python (3.11.5), the proposed system utilizes a standard webcam in conjunction with robust pose estimation algorithms to provide real-time analysis of patient movements during guided upper limb exercises. Instructional exercise videos featuring an NAO robot facilitate patient engagement and consistency in practice. The system generates instant quantitative feedback on movement precision, repetition accuracy, and exercise phase completion. The core advantages of the proposed approach include minimal equipment requirements, affordability, ease of setup, and enhanced interactive guidance compared to traditional telerehabilitation methods. By reducing the complexity and expense associated with many VR and wearable-sensor solutions, while acknowledging that some lower-cost and haptic-enabled VR options exist, this single-webcam approach aims to broaden access to guided home rehabilitation without specialized hardware. Full article
(This article belongs to the Section Biomedical Sensors)
►▼ Show Figures

Figure 1

22 pages, 667 KB  
Review
Analysis of Physiological Parameters and Driver Posture for Prevention of Road Accidents: A Review
by Alparslan Babur, Ali Moukadem, Alain Dieterlen and Katrin Skerl
Sensors 2025, 25(19), 6238; https://doi.org/10.3390/s25196238 - 8 Oct 2025
Viewed by 494
Abstract
This review provides an overview of existing accident prevention methods by monitoring the persons’ physiological state, observing movements, and physiological parameters. Firstly, different physiological parameters monitoring systems are introduced. Secondly, various systems dealing with position recognition on pressure sensing mats are presented. We [...] Read more.
This review provides an overview of existing accident prevention methods by monitoring the persons’ physiological state, observing movements, and physiological parameters. Firstly, different physiological parameters monitoring systems are introduced. Secondly, various systems dealing with position recognition on pressure sensing mats are presented. We conduct an in-depth literature search and quantitative analysis of papers published in this area and focus independently of the application (drivers, office and wheelchair users, etc.). Quantitative information about the number of subjects, investigated scenarios, sensor types, machine learning usage, and laboratory vs. real-world works is extracted. In posture recognition, most works recognize at least forward, backward, left and right movements on a seat. The remaining works use the pressure sensing mat for bedridden people. In physiological parameters measurement, most works detect the heart rate and often also add respiration rate recognition. Machine learning algorithms are used in most cases and are taking on an ever-greater importance for classification and regression problems. Although all solutions use different techniques, returning satisfactory results, none of them try to detect small movements, which can pose challenges in determining the optimal sensor topology and sampling frequency required to detect fine movements. For physiological measurements, there are lots of challenges to overcome in noisy environments, notably the detection of heart rate, blood pressure, and respiratory rate at very low signal-to-noise levels. Full article
(This article belongs to the Section Biomedical Sensors)
►▼ Show Figures

Figure 1

19 pages, 4825 KB  
Article
Research on Instance Segmentation Algorithm for Caged Chickens in Infrared Images Based on Improved Mask R-CNN
by Youqing Chen, Hang Liu, Lun Wang, Chen Chen, Siyu Li, Binyuan Zhong, Jihui Qiao, Rong Ye and Tong Li
Sensors 2025, 25(19), 6237; https://doi.org/10.3390/s25196237 - 8 Oct 2025
Viewed by 303
Abstract
Infrared images of caged chickens can provide valuable insights into their health status. Accurately detecting and segmenting individual chickens in these images is essential for effective health monitoring in large-scale chicken farming. However, the presence of obstacles such as cages, feeders, and drinkers [...] Read more.
Infrared images of caged chickens can provide valuable insights into their health status. Accurately detecting and segmenting individual chickens in these images is essential for effective health monitoring in large-scale chicken farming. However, the presence of obstacles such as cages, feeders, and drinkers can obscure the chickens, while clustering and overlapping among them may further hinder segmentation accuracy. This study proposes a Mask R-CNN-based instance segmentation algorithm specifically designed for caged chickens in infrared images. The backbone network is enhanced by incorporating the CBAM within this algorithm, which is further combined with the AC-FPN architecture to improve the model’s ability to extract features. Experimental results demonstrate that the model achieves average AP and AR10 values of 78.66% and 85.80%, respectively, in object detection, as per the COCO performance metrics. In segmentation tasks, the model attains average AP and AR10 values of 73.94% and 80.42%, respectively, reflecting improvements of 32.91% and 17.78% over the original model. Notably, among all categories of chicken flocks, the ‘Chicken-many’ category achieved an impressive average segmentation accuracy of 98.51%, and the other categories also surpassed 93%. The proposed instance segmentation method for caged chickens in infrared images effectively facilitates the recognition and segmentation of chickens within the challenging imaging conditions typical of high-density caged environments, thereby contributing to enhanced production efficiency and the advancement of intelligent breeding management. Full article
(This article belongs to the Special Issue Multi-Modal Image Processing Methods, Systems, and Applications: 2nd Edition)
►▼ Show Figures

Figure 1

22 pages, 4661 KB  
Article
Research on Eye-Tracking Control Methods Based on an Improved YOLOv11 Model
by Xiangyang Sun, Jiahua Wu, Wenjun Zhang, Xianwei Chen and Haixia Mei
Sensors 2025, 25(19), 6236; https://doi.org/10.3390/s25196236 - 8 Oct 2025
Viewed by 503
Abstract
Eye-tracking technology has gained traction in the field of medical rehabilitation due to its non-invasive and intuitive nature. However, current eye-tracking methods based on object detection technology suffer from insufficient accuracy in detecting the eye socket and iris, as well as inaccuracies in [...] Read more.
Eye-tracking technology has gained traction in the field of medical rehabilitation due to its non-invasive and intuitive nature. However, current eye-tracking methods based on object detection technology suffer from insufficient accuracy in detecting the eye socket and iris, as well as inaccuracies in determining eye movement direction. To address this, this study improved the YOLOv11 model using the EFFM and ORC modules, resulting in a 1.7% and 9.9% increase in recognition accuracy for the eye socket and iris, respectively, and a 5.5% and 44% increase in recall rate, respectively. A method combining frame voting mechanisms with eye movement area discrimination was proposed for eye movement direction discrimination, achieving average accuracy rates of 95.3%, 92.8%, and 94.8% for iris fixation, left, and right directions, respectively. The discrimination results of multiple eye movement images were mapped to a binary value, and eye movement encoding was used to obtain control commands that align with the robotic arm. The average matching degree of eye movement encoding ranged from 93.4% to 96.8%. An experimental platform was established, and the average completion rates for three object-grabbing tasks controlled by eye movements were 98%, 78%, and 96%, respectively. Full article
(This article belongs to the Section Sensing and Imaging)
►▼ Show Figures

Figure 1

27 pages, 2156 KB  
Article
MEDIotWALL: Securing Smart Healthcare Environments Through IoT Firewalls
by Irene Gosálvez-White, Nerea Rodríguez-Martín, Nicolás Barajas-García, Carmen Mena-Gallardo and Pedro García-Teodoro
Sensors 2025, 25(19), 6235; https://doi.org/10.3390/s25196235 - 8 Oct 2025
Viewed by 391
Abstract
IoT technology is transforming the healthcare industry through what is known as the Internet of Medical Things (IoMT), enhancing patient care while simultaneously reducing costs. Nevertheless, it introduces critical security challenges, particularly the risk of jeopardizing patient safety. Existing IoMT security solutions, often [...] Read more.
IoT technology is transforming the healthcare industry through what is known as the Internet of Medical Things (IoMT), enhancing patient care while simultaneously reducing costs. Nevertheless, it introduces critical security challenges, particularly the risk of jeopardizing patient safety. Existing IoMT security solutions, often limited to proprietary platforms or generic IoT firewalls, frequently lack transparency, scalability, and awareness with clinical regulations. To address these gaps, we present MEDIotWALL, a customized two-tier security architecture tailored for healthcare environments. The system integrates distributed real-time traffic monitoring with AI-driven rule generation, delivering a non-intrusive, centralized, human-supervised, and regulation-aware security framework. Experimental results demonstrate the cost-efficiency and effectiveness of the approach, ensuring robust medical protection while preserving authentication, confidentiality, and integrity of the environment. Full article
(This article belongs to the Special Issue Network Security and IoT Security: 2nd Edition)
►▼ Show Figures

Figure 1

26 pages, 12809 KB  
Article
Coating Thickness Estimation Using a CNN-Enhanced Ultrasound Echo-Based Deconvolution
by Marina Perez-Diego, Upeksha Chathurani Thibbotuwa, Ainhoa Cortés and Andoni Irizar
Sensors 2025, 25(19), 6234; https://doi.org/10.3390/s25196234 - 8 Oct 2025
Viewed by 365
Abstract
Coating degradation monitoring is increasingly important in offshore industries, where protective layers ensure corrosion prevention and structural integrity. In this context, coating thickness estimation provides critical information. The ultrasound pulse-echo technique is widely used for non-destructive testing (NDT), but closely spaced acoustic interfaces [...] Read more.
Coating degradation monitoring is increasingly important in offshore industries, where protective layers ensure corrosion prevention and structural integrity. In this context, coating thickness estimation provides critical information. The ultrasound pulse-echo technique is widely used for non-destructive testing (NDT), but closely spaced acoustic interfaces often produce overlapping echoes, which complicates detection and accurate isolation of each layer’s thickness. In this study, analysis of the pulse-echo signal from a coated sample has shown that the front-coating reflection affects each main backwall echo differently; by comparing two consecutive backwall echoes, we can cancel the acquisition system’s impulse response and isolate the propagation path-related information between the echoes. This work introduces an ultrasound echo-based methodology for estimating coating thickness by first obtaining the impulse response of the test medium (reflectivity sequence) through a deconvolution model, developed using two consecutive backwall echoes. This is followed by an enhanced detection of coating layer thickness in the reflectivity function using a 1D convolutional neural network (1D-CNN) trained with synthetic signals obtained from finite-difference time-domain (FDTD) simulations with k-Wave MATLAB toolbox (v1.4.0). The proposed approach estimates the front-side coating thickness in steel samples coated on both sides, with coating layers ranging from 60μm to 740μm applied over 5 mm substrates and under varying coating and steel properties. The minimum detectable thickness corresponds to approximately λ/5 for an 8 MHz ultrasonic transducer. On synthetic signals, where the true coating thickness and speed of sound are known, the model achieves an accuracy of approximately 8μm. These findings highlight the strong potential of the model for reliably monitoring relative thickness changes across a wide range of coatings in real samples. Full article
(This article belongs to the Special Issue Nondestructive Sensing and Imaging in Ultrasound—Second Edition)
►▼ Show Figures

Figure 1

29 pages, 5154 KB  
Article
Spatial-Frequency-Scale Variational Autoencoder for Enhanced Flow Diagnostics of Schlieren Data
by Ronghua Yang, Hao Wu, Rongfei Yang, Xingshuang Wu, Yifan Song, Meiying Lü and Mingrui Wang
Sensors 2025, 25(19), 6233; https://doi.org/10.3390/s25196233 - 8 Oct 2025
Viewed by 403
Abstract
Schlieren imaging is a powerful optical sensing technique that captures flow-induced refractive index gradients, offering valuable visual data for analyzing complex fluid dynamics. However, the large volume and structural complexity of the data generated by this sensor pose significant challenges for extracting key [...] Read more.
Schlieren imaging is a powerful optical sensing technique that captures flow-induced refractive index gradients, offering valuable visual data for analyzing complex fluid dynamics. However, the large volume and structural complexity of the data generated by this sensor pose significant challenges for extracting key physical insights and performing efficient reconstruction and temporal prediction. In this study, we propose a Spatial-Frequency-Scale variational autoencoder (SFS-VAE), a deep learning framework designed for the unsupervised feature decomposition of Schlieren sensor data. To address the limitations of traditional β-variational autoencoder (β-VAE) in capturing complex flow regions, the Progressive Frequency-enhanced Spatial Multi-scale Module (PFSM) is designed, which enhances the structures of different frequency bands through Fourier transform and multi-scale convolution; the Feature-Spatial Enhancement Module (FSEM) employs a gradient-driven spatial attention mechanism to extract key regional features. Experiments on flat plate film-cooled jet schlieren data show that SFS-VAE can effectively preserve the information of the mainstream region and more accurately capture the high-gradient features of the jet region, reducing the Root Mean Square Error (RMSE) by approximately 16.9% and increasing the Peak Signal-to-Noise Ratio (PSNR) by approximately 1.6 dB. Furthermore, when integrated with a Transformer for temporal prediction, the model exhibits significantly improved stability and accuracy in forecasting flow field evolution. Overall, the model’s physical interpretability and generalization ability make it a powerful new tool for advanced flow diagnostics through the robust analysis of Schlieren sensor data. Full article
(This article belongs to the Section Optical Sensors)
►▼ Show Figures

Figure 1

28 pages, 8425 KB  
Article
Data Reduction Methodology for Dynamic Characteristic Extraction in Photoplethysmogram
by Nina Sviridova and Sora Okazaki
Sensors 2025, 25(19), 6232; https://doi.org/10.3390/s25196232 - 8 Oct 2025
Viewed by 385
Abstract
Photoplethysmogram (PPG) signals are increasingly utilized in wearable and mobile healthcare applications due to their non-invasive nature and ease of use in measuring physiological parameters, such as heart rate, blood pressure, and oxygen saturation. Recent advancements have highlighted green-light photoplethysmogram (gPPG) as offering [...] Read more.
Photoplethysmogram (PPG) signals are increasingly utilized in wearable and mobile healthcare applications due to their non-invasive nature and ease of use in measuring physiological parameters, such as heart rate, blood pressure, and oxygen saturation. Recent advancements have highlighted green-light photoplethysmogram (gPPG) as offering superior signal quality and accuracy compared to traditional red-light photoplethysmogram (rPPG). Given the deterministic chaotic nature of PPG signals’ dynamics, nonlinear time series analysis has emerged as a powerful method for extracting health-related information not captured by conventional linear techniques. However, optimal data conditions, including appropriate sampling frequency and minimum required time series length for effective nonlinear analysis, remain insufficiently investigated. This study examines the impact of downsampling frequencies and reducing time series lengths on the accuracy of estimating dynamical characteristics from gPPG and rPPG signals. Results demonstrate that a sampling frequency of 200 Hz provides an optimal balance, maintaining robust correlations in dynamical indices while reducing computational load. Furthermore, analysis of varying time series lengths revealed that the dynamical properties stabilize sufficiently at around 170 s, achieving an error of less than 5%. A comparative analysis between gPPG and rPPG revealed no significant statistical differences, confirming their similar effectiveness in estimating dynamical properties under controlled conditions. These results enhance the reliability and applicability of PPG-based health monitoring technologies. Full article
(This article belongs to the Section Biomedical Sensors)
►▼ Show Figures

Figure 1

17 pages, 8135 KB  
Article
High-Precision Alignment Method for Electro-Optic Modulators via Combined Twyman-Green and Conoscopic Interferometry
by Peng Zhang and Qi Lu
Sensors 2025, 25(19), 6231; https://doi.org/10.3390/s25196231 - 8 Oct 2025
Viewed by 348
Abstract
Electro-optic modulators (EOMs) are critical components in advanced optical systems, including quantum communications and high-resolution imaging, where precise alignment is essential for optimal performance. However, conventional methods struggle to simultaneously achieve accurate optical axis, transmission axis, and azimuthal alignment of EOM components. This [...] Read more.
Electro-optic modulators (EOMs) are critical components in advanced optical systems, including quantum communications and high-resolution imaging, where precise alignment is essential for optimal performance. However, conventional methods struggle to simultaneously achieve accurate optical axis, transmission axis, and azimuthal alignment of EOM components. This study proposes a high-precision alignment method that synergistically combines Twyman-Green and conoscopic interferometry. The Twyman-Green system first ensures precise optical axis alignment of the electro-optic crystal by minimizing tilt errors. Subsequently, under zero applied voltage, conoscopic interferometry is used to align the transmission axes of the polarizer and analyzer by verifying that the centroids of the interference features orient at 45° and 135°. Finally, under half-wave voltage, azimuthal alignment of the electro-optic crystal is achieved by ensuring the same centroid orientation. Experimental validation using a Z-cut LiNbO3 modulator demonstrates exceptional alignment accuracy, with root mean square errors below 0.2862 mrad for transmission axis alignment and 0.3229 mrad for azimuthal alignment. The proposed method offers a robust solution for high-precision EOM alignment in demanding applications. Full article
(This article belongs to the Section Optical Sensors)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-327
Previous Issue
Next Issue
Back to TopTop