Next Issue
Volume 25, August-1
Previous Issue
Volume 25, July-1
 
 
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 14
sensors-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Sensors, Volume 25, Issue 14 (July-2 2025) – 286 articles

Cover Story (view full-size image):  
  • 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.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
15 pages, 1943 KiB  
Article
Multimodal Latent Representation Learning for Video Moment Retrieval
by Jinkwon Hwang, Mingyu Jeon and Junyeong Kim
Sensors 2025, 25(14), 4528; https://doi.org/10.3390/s25144528 - 21 Jul 2025
Viewed by 372
Abstract
The rise of artificial intelligence (AI) has revolutionized the processing and analysis of video sensor data, driving advancements in areas such as surveillance, autonomous driving, and personalized content recommendations. However, leveraging video data presents unique challenges, particularly in the time-intensive feature extraction process [...] Read more.
The rise of artificial intelligence (AI) has revolutionized the processing and analysis of video sensor data, driving advancements in areas such as surveillance, autonomous driving, and personalized content recommendations. However, leveraging video data presents unique challenges, particularly in the time-intensive feature extraction process required for model training. This challenge is intensified in research environments lacking advanced hardware resources like GPUs. We propose a new method called the multimodal latent representation learning framework (MLRL) to address these limitations. MLRL enhances the performance of downstream tasks by conducting additional representation learning on pre-extracted features. By integrating and augmenting multimodal data, our method effectively predicts latent representations, leveraging pre-extracted features to reduce model training time and improve task performance. We validate the efficacy of MLRL on the video moment retrieval task using the QVHighlight dataset, benchmarking against the QD-DETR model. Our results demonstrate significant improvements, highlighting the potential of MLRL to streamline video data processing by leveraging pre-extracted features to bypass the time-consuming extraction process of raw sensor data and enhance model accuracy in various sensor-based applications. Full article
(This article belongs to the Special Issue Multimodal Perception Modeling Based on Advanced Computational Technologies)
►▼ Show Figures

Figure 1

21 pages, 2575 KiB  
Article
Gait Analysis Using Walking-Generated Acceleration Obtained from Two Sensors Attached to the Lower Legs
by Ayuko Saito, Natsuki Sai, Kazutoshi Kurotaki, Akira Komatsu, Shinichiro Morichi and Satoru Kizawa
Sensors 2025, 25(14), 4527; https://doi.org/10.3390/s25144527 - 21 Jul 2025
Viewed by 226
Abstract
Gait evaluation approaches using small, lightweight inertial sensors have recently been developed, offering improvements in terms of both portability and usability. However, accelerometer outputs include both the acceleration that is generated by human motion and gravitational acceleration, which changes along with the posture [...] Read more.
Gait evaluation approaches using small, lightweight inertial sensors have recently been developed, offering improvements in terms of both portability and usability. However, accelerometer outputs include both the acceleration that is generated by human motion and gravitational acceleration, which changes along with the posture of the body part to which the sensor is attached. This study presents a gait analysis method that uses the gravitational, centrifugal, tangential, and translational accelerations obtained from sensors attached to the lower legs. In this method, each sensor pose is sequentially estimated using sensor fusion to combine data obtained from a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer. The estimated sensor pose is then used to calculate the gravitational acceleration that is included in each axis of the sensor coordinate system. The centrifugal and tangential accelerations are determined from the gyroscope output. The translational acceleration is then obtained by subtracting the centrifugal, tangential, and gravitational accelerations from the accelerometer output. As a result, the acceleration components contained in the outputs of the accelerometers attached to the lower legs are provided. As only the acceleration components caused by walking motion are captured, thus reflecting their characteristics, it is expected that the developed method can be used for gait evaluation. Full article
(This article belongs to the Special Issue IMU and Innovative Sensors for Healthcare)
►▼ Show Figures

Figure 1

28 pages, 14374 KiB  
Article
Novel Airfoil-Shaped Radar-Absorbing Inlet Grilles on Aircraft Incorporating Metasurfaces: Multidisciplinary Design and Optimization Using EHVI–Bayesian Method
by Xufei Wang, Yongqiang Shi, Qingzhen Yang, Huimin Xiang and Saile Zhang
Sensors 2025, 25(14), 4525; https://doi.org/10.3390/s25144525 - 21 Jul 2025
Viewed by 294
Abstract
Aircraft, as electromagnetically complex targets, have radar cross-sections (RCSs) that are influenced by various factors, with the inlet duct being a critical component that often serves as a primary source of electromagnetic scattering, significantly impacting the scattering characteristics. In light of the conflict [...] Read more.
Aircraft, as electromagnetically complex targets, have radar cross-sections (RCSs) that are influenced by various factors, with the inlet duct being a critical component that often serves as a primary source of electromagnetic scattering, significantly impacting the scattering characteristics. In light of the conflict between aerodynamic performance and electromagnetic characteristics in the design of aircraft engine inlet grilles, this paper proposes a metasurface radar-absorbing inlet grille (RIG) solution based on a NACA symmetric airfoil. The RIG adopts a sandwich structure consisting of a polyethylene terephthalate (PET) dielectric substrate, a copper zigzag metal strip array, and an indium tin oxide (ITO) resistive film. By leveraging the principles of surface plasmon polaritons, electromagnetic wave absorption can be achieved. To enhance the design efficiency, a multi-objective Bayesian optimization framework driven by the expected hypervolume improvement (EHVI) is constructed. The results show that, compared with a conventional rectangular cross-section grille, an airfoil-shaped grille under the same constraints will reduce both aerodynamic losses and the absorption bandwidth. After 100-step EHVI–Bayesian optimization, the optimized balanced model attains a 57.79% reduction in aerodynamic loss relative to the rectangular-shaped grille, while its absorption bandwidth increases by 111.99%. The RCS exhibits a reduction of over 8.77 dBsm in the high-frequency band. These results confirm that the proposed optimization design process can effectively balance the conflict between aerodynamic performance and stealth performance for RIGs, reducing the signal strength of aircraft engine inlets. Full article
(This article belongs to the Section Electronic Sensors)
►▼ Show Figures

Figure 1

17 pages, 3561 KiB  
Article
A Novel Adaptive Flexible Capacitive Sensor for Accurate Intravenous Fluid Monitoring in Clinical Settings
by Yang He, Fangfang Yang, Pengxuan Wei, Zongmin Lv and Yinghong Zhang
Sensors 2025, 25(14), 4524; https://doi.org/10.3390/s25144524 - 21 Jul 2025
Viewed by 199
Abstract
Intravenous infusion is an important clinical medical intervention, and its safety is critical to patient recovery. To mitigate the elevated risk of complications (e.g., air embolism) arising from delayed response to infusion endpoints, this paper designs a flexible double pole capacitive (FPB) sensor, [...] Read more.
Intravenous infusion is an important clinical medical intervention, and its safety is critical to patient recovery. To mitigate the elevated risk of complications (e.g., air embolism) arising from delayed response to infusion endpoints, this paper designs a flexible double pole capacitive (FPB) sensor, which includes a main pole plate, an adaptive pole plate, and a back shielding electrode. The sensor establishes a mapping between residual liquid volume in the infusion bottle and its equivalent capacitance, enabling a non-contact adaptive monitoring system. The system enables precise quantification of residual liquid levels, suppressing baseline drift induced by environmental temperature/humidity fluctuations and container variations via an adaptive algorithm, without requiring manual calibration, and overcomes the limitations of traditional rigid sensors when adapting to curved containers. Experimental results showed that the system achieved an overall sensitivity of 753.5 fF/mm, main pole plate linearity of 1.99%, and adaptive pole plate linearity of 0.53% across different test subjects, linearity of 0.53% across different test subjects, with liquid level resolution accuracy reaching 1 mm. These results validate the system’s ultra-high resolution (1 mm) and robust adaptability. Full article
(This article belongs to the Section Electronic Sensors)
►▼ Show Figures

Figure 1

21 pages, 2817 KiB  
Article
A Handheld IoT Vis/NIR Spectroscopic System to Assess the Soluble Solids Content of Wine Grapes
by Xu Zhang, Ziquan Qin, Ruijie Zhao, Zhuojun Xie and Xuebing Bai
Sensors 2025, 25(14), 4523; https://doi.org/10.3390/s25144523 - 21 Jul 2025
Viewed by 259
Abstract
The quality of wine largely depends on the quality of wine grapes, which is determined by their chemical composition. Therefore, measuring parameters related to grape ripeness, such as soluble solids content (SSC), is crucial for harvesting high-quality grapes. Visible–Near-Infrared (Vis/NIR) spectroscopy enables effective, [...] Read more.
The quality of wine largely depends on the quality of wine grapes, which is determined by their chemical composition. Therefore, measuring parameters related to grape ripeness, such as soluble solids content (SSC), is crucial for harvesting high-quality grapes. Visible–Near-Infrared (Vis/NIR) spectroscopy enables effective, non-destructive detection of SSC in grapes. However, commercial Vis/NIR spectrometers are often expensive, bulky, and power-consuming, making them unsuitable for on-site applications. This article integrated the AS7265X sensor to develop a low-cost handheld IoT multispectral detection device, which can collect 18 variables in the wavelength range of 410–940 nm. The data can be sent in real time to the cloud configuration, where it can be backed up and visualized. After simultaneously removing outliers detected by both Monte Carlo (MC) and principal component analysis (PCA) methods from the raw spectra, the SSC prediction model was established, resulting in an RV2 of 0.697. Eight preprocessing methods were compared, among which moving average smoothing (MAS) and Savitzky–Golay smoothing (SGS) improved the RV2 to 0.756 and 0.766, respectively. Subsequently, feature wavelengths were selected using UVE and SPA, reducing the number of variables from 18 to 5 and 6, respectively, further increasing the RV2 to 0.809 and 0.795. The results indicate that spectral data optimization methods are effective and essential for improving the performance of SSC prediction models. The IoT Vis/NIR Spectroscopic System proposed in this study offers a miniaturized, low-cost, and practical solution for SSC detection in wine grapes. Full article
(This article belongs to the Section Chemical Sensors)
►▼ Show Figures

Figure 1

20 pages, 4503 KiB  
Article
Comparative Validation of the fBrake Method with the Conventional Brake Efficiency Test Under UNE 26110 Using Roller Brake Tester Data
by Víctor Romero-Gómez and José Luis San Román
Sensors 2025, 25(14), 4522; https://doi.org/10.3390/s25144522 - 21 Jul 2025
Viewed by 195
Abstract
In periodic technical inspections (PTIs), evaluating the braking efficiency of light passenger vehicles at their Maximum Authorized Mass (MAM) presents a practical challenge, as bringing laden vehicles to inspection is often unfeasible due to logistical and infrastructure limitations. The fBrake method is proposed [...] Read more.
In periodic technical inspections (PTIs), evaluating the braking efficiency of light passenger vehicles at their Maximum Authorized Mass (MAM) presents a practical challenge, as bringing laden vehicles to inspection is often unfeasible due to logistical and infrastructure limitations. The fBrake method is proposed to overcome this issue by estimating braking efficiency at MAM based on measurements taken from vehicles in more accessible loading conditions. In this study, the fBrake method is validated by demonstrating the equivalence of its efficiency estimates extrapolated from two distinct configurations: an unladen state near the curb weight and a partially laden condition closer to MAM. Following the UNE 26110 standard (Road vehicles. Criteria for the assessment of the equivalence of braking efficiency test methods in relation to the methods defined in ISO 21069), roller brake tester measurements were used to obtain force data under both conditions. The analysis showed that the extrapolated efficiencies agree within combined uncertainty limits, with normalized errors below 1 in all segments tested. Confidence intervals were reduced by up to 74% after electronics update. These results confirm the reliability of the fBrake method for M1 and N1 vehicles and support its adoption as an equivalent procedure in compliance with UNE 26110, particularly when fully laden testing is impractical. Full article
(This article belongs to the Special Issue Advanced Sensing and Analysis Technology in Transportation Safety)
►▼ Show Figures

Figure 1

31 pages, 4435 KiB  
Article
A Low-Cost IoT Sensor and Preliminary Machine-Learning Feasibility Study for Monitoring In-Cabin Air Quality: A Pilot Case from Almaty
by Nurdaulet Tasmurzayev, Bibars Amangeldy, Gaukhar Smagulova, Zhanel Baigarayeva and Aigerim Imash
Sensors 2025, 25(14), 4521; https://doi.org/10.3390/s25144521 - 21 Jul 2025
Viewed by 388
Abstract
The air quality within urban public transport is a critical determinant of passenger health. In the crowded and poorly ventilated cabins of Almaty’s metro, buses, and trolleybuses, concentrations of CO2 and PM2.5 often accumulate, elevating the risk of respiratory and cardiovascular [...] Read more.
The air quality within urban public transport is a critical determinant of passenger health. In the crowded and poorly ventilated cabins of Almaty’s metro, buses, and trolleybuses, concentrations of CO2 and PM2.5 often accumulate, elevating the risk of respiratory and cardiovascular diseases. This study investigates the air quality along three of the city’s busiest transport corridors, analyzing how the concentrations of CO2, PM2.5, and PM10, as well as the temperature and relative humidity, fluctuate with the passenger density and time of day. Continuous measurements were collected using the Tynys mobile IoT device, which was bench-calibrated against a commercial reference sensor. Several machine learning models (logistic regression, decision tree, XGBoost, and random forest) were trained on synchronized environmental and occupancy data, with the XGBoost model achieving the highest predictive accuracy at 91.25%. Our analysis confirms that passenger occupancy is the primary driver of in-cabin pollution and that these machine learning models effectively capture the nonlinear relationships among environmental variables. Since the surveyed routes serve Almaty’s most densely populated districts, improving the ventilation on these lines is of immediate importance to public health. Furthermore, the high-temporal-resolution data revealed short-term pollution spikes that correspond with peak ridership, advancing the current understanding of exposure risks in transit. These findings highlight the urgent need to combine real-time monitoring with ventilation upgrades. They also demonstrate the practical value of using low-cost IoT technologies and data-driven analytics to safeguard public health in urban mobility systems. Full article
(This article belongs to the Special Issue IoT-Based Sensing Systems for Urban Air Quality Forecasting)
►▼ Show Figures

Figure 1

24 pages, 3409 KiB  
Article
DepressionMIGNN: A Multiple-Instance Learning-Based Depression Detection Model with Graph Neural Networks
by Shiwen Zhao, Yunze Zhang, Yikai Su, Kaifeng Su, Jiemin Liu, Tao Wang and Shiqi Yu
Sensors 2025, 25(14), 4520; https://doi.org/10.3390/s25144520 - 21 Jul 2025
Viewed by 316
Abstract
The global prevalence of depression necessitates the application of technological solutions, particularly sensor-based systems, to augment scarce resources for early diagnostic purposes. In this study, we use benchmark datasets that contain multimodal data including video, audio, and transcribed text. To address depression detection [...] Read more.
The global prevalence of depression necessitates the application of technological solutions, particularly sensor-based systems, to augment scarce resources for early diagnostic purposes. In this study, we use benchmark datasets that contain multimodal data including video, audio, and transcribed text. To address depression detection as a chronic long-term disorder reflected by temporal behavioral patterns, we propose a novel framework that segments videos into utterance-level instances using GRU for contextual representation, and then constructs graphs where utterance embeddings serve as nodes connected through dual relationships capturing both chronological development and intermittent relevant information. Graph neural networks are employed to learn multi-dimensional edge relationships and align multimodal representations across different temporal dependencies. Our approach achieves superior performance with an MAE of 5.25 and RMSE of 6.75 on AVEC2014, and CCC of 0.554 and RMSE of 4.61 on AVEC2019, demonstrating significant improvements over existing methods that focus primarily on momentary expressions. Full article
(This article belongs to the Special Issue Multimodal Human Behavior Understanding in Human–AI Interaction: Sensor-Based Signal Processing and Interaction Techniques)
►▼ Show Figures

Figure 1

23 pages, 3858 KiB  
Article
MCFA: Multi-Scale Cascade and Feature Adaptive Alignment Network for Cross-View Geo-Localization
by Kaiji Hou, Qiang Tong, Na Yan, Xiulei Liu and Shoulu Hou
Sensors 2025, 25(14), 4519; https://doi.org/10.3390/s25144519 - 21 Jul 2025
Viewed by 314
Abstract
Cross-view geo-localization (CVGL) presents significant challenges due to the drastic variations in perspective and scene layout between unmanned aerial vehicle (UAV) and satellite images. Existing methods have made certain advancements in extracting local features from images. However, they exhibit limitations in modeling the [...] Read more.
Cross-view geo-localization (CVGL) presents significant challenges due to the drastic variations in perspective and scene layout between unmanned aerial vehicle (UAV) and satellite images. Existing methods have made certain advancements in extracting local features from images. However, they exhibit limitations in modeling the interactions among local features and fall short in aligning cross-view representations accurately. To address these issues, we propose a Multi-Scale Cascade and Feature Adaptive Alignment (MCFA) network, which consists of a Multi-Scale Cascade Module (MSCM) and a Feature Adaptive Alignment Module (FAAM). The MSCM captures the features of the target’s adjacent regions and enhances the model’s robustness by learning key region information through association and fusion. The FAAM, with its dynamically weighted feature alignment module, adaptively adjusts feature differences across different viewpoints, achieving feature alignment between drone and satellite images. Our method achieves state-of-the-art (SOTA) performance on two public datasets, University-1652 and SUES-200. In generalization experiments, our model outperforms existing SOTA methods, with an average improvement of 1.52% in R@1 and 2.09% in AP, demonstrating its effectiveness and strong generalization in cross-view geo-localization tasks. Full article
(This article belongs to the Section Remote Sensors)
►▼ Show Figures

Figure 1

24 pages, 8344 KiB  
Article
Research and Implementation of Travel Aids for Blind and Visually Impaired People
by Jun Xu, Shilong Xu, Mingyu Ma, Jing Ma and Chuanlong Li
Sensors 2025, 25(14), 4518; https://doi.org/10.3390/s25144518 - 21 Jul 2025
Viewed by 273
Abstract
Blind and visually impaired (BVI) people face significant challenges in perception, navigation, and safety during travel. Existing infrastructure (e.g., blind lanes) and traditional aids (e.g., walking sticks, basic audio feedback) provide limited flexibility and interactivity for complex environments. To solve this problem, we [...] Read more.
Blind and visually impaired (BVI) people face significant challenges in perception, navigation, and safety during travel. Existing infrastructure (e.g., blind lanes) and traditional aids (e.g., walking sticks, basic audio feedback) provide limited flexibility and interactivity for complex environments. To solve this problem, we propose a real-time travel assistance system based on deep learning. The hardware comprises an NVIDIA Jetson Nano controller, an Intel D435i depth camera for environmental sensing, and SG90 servo motors for feedback. To address embedded device computational constraints, we developed a lightweight object detection and segmentation algorithm. Key innovations include a multi-scale attention feature extraction backbone, a dual-stream fusion module incorporating the Mamba architecture, and adaptive context-aware detection/segmentation heads. This design ensures high computational efficiency and real-time performance. The system workflow is as follows: (1) the D435i captures real-time environmental data; (2) the processor analyzes this data, converting obstacle distances and path deviations into electrical signals; (3) servo motors deliver vibratory feedback for guidance and alerts. Preliminary tests confirm that the system can effectively detect obstacles and correct path deviations in real time, suggesting its potential to assist BVI users. However, as this is a work in progress, comprehensive field trials with BVI participants are required to fully validate its efficacy. Full article
(This article belongs to the Section Intelligent Sensors)
►▼ Show Figures

Figure 1

19 pages, 3193 KiB  
Article
Theoretical Analysis and Research on Support Reconstruction Control of Magnetic Bearing with Redundant Structure
by Huaqiang Sun, Zhiqin Liang and Baixin Cheng
Sensors 2025, 25(14), 4517; https://doi.org/10.3390/s25144517 - 21 Jul 2025
Viewed by 229
Abstract
At present, the redundant structures are one of the most effective methods for solving magnetic levitation bearing coil failure. Coil failure causes residual effective magnetic poles to form different support structures and even asymmetrical structures. For the magnetic bearing with redundant structures, how [...] Read more.
At present, the redundant structures are one of the most effective methods for solving magnetic levitation bearing coil failure. Coil failure causes residual effective magnetic poles to form different support structures and even asymmetrical structures. For the magnetic bearing with redundant structures, how to construct the electromagnetic force (EMF) that occurs under different support structures to achieve support reconstruction is the key to realizing fault tolerance control. To reveal the support reconstruction mechanism of magnetic bearing with a redundant structure, firstly, this paper takes a single-degree-of-freedom magnetic suspension body as an example to conduct a linearization theory analysis of the offset current, clarifying the concept of the current distribution matrix (CDM) and its function; then, the nonlinear EMF mode of magnetic bearing with an eight-pole is constructed, and it is linearized by using the theory of bias current linearization. Furthermore, the conditions of no coils fail, the 8th coil fails, and the 6–8th coils fail are considered, and, with the maximum principle function of EMF, the corresponding current matrices are obtained. Meanwhile, based on the CDM, the corresponding magnetic flux densities were calculated, proving that EMF reconstruction can be achieved under the three support structures. Finally, with the CDM and position control law, a fault-tolerant control system was constructed, and the simulation of the magnetic bearing with a redundant structure was carried out. The simulation results reveal the mechanism of support reconstruction with three aspects of rotor displacement, the value and direction of currents that occur in each coil. The simulation results show that, in the 8-pole magnetic bearing, this study can achieve support reconstruction in the case of faults in up to two coils. Under the three working conditions of wireless no coil failure, the 8th coil fails and the 6–8th coils fail, the current distribution strategy was adjusted through the CDM. The instantaneous displacement disturbance during the support reconstruction process was less than 0.28 μm, and the EMF after reconstruction was basically consistent with the expected value. Full article
(This article belongs to the Section Electronic Sensors)
►▼ Show Figures

Figure 1

14 pages, 3344 KiB  
Article
Current Sensor with Optimized Linearity for Lightning Impulse Current Measurement
by Wenting Li, Yinglong Diao, Feng Zhou, Zhaozhi Long, Shijun Xie, Jiawei Fan, Kangmin Hu and Zhehao Wang
Sensors 2025, 25(14), 4516; https://doi.org/10.3390/s25144516 - 21 Jul 2025
Viewed by 221
Abstract
Impulse current measurement technology is widely used in various applications, including lightning protection monitoring in power systems, welding current measurement in aircraft and shipbuilding industries, as well as high-current measurement in pulsed power systems. With the advancement of industrial technology, the measurement range [...] Read more.
Impulse current measurement technology is widely used in various applications, including lightning protection monitoring in power systems, welding current measurement in aircraft and shipbuilding industries, as well as high-current measurement in pulsed power systems. With the advancement of industrial technology, the measurement range of impulse currents has continuously expanded, reaching levels as high as mega-amperes (MA). The calibration of the scale factor for impulse current measurement devices is determined through comparison with standard measurement devices. Developing high-accuracy impulse current measurement devices and accurately judging their characteristics are prerequisites for ensuring the precise calibration of impulse current values. This paper introduces two different types of high-impulse current measurement devices. Experimental studies were conducted on the scale factor and response characteristics of the sensors. The scale factor extension calibration method for sensors under high currents of more than 100 kA has also been introduced. Test results indicate that the developed impulse current measurement devices can serve as standard measurement devices for high impulse current measurement. Full article
(This article belongs to the Section Electronic Sensors)
►▼ Show Figures

Figure 1

30 pages, 2049 KiB  
Review
Wearable Sensors-Based Intelligent Sensing and Application of Animal Behaviors: A Comprehensive Review
by Luyu Ding, Chongxian Zhang, Yuxiao Yue, Chunxia Yao, Zhuo Li, Yating Hu, Baozhu Yang, Weihong Ma, Ligen Yu, Ronghua Gao and Qifeng Li
Sensors 2025, 25(14), 4515; https://doi.org/10.3390/s25144515 - 21 Jul 2025
Viewed by 453
Abstract
Accurate monitoring of animal behaviors enables improved management in precision livestock farming (PLF), supporting critical applications including health assessment, estrus detection, parturition monitoring, and feed intake estimation. Although both contact and non-contact sensing modalities are utilized, wearable devices with embedded sensors (e.g., accelerometers, [...] Read more.
Accurate monitoring of animal behaviors enables improved management in precision livestock farming (PLF), supporting critical applications including health assessment, estrus detection, parturition monitoring, and feed intake estimation. Although both contact and non-contact sensing modalities are utilized, wearable devices with embedded sensors (e.g., accelerometers, pressure sensors) offer unique advantages through continuous data streams that enhance behavioral traceability. Focusing specifically on contact sensing techniques, this review examines sensor characteristics and data acquisition challenges, methodologies for processing behavioral data and implementing identification algorithms, industrial applications enabled by recognition outcomes, and prevailing challenges with emerging research opportunities. Current behavior classification relies predominantly on traditional machine learning or deep learning approaches with high-frequency data acquisition. The fundamental limitation restricting advancement in this field is the difficulty in maintaining high-fidelity recognition performance at reduced acquisition rates, particularly for integrated multi-behavior identification. Considering that the computational demands and limited adaptability to complex field environments remain significant constraints, Tiny Machine Learning (Tiny ML) could present opportunities to guide future research toward practical, scalable behavioral monitoring solutions. In addition, algorithm development for functional applications post behavior recognition may represent a critical future research direction. Full article
(This article belongs to the Section Wearables)
►▼ Show Figures

Figure 1

14 pages, 730 KiB  
Article
Opportunities and Limitations of Wrist-Worn Devices for Dyskinesia Detection in Parkinson’s Disease
by Alexander Johannes Wiederhold, Qi Rui Zhu, Sören Spiegel, Adrin Dadkhah, Monika Pötter-Nerger, Claudia Langebrake, Frank Ückert and Christopher Gundler
Sensors 2025, 25(14), 4514; https://doi.org/10.3390/s25144514 - 21 Jul 2025
Viewed by 297
Abstract
During the in-hospital optimization of dopaminergic dosage for Parkinson’s disease, drug-induced dyskinesias emerge as a common side effect. Wrist-worn devices present a substantial opportunity for continuous movement recording and the supportive identification of these dyskinesias. To bridge the gap between dyskinesia assessment and [...] Read more.
During the in-hospital optimization of dopaminergic dosage for Parkinson’s disease, drug-induced dyskinesias emerge as a common side effect. Wrist-worn devices present a substantial opportunity for continuous movement recording and the supportive identification of these dyskinesias. To bridge the gap between dyskinesia assessment and machine learning-enabled detection, the recorded information requires meaningful data representations. This study evaluates and compares two distinct representations of sensor data: a task-dependent, semantically grounded approach and automatically extracted large-scale time-series features. Each representation was assessed on public datasets to identify the best-performing machine learning model and subsequently applied to our own collected dataset to assess generalizability. Data representations incorporating semantic knowledge demonstrated comparable or superior performance to reported works, with peak F1 scores of 0.68. Generalization to our own dataset from clinical practice resulted in an observed F1 score of 0.53 using both setups. These results highlight the potential of semantic movement data analysis for dyskinesia detection. Dimensionality reduction in accelerometer-based movement data positively impacts performance, and models trained with semantically obtained features avoid overfitting. Expanding cohorts with standardized neurological assessments labeled by medical experts is essential for further improvements. Full article
(This article belongs to the Section Wearables)
►▼ Show Figures

Figure 1

21 pages, 1057 KiB  
Article
Hybrid Sensor Placement Framework Using Criterion-Guided Candidate Selection and Optimization
by Se-Hee Kim, JungHyun Kyung, Jae-Hyoung An and Hee-Chang Eun
Sensors 2025, 25(14), 4513; https://doi.org/10.3390/s25144513 - 21 Jul 2025
Viewed by 200
Abstract
This study presents a hybrid sensor placement methodology that combines criterion-based candidate selection with advanced optimization algorithms. Four established selection criteria—modal kinetic energy (MKE), modal strain energy (MSE), modal assurance criterion (MAC) sensitivity, and mutual information (MI)—are used to evaluate DOF sensitivity and [...] Read more.
This study presents a hybrid sensor placement methodology that combines criterion-based candidate selection with advanced optimization algorithms. Four established selection criteria—modal kinetic energy (MKE), modal strain energy (MSE), modal assurance criterion (MAC) sensitivity, and mutual information (MI)—are used to evaluate DOF sensitivity and generate candidate pools. These are followed by one of four optimization algorithms—greedy, genetic algorithm (GA), particle swarm optimization (PSO), or simulated annealing (SA)—to identify the optimal subset of sensor locations. A key feature of the proposed approach is the incorporation of constraint dynamics using the Udwadia–Kalaba (U–K) generalized inverse formulation, which enables the accurate expansion of structural responses from sparse sensor data. The framework assumes a noise-free environment during the initial sensor design phase, but robustness is verified through extensive Monte Carlo simulations under multiple noise levels in a numerical experiment. This combined methodology offers an effective and flexible solution for data-driven sensor deployment in structural health monitoring. To clarify the rationale for using the Udwadia–Kalaba (U–K) generalized inverse, we note that unlike conventional pseudo-inverses, the U–K method incorporates physical constraints derived from partial mode shapes. This allows a more accurate and physically consistent reconstruction of unmeasured responses, particularly under sparse sensing. To clarify the benefit of using the U–K generalized inverse over conventional pseudo-inverses, we emphasize that the U–K method allows the incorporation of physical constraints derived from partial mode shapes directly into the reconstruction process. This leads to a constrained dynamic solution that not only reflects the known structural behavior but also improves numerical conditioning, particularly in underdetermined or ill-posed cases. Unlike conventional Moore–Penrose pseudo-inverses, which yield purely algebraic solutions without physical insight, the U–K formulation ensures that reconstructed responses adhere to dynamic compatibility, thereby reducing artifacts caused by sparse measurements or noise. Compared to unconstrained least-squares solutions, the U–K approach improves stability and interpretability in practical SHM scenarios. Full article
(This article belongs to the Special Issue Advanced Fault Diagnosis and Health Monitoring Techniques for Complex Engineering Systems: 2nd Edition)
►▼ Show Figures

Figure 1

14 pages, 2512 KiB  
Article
Research on Two-Stage Data Compression at the Acquisition Node in Remote-Detection Acoustic Logging
by Xiaolong Hao, Yangtao Hu, Bingnan Yan, Hang Hui, Yunxia Chen and Bingqi Zhang
Sensors 2025, 25(14), 4512; https://doi.org/10.3390/s25144512 - 21 Jul 2025
Viewed by 196
Abstract
The substantial volume of data acquired through remote-detection acoustic logging poses a remarkable challenge because of the limited real-time upload speed of the cable, which severely impedes its further application. To address this issue, a two-stage data compression method that was implemented at [...] Read more.
The substantial volume of data acquired through remote-detection acoustic logging poses a remarkable challenge because of the limited real-time upload speed of the cable, which severely impedes its further application. To address this issue, a two-stage data compression method that was implemented at the acquisition node was proposed in this study. This approach includes a field programmable gate array (FPGA)-based hardware system and a two-stage downhole data compression algorithm combining wavelet transform and adaptive differential pulse-code modulation paired with ground decompression software. Finally, the proposed compression method was evaluated using actual logging data. The test results revealed that the overall compression rate of the two-stage compression method was 25.1%. The reconstructed waveforms highly retained the overall shape of the original waveforms, and the severe relative distortion of individual data points did not affect the extraction of the sliding longitudinal, sliding transverse and reflected waveforms. The FPGA compressed 2048 16-bit waveforms in approximately 100 μs with low resource utilization and workload. It considerably outperformed DSP-based pre-transmission compression. Herein, the data compression method at the acquisition node helped in reducing the workload on the master control node and increasing the effective speed of the cable transmission up to 400%, thereby enhancing the remote-detection acoustic logging. Full article
(This article belongs to the Section Physical Sensors)
►▼ Show Figures

Figure 1

17 pages, 9561 KiB  
Article
Magnetic Data Correction for Fluxgate Magnetometers on a Paramagnetic Unmanned Surface Vehicle: A Comparative Analysis in Marine Surveys
by Seonggyu Choi, Mijeong Kim, Yosup Park, Gidon Moon and Hanjin Choe
Sensors 2025, 25(14), 4511; https://doi.org/10.3390/s25144511 - 21 Jul 2025
Viewed by 281
Abstract
Unmanned Surface Vehicle (USV) offers a cost-effective platform for high-resolution marine magnetic surveys using shipborne fluxgate magnetometers. However, platform-induced magnetic interference and electromagnetic interference (EMI) can degrade data quality, even with paramagnetic hulls. This study evaluates fluxgate magnetometer data acquired from a paramagnetic-hulled [...] Read more.
Unmanned Surface Vehicle (USV) offers a cost-effective platform for high-resolution marine magnetic surveys using shipborne fluxgate magnetometers. However, platform-induced magnetic interference and electromagnetic interference (EMI) can degrade data quality, even with paramagnetic hulls. This study evaluates fluxgate magnetometer data acquired from a paramagnetic-hulled USV. Noise characterization identified EMI and maneuver-induced high-frequency noise, the latter of which was effectively reduced through low-pass filtering. We compared four different correction approaches addressing both vessel attitude and magnetization. The results demonstrate that the paramagnetic hull significantly reduces magnetic interference and shortens the duration of viscous magnetization (VM) effects caused by eddy currents in the platform, compared to conventional ferromagnetic vessels. Nonetheless, residual magnetization from onboard ferromagnetic components still requires correction. A method utilizing all nine components of the susceptibility tensor demonstrated improved accuracy and stability. Despite corrections, low-frequency VM-related noise during azimuth changes and a consistent absolute offset (~200 nT) remain when compared to towed scalar magnetometer data. These findings validate the use of paramagnetic USV for vector magnetic surveys, highlighting their benefit in VM mitigation while emphasizing the need for further development in VM correction and offset correction to achieve high-precision measurements. Full article
(This article belongs to the Special Issue Magnetic Sensors and Systems for Scientific and Industrial Applications)
►▼ Show Figures

Figure 1

26 pages, 3533 KiB  
Article
EDMR: An Enhanced Dynamic Multi-Hop Routing Protocol with a Novel Sleeping Mechanism for Wireless Sensor Networks
by Emad Alnawafa and Mohammad Allaymoun
Sensors 2025, 25(14), 4510; https://doi.org/10.3390/s25144510 - 21 Jul 2025
Viewed by 234
Abstract
Numerous protocols have emerged to address the energy depletion problem in Wireless Sensor Networks (WSNs). Among these protocols, the Dynamic Multi-Hop Routing (DMR) protocol adopts a dynamic technique for routing data across the network. The use of the DMR protocol has shown promising [...] Read more.
Numerous protocols have emerged to address the energy depletion problem in Wireless Sensor Networks (WSNs). Among these protocols, the Dynamic Multi-Hop Routing (DMR) protocol adopts a dynamic technique for routing data across the network. The use of the DMR protocol has shown promising results in reducing energy consumption, prolonging the network lifetime, and increasing throughput. To improve the performance of WSNs, this paper proposes the Enhanced Dynamic Multi-Hop Routing (EDMR) protocol as a modification of the DMR protocol. The EDMR protocol introduces an effective sleeping mechanism that selectively deactivates clusters that do not generate significantly updated data for a specific duration. This mechanism reduces redundant transmissions, thereby saving energy and prolonging the network lifetime. The EDMR protocol incorporates static and dynamic approaches to support two major categories of applications: monitoring and event-driven applications. The proposed protocol is evaluated against the DMR protocol, the Enhanced Dynamic Multi-Hop Technique (EMDHT-LEACH) protocol, and the Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol. The simulation results demonstrate that the EDMR protocol mitigates energy depletion, extends the network lifetime, increases stability, and improves network throughput toward the Base Station (BS), while reducing packet redundancy compared with the other protocols. Full article
(This article belongs to the Section Internet of Things)
►▼ Show Figures

Figure 1

27 pages, 1868 KiB  
Article
SAM2-DFBCNet: A Camouflaged Object Detection Network Based on the Heira Architecture of SAM2
by Cao Yuan, Libang Liu, Yaqin Li and Jianxiang Li
Sensors 2025, 25(14), 4509; https://doi.org/10.3390/s25144509 - 21 Jul 2025
Viewed by 308
Abstract
Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with their background, presenting significant challenges such as low contrast, complex textures, and blurred boundaries. Existing deep learning methods often struggle to achieve robust segmentation under these conditions. To address these [...] Read more.
Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with their background, presenting significant challenges such as low contrast, complex textures, and blurred boundaries. Existing deep learning methods often struggle to achieve robust segmentation under these conditions. To address these limitations, this paper proposes a novel COD network, SAM2-DFBCNet, built upon the SAM2 Hiera architecture. Our network incorporates three key modules: (1) the Camouflage-Aware Context Enhancement Module (CACEM), which fuses local and global features through an attention mechanism to enhance contextual awareness in low-contrast scenes; (2) the Cross-Scale Feature Interaction Bridge (CSFIB), which employs a bidirectional convolutional GRU for the dynamic fusion of multi-scale features, effectively mitigating representation inconsistencies caused by complex textures and deformations; and (3) the Dynamic Boundary Refinement Module (DBRM), which combines channel and spatial attention mechanisms to optimize boundary localization accuracy and enhance segmentation details. Extensive experiments on three public datasets—CAMO, COD10K, and NC4K—demonstrate that SAM2-DFBCNet outperforms twenty state-of-the-art methods, achieving maximum improvements of 7.4%, 5.78%, and 4.78% in key metrics such as S-measure (Sα), F-measure (Fβ), and mean E-measure (Eϕ), respectively, while reducing the Mean Absolute Error (M) by 37.8%. These results validate the superior performance and robustness of our approach in complex camouflage scenarios. Full article
(This article belongs to the Special Issue Transformer Applications in Target Tracking)
►▼ Show Figures

Figure 1

21 pages, 10783 KiB  
Article
An ALoGI PU Algorithm for Simulating Kelvin Wake on Sea Surface Based on Airborne Ku SAR
by Limin Zhai, Yifan Gong and Xiangkun Zhang
Sensors 2025, 25(14), 4508; https://doi.org/10.3390/s25144508 - 21 Jul 2025
Viewed by 305
Abstract
The airborne Synthetic Aperture Radar (SAR) has the advantages of high-precision real-time observation of wave height variations and portability in the high frequency band, such as the Ku band. In view of the Four Fast Fourier Transform (4-FFT) algorithm, combined with a Gaussian [...] Read more.
The airborne Synthetic Aperture Radar (SAR) has the advantages of high-precision real-time observation of wave height variations and portability in the high frequency band, such as the Ku band. In view of the Four Fast Fourier Transform (4-FFT) algorithm, combined with a Gaussian operator, a Laplacian of Gaussian (LoG) Phase Unwrapping (PU) expression was derived. Then, an Adaptive LoG (ALoG) algorithm was proposed based on adaptive variance, further optimizing the algorithm through iteration. Building the models of Kelvin wake on the sea surface and height to phase, the interferometric phase of wave height can be simulated. These PU algorithms were qualitatively and quantitatively evaluated. The Principal Component Analysis (PCA) scores of the ALoG iteration (ALoGI) algorithm are the best under the tested noise levels of the simulation. Through a simulation experiment, it has been proven that the superiority of the ALoGI algorithm in high spatial resolution inversion for the sea-ship surface height of the Kelvin wake, with good stability and noise resistance. Full article
(This article belongs to the Section Radar Sensors)
►▼ Show Figures

Figure 1

15 pages, 1991 KiB  
Article
Hybrid Deep–Geometric Approach for Efficient Consistency Assessment of Stereo Images
by Michał Kowalczyk, Piotr Napieralski and Dominik Szajerman
Sensors 2025, 25(14), 4507; https://doi.org/10.3390/s25144507 - 20 Jul 2025
Viewed by 397
Abstract
We present HGC-Net, a hybrid pipeline for assessing geometric consistency between stereo image pairs. Our method integrates classical epipolar geometry with deep learning components to compute an interpretable scalar score A, reflecting the degree of alignment. Unlike traditional techniques, which may overlook subtle [...] Read more.
We present HGC-Net, a hybrid pipeline for assessing geometric consistency between stereo image pairs. Our method integrates classical epipolar geometry with deep learning components to compute an interpretable scalar score A, reflecting the degree of alignment. Unlike traditional techniques, which may overlook subtle miscalibrations, HGC-Net reliably detects both severe and mild geometric distortions, such as sub-degree tilts and pixel-level shifts. We evaluate the method on the Middlebury 2014 stereo dataset, using synthetically distorted variants to simulate misalignments. Experimental results show that our score degrades smoothly with increasing geometric error and achieves high detection rates even at minimal distortion levels, outperforming baseline approaches based on disparity or calibration checks. The method operates in real time (12.5 fps on 1080p input) and does not require access to internal camera parameters, making it suitable for embedded stereo systems and quality monitoring in robotic and AR/VR applications. The approach also supports explainability via confidence maps and anomaly heatmaps, aiding human operators in identifying problematic regions. Full article
(This article belongs to the Special Issue Feature Papers in Physical Sensors 2025)
►▼ Show Figures

Figure 1

16 pages, 5468 KiB  
Article
Alpine Meadow Fractional Vegetation Cover Estimation Using UAV-Aided Sentinel-2 Imagery
by Kai Du, Yi Shao, Naixin Yao, Hongyan Yu, Shaozhong Ma, Xufeng Mao, Litao Wang and Jianjun Wang
Sensors 2025, 25(14), 4506; https://doi.org/10.3390/s25144506 - 20 Jul 2025
Viewed by 261
Abstract
Fractional Vegetation Cover (FVC) is a crucial indicator describing vegetation conditions and provides essential data for ecosystem health assessments. However, due to the low and sparse vegetation in alpine meadows, it is challenging to obtain pure vegetation pixels from Sentinel-2 imagery, resulting in [...] Read more.
Fractional Vegetation Cover (FVC) is a crucial indicator describing vegetation conditions and provides essential data for ecosystem health assessments. However, due to the low and sparse vegetation in alpine meadows, it is challenging to obtain pure vegetation pixels from Sentinel-2 imagery, resulting in errors in the FVC estimation using traditional pixel dichotomy models. This study integrated Sentinel-2 imagery with unmanned aerial vehicle (UAV) data and utilized the pixel dichotomy model together with four machine learning algorithms, namely Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Deep Neural Network (DNN), to estimate FVC in an alpine meadow region. First, FVC was preliminarily estimated using the pixel dichotomy model combined with nine vegetation indices applied to Sentinel-2 imagery. The performance of these estimates was evaluated against reference FVC values derived from centimeter-level UAV data. Subsequently, four machine learning models were employed for an accurate FVC inversion, using the estimated FVC values and UAV-derived reference FVC as inputs, following feature importance ranking and model parameter optimization. The results showed that: (1) Machine learning algorithms based on Sentinel-2 and UAV imagery effectively improved the accuracy of FVC estimation in alpine meadows. The DNN-based FVC estimation performed best, with a coefficient of determination of 0.82 and a root mean square error (RMSE) of 0.09. (2) In vegetation coverage estimation based on the pixel dichotomy model, different vegetation indices demonstrated varying performances across areas with different FVC levels. The GNDVI-based FVC achieved a higher accuracy (RMSE = 0.08) in high-vegetation coverage areas (FVC > 0.7), while the NIRv-based FVC and the SR-based FVC performed better (RMSE = 0.10) in low-vegetation coverage areas (FVC < 0.4). The method provided in this study can significantly enhance FVC estimation accuracy with limited fieldwork, contributing to alpine meadow monitoring on the Qinghai–Tibet Plateau. Full article
(This article belongs to the Section Remote Sensors)
►▼ Show Figures

Graphical abstract

22 pages, 6556 KiB  
Article
Multi-Task Trajectory Prediction Using a Vehicle-Lane Disentangled Conditional Variational Autoencoder
by Haoyang Chen, Na Li, Hangguan Shan, Eryun Liu and Zhiyu Xiang
Sensors 2025, 25(14), 4505; https://doi.org/10.3390/s25144505 - 20 Jul 2025
Viewed by 357
Abstract
Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability [...] Read more.
Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability to capture evolving spatial contexts and produce diverse yet contextually coherent predictions. To tackle these challenges, we propose MS-SLV, a novel generative framework that introduces (1) a time-aware scene encoder that aligns HD map features with vehicle motion to capture evolving scene semantics and (2) a structured latent model that explicitly disentangles agent-specific intent and scene-level constraints. Additionally, we introduce an auxiliary lane prediction task to provide targeted supervision for scene understanding and improve latent variable learning. Our approach jointly predicts future trajectories and lane sequences, enabling more interpretable and scene-consistent forecasts. Extensive evaluations on the nuScenes dataset demonstrate the effectiveness of MS-SLV, achieving a 12.37% reduction in average displacement error and a 7.67% reduction in final displacement error over state-of-the-art methods. Moreover, MS-SLV significantly improves multi-modal prediction, reducing the top-5 Miss Rate (MR5) and top-10 Miss Rate (MR10) by 26% and 33%, respectively, and lowering the Off-Road Rate (ORR) by 3%, as compared with the strongest baseline in our evaluation. Full article
(This article belongs to the Special Issue AI-Driven Sensor Technologies for Next-Generation Electric Vehicles)
►▼ Show Figures

Figure 1

28 pages, 5540 KiB  
Article
An Ontology Proposal for Implementing Digital Twins in Hospitality: The Case of Front-End Services
by Moises Segura-Cedres, Desiree Manzano-Farray, Carmen Lidia Aguiar-Castillo, Rafael Perez-Jimenez and Victor Guerra-Yanez
Sensors 2025, 25(14), 4504; https://doi.org/10.3390/s25144504 - 20 Jul 2025
Viewed by 337
Abstract
The implementation of Digital Twins (DTs) in hospitality facilities represents a significant opportunity to optimize front-end services, enhancing guest experience and operational efficiency. This paper proposes an ontology-driven approach for DTs in hotel reception areas, focusing on integrating IoT devices, real-time data processing, [...] Read more.
The implementation of Digital Twins (DTs) in hospitality facilities represents a significant opportunity to optimize front-end services, enhancing guest experience and operational efficiency. This paper proposes an ontology-driven approach for DTs in hotel reception areas, focusing on integrating IoT devices, real-time data processing, and service optimization. By modeling interactions between guests, receptionists, and hotel management systems, DTs enhance resource allocation, predictive maintenance, and customer satisfaction. Simulations and historical data analysis enable forecasting demand fluctuations and optimizing check-in/check-out processes. This research provides a structured framework for DT applications in hospitality, validated through scenario-based simulations, showing significant improvements in check-in time and guest satisfaction. Validation was conducted through scenario-based simulations reflecting real-world operational challenges, such as guest surges, room assignment, and staff workload balancing. Metrics including check-in time, guest satisfaction index, task completion rates, and prediction accuracy were used to evaluate performance. Simulations were grounded in historical hotel data and modeled typical peak-period dynamics to ensure realism. Results demonstrated a 25–35% reduction in check-in time, a 20% improvement in staff efficiency, and significant enhancements in guest satisfaction, underscoring the practical value of the proposed framework in real hospitality settings. Full article
(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2025)
►▼ Show Figures

Graphical abstract

9 pages, 1583 KiB  
Article
Snapshot Quantitative Phase Imaging with Acousto-Optic Chromatic Aberration Control
by Christos Alexandropoulos, Laura Rodríguez-Suñé and Martí Duocastella
Sensors 2025, 25(14), 4503; https://doi.org/10.3390/s25144503 - 20 Jul 2025
Viewed by 284
Abstract
The transport of intensity equation enables quantitative phase imaging from only two axially displaced intensity images, facilitating the characterization of low-contrast samples like cells and microorganisms. However, the rapid selection of the correct defocused planes, crucial for real-time phase imaging of dynamic events, [...] Read more.
The transport of intensity equation enables quantitative phase imaging from only two axially displaced intensity images, facilitating the characterization of low-contrast samples like cells and microorganisms. However, the rapid selection of the correct defocused planes, crucial for real-time phase imaging of dynamic events, remains challenging. Additionally, the different images are normally acquired sequentially, further limiting phase-reconstruction speed. Here, we report on a system that addresses these issues and enables user-tuned defocusing with snapshot phase retrieval. Our approach is based on combining multi-color pulsed illumination with acousto-optic defocusing for microsecond-scale chromatic aberration control. By illuminating each plane with a different color and using a color camera, the information to reconstruct a phase map can be gathered in a single acquisition. We detail the fundamentals of our method, characterize its performance, and demonstrate live phase imaging of a freely moving microorganism at speeds of 150 phase reconstructions per second, limited only by the camera’s frame rate. Full article
(This article belongs to the Special Issue Optical Imaging for Medical Applications)
►▼ Show Figures

Figure 1

25 pages, 6969 KiB  
Article
An Analysis of the Design and Kinematic Characteristics of an Octopedic Land–Air Bionic Robot
by Jianwei Zhao, Jiaping Gao, Mingsong Bao, Hao Zhai, Xu Pei and Zheng Jiang
Sensors 2025, 25(14), 4502; https://doi.org/10.3390/s25144502 - 19 Jul 2025
Viewed by 421
Abstract
The urgent need for complex terrain adaptability in industrial automation and disaster relief has highlighted the great potential of octopedal wheel-legged robots. However, their design complexity and motion control challenges must be addressed. In this study, an innovative design approach is employed to [...] Read more.
The urgent need for complex terrain adaptability in industrial automation and disaster relief has highlighted the great potential of octopedal wheel-legged robots. However, their design complexity and motion control challenges must be addressed. In this study, an innovative design approach is employed to construct a highly adaptive robot architecture capable of intelligently adjusting the wheel-leg configuration to cope with changing environments. An advanced kinematic analysis and simulation techniques are combined with inverse kinematic algorithms and dynamic planning to achieve a typical ‘Step-Wise Octopedal Dynamic Coordination Gait’ and different gait planning and optimization. The effectiveness of the design and control strategy is verified through the construction of an experimental platform and field tests, significantly improving the robot’s adaptability and mobility in complex terrain. Additionally, an optional integrated quadrotor module with a compact folding mechanism is incorporated, enabling the robot to overcome otherwise impassable obstacles via short-distance flight when ground locomotion is impaired. This achievement not only enriches the theory and methodology of the multi-legged robot design but also establishes a solid foundation for its widespread application in disaster rescue, exploration, and industrial automation. Full article
(This article belongs to the Section Sensors and Robotics)
►▼ Show Figures

Figure 1

22 pages, 3091 KiB  
Article
Assessment of the Risk of Failure in Electric Power Supply Systems for Railway Traffic Control Devices
by Tomasz Ciszewski, Jerzy Wojciechowski, Mieczysław Kornaszewski, Grzegorz Krawczyk, Beata Kuźmińska-Sołśnia and Artur Hermanowicz
Sensors 2025, 25(14), 4501; https://doi.org/10.3390/s25144501 - 19 Jul 2025
Viewed by 341
Abstract
This paper provides a reliability analysis of selected components in the electrical power supply systems used for railway traffic control equipment. It includes rectifiers, controllers, inverters, generators, batteries, sensors, and switching elements. The study used failure data from power supply system elements on [...] Read more.
This paper provides a reliability analysis of selected components in the electrical power supply systems used for railway traffic control equipment. It includes rectifiers, controllers, inverters, generators, batteries, sensors, and switching elements. The study used failure data from power supply system elements on selected railway lines. The analysis was performed using a mathematical model based on Markov processes. Based on the findings, recommendations were made to improve safety levels. The results presented in the paper could serve as a valuable source of information for operators of power supply systems in railway traffic control, helping them optimize maintenance processes and increase equipment reliability. Full article
(This article belongs to the Special Issue Diagnosis and Risk Analysis of Electrical Systems)
►▼ Show Figures

Figure 1

18 pages, 2948 KiB  
Article
Energy-Aware Duty Cycle Management for Solar-Powered IoT Devices
by Michael Gerndt, Mustafa Ispir, Isaac Nunez and Shajulin Benedict
Sensors 2025, 25(14), 4500; https://doi.org/10.3390/s25144500 - 19 Jul 2025
Viewed by 278
Abstract
IoT devices with sensors and actuators are frequently deployed in environments without access to the power grid. These devices are battery powered and might make use of energy harvesting if battery lifetime is too limited. This article focuses on automatically adapting the duty [...] Read more.
IoT devices with sensors and actuators are frequently deployed in environments without access to the power grid. These devices are battery powered and might make use of energy harvesting if battery lifetime is too limited. This article focuses on automatically adapting the duty cycle frequency to the predicted available solar energy so that a continuous operation of IoT applications is guaranteed. The implementation is based on a low-cost solar control board that is integrated with the Serverless IoT Framework (SIF), which provides an event-based programming paradigm for microcontroller-based IoT devices. The paper presents a case study where the IoT device sleep time is pro-actively adapted to a predicted sequence of cloudy days to guarantee continuous operation. Full article
(This article belongs to the Section Internet of Things)
►▼ Show Figures

Figure 1

41 pages, 9748 KiB  
Article
Wind Turbine Fault Detection Through Autoencoder-Based Neural Network and FMSA
by Welker Facchini Nogueira, Arthur Henrique de Andrade Melani and Gilberto Francisco Martha de Souza
Sensors 2025, 25(14), 4499; https://doi.org/10.3390/s25144499 - 19 Jul 2025
Viewed by 381
Abstract
Amid the global shift toward clean energy, wind power has emerged as a critical pillar of the modern energy matrix. To improve the reliability and maintainability of wind farms, this work proposes a novel hybrid fault detection approach that combines expert-driven diagnostic knowledge [...] Read more.
Amid the global shift toward clean energy, wind power has emerged as a critical pillar of the modern energy matrix. To improve the reliability and maintainability of wind farms, this work proposes a novel hybrid fault detection approach that combines expert-driven diagnostic knowledge with data-driven modeling. The framework integrates autoencoder-based neural networks with Failure Mode and Symptoms Analysis, leveraging the strengths of both methodologies to enhance anomaly detection, feature selection, and fault localization. The methodology comprises five main stages: (i) the identification of failure modes and their observable symptoms using FMSA, (ii) the acquisition and preprocessing of SCADA monitoring data, (iii) the development of dedicated autoencoder models trained exclusively on healthy operational data, (iv) the implementation of an anomaly detection strategy based on the reconstruction error and a persistence-based rule to reduce false positives, and (v) evaluation using performance metrics. The approach adopts a fault-specific modeling strategy, in which each turbine and failure mode is associated with a customized autoencoder. The methodology was first validated using OpenFAST 3.5 simulated data with induced faults comprising normal conditions and a 1% mass imbalance fault on a blade, enabling the verification of its effectiveness under controlled conditions. Subsequently, the methodology was applied to a real-world SCADA data case study from wind turbines operated by EDP, employing historical operational data from turbines, including thermal measurements and operational variables such as wind speed and generated power. The proposed system achieved 99% classification accuracy on simulated data detect anomalies up to 60 days before reported failures in real operational conditions, successfully identifying degradations in components such as the transformer, gearbox, generator, and hydraulic group. The integration of FMSA improves feature selection and fault localization, enhancing both the interpretability and precision of the detection system. This hybrid approach demonstrates the potential to support predictive maintenance in complex industrial environments. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
►▼ Show Figures

Figure 1

23 pages, 5467 KiB  
Article
Design of Heavy Agricultural Machinery Rail Transport System and Dynamic Performance Research on Tracks in Hilly Regions of Southern China
by Cheng Lin, Hao Chen, Jiawen Chen, Shaolong Gou, Yande Liu and Jun Hu
Sensors 2025, 25(14), 4498; https://doi.org/10.3390/s25144498 - 19 Jul 2025
Viewed by 252
Abstract
To address the limitations of conventional single-track rail systems in challenging hilly and mountainous terrains, which are ill-suited for transporting heavy agricultural machinery, there is a critical need to develop a specialized the double-track rail transportation system optimized for orchard equipment. Recognizing this [...] Read more.
To address the limitations of conventional single-track rail systems in challenging hilly and mountainous terrains, which are ill-suited for transporting heavy agricultural machinery, there is a critical need to develop a specialized the double-track rail transportation system optimized for orchard equipment. Recognizing this requirement, our research team designed and implemented a double-track rail transportation system. In this innovative system, the rail functions as the pivotal component, with its structural properties significantly impacting the machine’s overall stability and operational performance. In this study, resistance strain gauges were employed to analyze the stress–strain distribution of the track under a full load of 750 kg, a critical factor in the system’s design. To further investigate the structural performance of the double-track rail, the impact hammer method was utilized in conjunction with triaxial acceleration sensors to conduct experimental modal analysis (EMA) under actual support conditions. By integrating the Eigensystem Realization Algorithm (ERA), the first 20 natural modes and their corresponding parameters were successfully identified with high precision. A comparative analysis between finite element simulation results and experimental measurements was performed, revealing the double-track rail’s inherent vibration characteristics under constrained modal conditions versus actual boundary constraints. These valuable findings serve as a theoretical foundation for the dynamic optimization of rail structures and the mitigation of resonance issues. The advancement of hilly and mountainous rail transportation systems holds significant promise for enhancing productivity and transportation efficiency in agricultural operations. Full article
(This article belongs to the Section Vehicular Sensing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-286
Previous Issue
Next Issue
Back to TopTop