Sensors

18 pages, 1244 KB

Open AccessArticle

Interfacial Charge-Transfer Engineering in Borophene–MWCNT Heterostructures for Multifunctional Humidity and Physiological Sensing

by Anran Ma, Tao Wang, Zhilin Zhao, Yi Liu, Maoping Xu, Shengxiang Gao, Rui Zhu, Jiamin Wu, Chuang Hou and Guoan Tai

Sensors 2026, 26(3), 976; https://doi.org/10.3390/s26030976 (registering DOI) - 2 Feb 2026

Abstract

Humidity sensing is essential in medical fields such as respiratory support, neonatal care, sterilization, and pharmaceutical storage. However, current sensors face limitations, including slow response/recovery, low sensitivity, and poor long-term stability. To address these challenges, we developed borophene-multiwalled carbon nanotube (MWCNT) heterostructures using [...] Read more.

Humidity sensing is essential in medical fields such as respiratory support, neonatal care, sterilization, and pharmaceutical storage. However, current sensors face limitations, including slow response/recovery, low sensitivity, and poor long-term stability. To address these challenges, we developed borophene-multiwalled carbon nanotube (MWCNT) heterostructures using a stepwise in situ thermal decomposition method. The resulting humidity sensor exhibits an ultrabroad detection range (11–97% RH), ultra-high sensitivity (55,000% at 97% RH), and fast response/recovery times (10.04 s/4.8 s). Through interfacial charge-transfer engineering, the system facilitates rapid electron migration, enhances Schottky barrier modulation, and provides abundant active adsorption sites for water molecules, thereby achieving comprehensive improvement in sensing performance. It also demonstrates excellent selectivity, mechanical flexibility, and operational stability. Notably, the sensor’s sensitivity at 97% RH surpasses that of sensors based on pure borophene or MWCNT by 37–462 times, highlighting the advantages of heterostructure engineering. The multifunctionality of the device suggests its potential in areas beyond conventional sensing, including non-contact voice recognition, skin humidity mapping, and real-time breath monitoring. These results lay a solid foundation for developing borophene-MWCNT heterostructures into a high-performance platform for next-generation medical diagnostics and intelligent health monitoring. Full article

(This article belongs to the Special Issue Systems for Contactless Monitoring of Vital Signs)

21 pages, 419 KB

Open AccessArticle

IoT-Based Intervention and Home Support to Address Frailty-Related Vulnerability and Well-Being in Older Adults Living in Rural Areas

by Jessica Fernández-Solana, Rodrigo Vélez-Santamaría, Ana I. Sánchez-Iglesias, Maria Isabel Villanueva-Alameda, Jerónimo J. González-Bernal and Josefa González-Santos

Sensors 2026, 26(3), 975; https://doi.org/10.3390/s26030975 (registering DOI) - 2 Feb 2026

Abstract

Background: Spain has an increasingly aging population in rural areas. These individuals often face the burden of illness and the limitations it causes in solitude, leading to greater impacts on their health and quality of life. Therefore, the aim of this study was [...] Read more.

Background: Spain has an increasingly aging population in rural areas. These individuals often face the burden of illness and the limitations it causes in solitude, leading to greater impacts on their health and quality of life. Therefore, the aim of this study was to evaluate the effectiveness of a combined IoT-based home monitoring and Silver Caregiver support intervention on health-related quality of life and functional, cognitive, emotional, and social outcomes in older adults living alone in rural settings. Material and methods: A longitudinal study was conducted with a sample of 144 older adults from rural areas who received home support through a Silver Caregiver and IoT technology. Results: Statistically significant differences were observed in cognitive status, anxiety, depression, family functionality, social support, life satisfaction, and quality of life. Conclusions: The findings indicate that the combined intervention primarily enhances psychological well-being, social connectedness, and perceived quality of life while contributing to the maintenance of basic physical function in older adults living in rural areas. Full article

(This article belongs to the Special Issue IoT and Sensor Technologies for Healthcare)

26 pages, 4105 KB

Open AccessArticle

Robust Dual-Stream Diagnosis Network for Ultrasound Breast Tumor Classification with Cross-Domain Segmentation Priors

by Xiaokai Jiang, Xuewen Ding, Jinying Ma, Chunyu Liu and Xinyi Li

Sensors 2026, 26(3), 974; https://doi.org/10.3390/s26030974 (registering DOI) - 2 Feb 2026

Abstract

Ultrasound imaging is widely used for early breast cancer screening to enhance patient survival. However, interpreting these images is inherently challenging due to speckle noise, low lesion-to-tissue contrast, and highly variable tumor morphology within complex anatomical structures. Additionally, variations in image characteristics across [...] Read more.

Ultrasound imaging is widely used for early breast cancer screening to enhance patient survival. However, interpreting these images is inherently challenging due to speckle noise, low lesion-to-tissue contrast, and highly variable tumor morphology within complex anatomical structures. Additionally, variations in image characteristics across institutions and devices further impede the development of robust and generalizable computer-aided diagnostic systems. To alleviate these issues, this paper presents a cross-domain segmentation prior guided classification strategy for robust breast tumor diagnosis in ultrasound imaging, implemented through a novel Dual-Stream Diagnosis Network (DSDNet). DSDNet adopts a decoupled dual-stream architecture, where a frozen segmentation branch supplies spatial priors to guide the classification backbone. This design enables stable and accurate performance across diverse imaging conditions and clinical settings. To realize the proposed DSDNet framework, three novel modules are created. The Dual-Stream Mask Attention (DSMA) module enhances lesion priors by jointly modeling foreground and background cues. The Segmentation Prior Guidance Fusion (SPGF) module integrates multi-scale priors into the classification backbone using cross-domain spatial cues, improving tumor morphology representation. The Mamba-Inspired Linear Transformer (MILT) block, built upon the Mamba-Inspired Linear Attention (MILA) mechanism, serves as an efficient attention-based feature extractor. On the BUSI, BUS, and GDPH_SYSUCC datasets, DSDNet achieves ACC values of 0.878, 0.836, and 0.882, and Recall scores of 0.866, 0.789, and 0.878, respectively. These results highlight the effectiveness and strong classification performance of our method in ultrasound breast cancer diagnosis. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

12 pages, 3367 KB

Open AccessArticle

A Miniature Inductive Encoder for Linear Displacement Measurement

by Wei Xiong, Shouhao Wang, Yajun Ma, Peng Chen, Sijia Cao, Jiajia Xu and Yanxu Wang

Sensors 2026, 26(3), 973; https://doi.org/10.3390/s26030973 (registering DOI) - 2 Feb 2026

Abstract

In order to satisfy the measurement of objects in compact settings, a miniaturized linear inductive encoder with a measurement range of 15 mm is investigated in this paper. The encoder structure integrates a movable part with conductive plates and a stationary part with [...] Read more.

In order to satisfy the measurement of objects in compact settings, a miniaturized linear inductive encoder with a measurement range of 15 mm is investigated in this paper. The encoder structure integrates a movable part with conductive plates and a stationary part with planar excitation and inductive coils. When a high-frequency alternating current is applied to the excitation coils, a time-varying magnetic field will be generated. Meanwhile, the conductive plates on the movable element will produce an eddy current magnetic field to reduce or boost the magnetic field. As the movable part moves, two-channel amplitude-modulated electrical signals whose amplitudes vary with displacement are obtained. The CORDIC algorithm is utilized to calculate the displacement. The paper describes the structure and working principle of the encoder, presents corresponding finite element simulations of the magnetic field, and introduces a prototype fabricated by PCB technology. Experiments evaluating stability, resolution, and accuracy show that the encoder reaches the measurement accuracy of 12.8 μm within one pitch, and the resolution is 0.7 μm. Importantly, its minimal dimensions (20 mm × 10 mm × 1 mm) enable installation in highly constrained mechanisms. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

30 pages, 1298 KB

Open AccessReview

A Comprehensive Review of Non-Invasive Core Body Temperature Measurement Techniques

by Yuki Hashimoto

Sensors 2026, 26(3), 972; https://doi.org/10.3390/s26030972 (registering DOI) - 2 Feb 2026

Abstract

Core body temperature (CBT) is a fundamental physiological parameter tightly regulated by thermoregulatory mechanisms and is critically important for heat stress assessment, clinical management, and circadian rhythm research. Although invasive measurements such as pulmonary artery, esophageal, and rectal temperatures provide high accuracy, their [...] Read more.

Core body temperature (CBT) is a fundamental physiological parameter tightly regulated by thermoregulatory mechanisms and is critically important for heat stress assessment, clinical management, and circadian rhythm research. Although invasive measurements such as pulmonary artery, esophageal, and rectal temperatures provide high accuracy, their practical use is limited by invasiveness, discomfort, and restricted feasibility for continuous monitoring in daily-life or field environments. Consequently, extensive efforts have been devoted to developing non-invasive CBT measurement and estimation techniques. This review provides an application-oriented synthesis of invasive reference methods and representative non-invasive approaches, including in-ear sensors, infrared thermography, ingestible telemetric sensors, heat-flux-based techniques, and model-based estimation using wearable physiological signals. For each approach, measurement principles, accuracy, invasiveness, usability, and application domains are comparatively examined, with particular emphasis on trade-offs between measurement fidelity and real-world implementability. Rather than ranking methods by absolute performance, this review highlights their relative positioning across clinical, occupational, and daily-life contexts. While no single non-invasive technique can universally replace invasive gold standards, recent advances in wearable sensing, heat-flux modeling, and multimodal estimation demonstrate growing potential for practical CBT monitoring. Overall, the findings suggest that future CBT assessment will increasingly rely on hybrid and context-aware systems that integrate complementary methods to enable reliable monitoring under real-world conditions. This review is intended for researchers and practitioners who need to select or design CBT monitoring systems. Full article

(This article belongs to the Special Issue Wearable Physiological Sensors for Smart Healthcare)

► Show Figures

Figure 1

38 pages, 2058 KB

Open AccessArticle

AI-Enhanced Hybrid QAM–PPM Visible Light Communication for Body Area Networks

by Shreyash Shrestha, Attaphongse Taparugssanagorn, Stefano Caputo and Lorenzo Mucchi

Sensors 2026, 26(3), 971; https://doi.org/10.3390/s26030971 (registering DOI) - 2 Feb 2026

Abstract

This paper investigates an artificial intelligence (AI)-enhanced visible light communication (VLC) system for body area networks (BANs) based on a hybrid modulation framework that jointly employs quadrature amplitude modulation (QAM) and pulse-position modulation (PPM). The dual-modulation strategy leverages the high spectral efficiency of [...] Read more.

This paper investigates an artificial intelligence (AI)-enhanced visible light communication (VLC) system for body area networks (BANs) based on a hybrid modulation framework that jointly employs quadrature amplitude modulation (QAM) and pulse-position modulation (PPM). The dual-modulation strategy leverages the high spectral efficiency of QAM together with the robustness of PPM to light-emitting diode (LED) nonlinearity and timing distortions, enabling simultaneous high-rate and reliable communication, two essential requirements in BAN applications. To address the nonlinear response of light-emitting diodes and the variability in indoor optical channels, the system integrates classical predistortion techniques with a deep learning equalizer combining convolutional neural network (CNN)–transformer layers. This hybrid model captures both local and long-range distortion patterns, improving symbol reconstruction for both modulation branches. The study further examines pilot-assisted equalization and adaptive bit loading, showing that these strategies strengthen link robustness under diverse channel conditions while enhancing spectral efficiency. The proposed architecture demonstrates that combining dual modulation with AI-driven equalization and adaptive transmission strategies leads to a more resilient and efficient VLC system, well-suited for the dynamic constraints of wearable and body-centric communication environments. Full article

(This article belongs to the Special Issue AI-Enabled Sensing Technology for Smart Healthcare and Precision Diagnosis)

► Show Figures

Figure 1

14 pages, 1628 KB

Open AccessArticle

Assessment of the Effect of Four Kneeling Chair Angle Combinations on Muscle Activity and Perceived Discomfort

by Xiaoxiao Lei, Jutao Li, Jingchen Cong, Mengyang Ren and Zhongxia Xiang

Sensors 2026, 26(3), 970; https://doi.org/10.3390/s26030970 (registering DOI) - 2 Feb 2026

Abstract

The kneeling chair has an advantage over the traditional chair in that it promotes lumbar lordosis, while findings regarding muscle activity and subjective (dis)comfort evaluation between the two are inconsistent. Furthermore, there is a lack of studies focusing on the angle combinations of [...] Read more.

The kneeling chair has an advantage over the traditional chair in that it promotes lumbar lordosis, while findings regarding muscle activity and subjective (dis)comfort evaluation between the two are inconsistent. Furthermore, there is a lack of studies focusing on the angle combinations of the kneeling chair. This study investigated an unsupported traditional sitting configuration and four unsupported kneeling configurations with different angle combinations through measurements of surface electromyography (EMG) signals, body part discomfort (BPD) scores, and seat configuration evaluation scores. A significant decrease in lumbar erector spinae (LES) muscle activity and perceived discomfort was observed in the kneeling configuration compared with the results for the traditional sitting configuration. Among the four angle combinations, the optimal arrangement was identified, which resulted in significantly less LES muscle activity and perceived discomfort. Our findings provide guidance for the design and future studies of the kneeling chair. Full article

(This article belongs to the Special Issue Human-Centric Sensing and Technologies in Industry 5.0)

► Show Figures

Figure 1

23 pages, 14603 KB

Open AccessArticle

A Multi-Modal Decision-Level Fusion Framework for Hypervelocity Impact Damage Classification in Spacecraft

by Kuo Zhang, Chun Yin, Pengju Kuang, Xuegang Huang and Xiao Peng

Sensors 2026, 26(3), 969; https://doi.org/10.3390/s26030969 (registering DOI) - 2 Feb 2026

Abstract

During on-orbit service, spacecraft are subjected to hypervelocity impacts (HVIs) from micrometeoroids and space debris, causing diverse damage types that challenge structural health assessment. Unimodal approaches often struggle with similar damage patterns due to mechanical noise and imaging distance variations. To overcome these [...] Read more.

During on-orbit service, spacecraft are subjected to hypervelocity impacts (HVIs) from micrometeoroids and space debris, causing diverse damage types that challenge structural health assessment. Unimodal approaches often struggle with similar damage patterns due to mechanical noise and imaging distance variations. To overcome these physical limitations, this study proposes a physics-informed multimodal fusion framework. Innovatively, we integrate a distance-aware infrared enhancement strategy with vibration spectral subtraction to align heterogeneous data qualities while employing a dual-stream ResNet coupled with Dempster–Shafer (D-S) evidence theory to rigorously resolve inter-modal conflicts at the decision level. Experimental results demonstrate that the proposed strategy achieves a mean accuracy of 99.01%, significantly outperforming unimodal baselines (92.96% and 97.11%). Notably, the fusion mechanism corrects specific misclassifications in micro-cracks and perforation, ensuring a precision exceeding 96.9% across all categories with high stability (standard deviation 0.74%). These findings validate the efficacy of multimodal fusion for precise on-orbit damage assessment, offering a robust solution for spacecraft structural health monitoring. Full article

(This article belongs to the Topic Advances in Non-Destructive Testing Methods, 3rd Edition)

19 pages, 6175 KB

Open AccessArticle

Dynamic Feature Fusion for Sparse Radar Detection: Motion-Centric BEV Learning with Adaptive Task Balancing

by Yixun Sang, Junjie Cui, Yaoguang Sun, Fan Zhang, Yanting Li and Guoqiang Shi

Sensors 2026, 26(3), 968; https://doi.org/10.3390/s26030968 (registering DOI) - 2 Feb 2026

Abstract

This paper proposes a novel motion-aware framework to address key challenges in 4D millimeter-wave radar detection for autonomous driving. While existing methods struggle with sparse point clouds and dynamic object characterization, our approach introduces three key innovations: (1) A Bird’s Eye View (BEV) [...] Read more.

This paper proposes a novel motion-aware framework to address key challenges in 4D millimeter-wave radar detection for autonomous driving. While existing methods struggle with sparse point clouds and dynamic object characterization, our approach introduces three key innovations: (1) A Bird’s Eye View (BEV) fusion network incorporating velocity vector decomposition and dynamic gating mechanisms, effectively encoding motion patterns through independent XY-component convolutions; (2) a gradient-aware multi-task balancing scheme using learnable uncertainty parameters and dynamic weight normalization, resolving optimization conflicts between classification and regression tasks; and (3) a two-phase progressive training strategy combining multi-frame pre-training with sparse single-frame refinement. Evaluated on the TJ4D benchmark, our method achieves 33.25% mean Average Precision (mAP)_3D with minimal parameter overhead (1.73 M), showing particular superiority in pedestrian detection (+4.16% AP) while maintaining real-time performance (24.4 FPS on embedded platforms). Comprehensive ablation studies validate each component’s contribution, with thermal map visualization demonstrating effective motion pattern learning. This work advances robust perception under challenging conditions through principled motion modeling and efficient architecture design. Full article

(This article belongs to the Section Radar Sensors)

► Show Figures

Figure 1

20 pages, 1314 KB

Open AccessArticle

Nash Bargaining-Based Hybrid MAC Protocol for Wireless Body Area Networks

by Haoru Su, Jiale Yang, Rong Li and Jian He

Sensors 2026, 26(3), 967; https://doi.org/10.3390/s26030967 (registering DOI) - 2 Feb 2026

Abstract

Wireless Body Area Network (WBAN) is an emerging medical health monitoring technology. However, WBANs encounter critical challenges in balancing reliability, energy efficiency, and Quality of Service (QoS) requirements for life-critical medical data. The design of its Medium Access Control (MAC) protocol has challenges [...] Read more.

Wireless Body Area Network (WBAN) is an emerging medical health monitoring technology. However, WBANs encounter critical challenges in balancing reliability, energy efficiency, and Quality of Service (QoS) requirements for life-critical medical data. The design of its Medium Access Control (MAC) protocol has challenges since dynamic body-shadowing effects and heterogeneous traffic patterns. In this paper, we propose the Nash Bargaining Rate-optimization MAC (NBR-MAC), a hybrid MAC protocol that integrates TDMA-based Guaranteed Time Slots (GTS) with CSMA/CA-based contention access. Unlike traditional schemes, we model the rate allocation as an Asymmetric Nash Bargaining Game, introducing a rigorous disagreement point to guarantee minimum service for critical nodes. The utility function is normalized to resolve dimensional inconsistencies, incorporating sensor priority, buffer status, and channel quality. The Nash Bargaining solution is derived after proving convexity and verifying the axioms. Superframe time slots are allocated based on sensor data priority. Simulation results demonstrate that the proposed protocol enhances transmission success ratio and throughput while reducing packet age and energy consumption under different load conditions. Full article

(This article belongs to the Special Issue Body Area Networks: Intelligence, Sensing and Communication)

► Show Figures

Figure 1

23 pages, 4154 KB

Open AccessArticle

Feasibility Domain Construction and Characterization Method for Intelligent Underground Mining Equipment Integrating ORB-SLAM3 and Depth Vision

by Siya Sun, Xiaotong Han, Hongwei Ma, Haining Yuan, Sirui Mao, Chuanwei Wang, Kexiang Ma, Yifeng Guo and Hao Su

Sensors 2026, 26(3), 966; https://doi.org/10.3390/s26030966 (registering DOI) - 2 Feb 2026

Abstract

To address the limited environmental perception capability and the difficulty of achieving consistent and efficient representation of the workspace feasible domain caused by high dust concentration, uneven illumination, and enclosed spaces in underground coal mines, this paper proposes a digital spatial construction and [...] Read more.

To address the limited environmental perception capability and the difficulty of achieving consistent and efficient representation of the workspace feasible domain caused by high dust concentration, uneven illumination, and enclosed spaces in underground coal mines, this paper proposes a digital spatial construction and representation method for underground environments by integrating RGB-D depth vision with ORB-SLAM3. First, a ChArUco calibration board with embedded ArUco markers is adopted to perform high-precision calibration of the RGB-D camera, improving the reliability of geometric parameters under weak-texture and non-uniform lighting conditions. On this basis, a “dense–sparse cooperative” OAK-DenseMapper Pro module is further developed; the module improves point-cloud generation using a mathematical projection model, and combines enhanced stereo matching with multi-stage depth filtering to achieve high-quality dense point-cloud reconstruction from RGB-D observations. The dense point cloud is then converted into a probabilistic octree occupancy map, where voxel-wise incremental updates are performed for observed space while unknown regions are retained, enabling a memory-efficient and scalable 3D feasible-space representation. Experiments are conducted in multiple representative coal-mine tunnel scenarios; compared with the original ORB-SLAM3, the number of points in dense mapping increases by approximately 38% on average; in trajectory evaluation on the TUM dataset, the root mean square error, mean error, and median error of the absolute pose error are reduced by 7.7%, 7.1%, and 10%, respectively; after converting the dense point cloud to an octree, the map memory footprint is only about 0.5% of the original point cloud, with a single conversion time of approximately 0.75 s. The experimental results demonstrate that, while ensuring accuracy, the proposed method achieves real-time, efficient, and consistent representation of the 3D feasible domain in complex underground environments, providing a reliable digital spatial foundation for path planning, safe obstacle avoidance, and autonomous operation. Full article

(This article belongs to the Special Issue Perception and Control Technology for Intelligent Autonomous Unmanned Systems)

32 pages, 14050 KB

Open AccessArticle

MURM-A*: An Improved A* Within Comprehensive Path-Planning Scheme for Cellular-Connected Multi-UAVs Based on Radio Map and Complex Network

by Yanming Chai, Qibin He, Yapeng Wang, Xu Yang and Sio-Kei Im

Sensors 2026, 26(3), 965; https://doi.org/10.3390/s26030965 (registering DOI) - 2 Feb 2026

Abstract

For the purpose of fulfilling the dual requirements of persistent cellular network connectivity and flight safety for cellular-connected Unmanned Aerial Vehicles (UAVs) operating in dense urban airspace, this paper presents an A*-oriented comprehensive path-planning scheme for multiple connected UAVs that integrates a radio [...] Read more.

For the purpose of fulfilling the dual requirements of persistent cellular network connectivity and flight safety for cellular-connected Unmanned Aerial Vehicles (UAVs) operating in dense urban airspace, this paper presents an A*-oriented comprehensive path-planning scheme for multiple connected UAVs that integrates a radio map and complex network. Existing research often lacks rigorous processing of environmental map data, while the traditional A* algorithm struggles to simultaneously handle constraints such as obstacle avoidance, flight maneuverability, and multi-UAV path conflicts. To overcome these limitations, this study first constructs a path-planning model based on complex-network theory using environmental data and the radio map, clarifying the separation of responsibilities between environment representation and algorithmic search. On this basis, we proposed an improved A* algorithm for multi-UAV scenarios termed MURM-A*. Simulation results demonstrate that the proposed algorithm effectively avoids collisions with obstacles, adheres to UAV flight dynamics, and prevents spatial conflicts between multi-UAV paths, while achieving a joint optimization between path efficiency and radio quality. In terms of performance comparison, the proposed algorithm shows a marginal difference but ensures operational validity compared to traditional A*, exhibits a slightly increase in flight time but achieves a substantial reduction in radio-outage time compared to the Deep Reinforcement Learning (DRL) method. Furthermore, employing the path-planning model enables the algorithm to more accurately identify environmental information compared to directly using raw environmental maps. The modeling time is also notably shorter than the training time required for DRL methods. This study provides a well-structured and extensible systematic framework for reliable path planning of multiple cellular-connected UAVs in complex radio environments. Full article

(This article belongs to the Special Issue Recent Advances in UAV Communications and Networks)

43 pages, 8604 KB

Open AccessArticle

Bibliometric and Visualization Analysis of Path Planning and Trajectory Tracking Research for Autonomous Vehicles from 2000 to 2025

by Bo Niu and Roman Y. Dobretsov

Sensors 2026, 26(3), 964; https://doi.org/10.3390/s26030964 (registering DOI) - 2 Feb 2026

Abstract

With the rapid development of the automotive industry, autonomous driving has attracted growing research interest, among which path planning and trajectory tracking play a central role. To better understand the evolution, current status, and future directions of this field, this study conducts a [...] Read more.

With the rapid development of the automotive industry, autonomous driving has attracted growing research interest, among which path planning and trajectory tracking play a central role. To better understand the evolution, current status, and future directions of this field, this study conducts a comprehensive bibliometric analysis combined with latent Dirichlet allocation (LDA) topic modeling on publications related to autonomous vehicle path planning and trajectory tracking indexed in the Web of Science database. Multiple dimensions are examined, including publication trends, highly cited authors, leading institutions, research domains, and keyword co-occurrence patterns. The results reveal a sustained growth in research output, with trajectory planning, path optimization, trajectory tracking, and model predictive control (MPC) emerging as dominant topics, alongside a notable rise in learning-based approaches. In particular, reinforcement learning (RL) and deep reinforcement learning (DRL) have become increasingly prominent in complex decision-making and tracking control scenarios. The analysis further identifies core contributors and institutions, highlighting the leading roles of China and the United States in this research area. Overall, the findings provide a systematic overview of the knowledge structure and evolving research trends, offering valuable insights into key opportunities and challenges and supporting future research toward safer and more intelligent autonomous driving systems. Full article

(This article belongs to the Topic Advances in Autonomous Vehicles, Automation, and Robotics)

► Show Figures

Figure 1

26 pages, 1369 KB

Open AccessArticle

Progressive Attention-Enhanced EfficientNet–UNet for Robust Water-Body Mapping from Satellite Imagery

by Mohamed Ezz, Alaa S. Alaerjan, Ayman Mohamed Mostafa, Noureldin Laban and Hind H. Zeyada

Sensors 2026, 26(3), 963; https://doi.org/10.3390/s26030963 (registering DOI) - 2 Feb 2026

Abstract

The sustainable management of water resources and the development of climate-resilient infrastructure depend on the precise identification of water bodies in satellite imagery. This paper presents a novel deep learning architecture that integrates a convolutional block attention module (CBAM) into a modified EfficientNet–UNet [...] Read more.

The sustainable management of water resources and the development of climate-resilient infrastructure depend on the precise identification of water bodies in satellite imagery. This paper presents a novel deep learning architecture that integrates a convolutional block attention module (CBAM) into a modified EfficientNet–UNet backbone. This integration allows the model to prioritize informative features and spatial areas. The model robustness is ensured through a rigorous training regimen featuring five-fold cross-validation, dynamic test-time augmentation, and optimization with the Lovász loss function. The final model achieved the following values on the independent test set: precision = 90.67%, sensitivity = 86.96%, specificity = 96.18%, accuracy = 93.42%, Dice score = 88.78%, and IoU = 79.82%. These results demonstrate improvement over conventional segmentation pipelines, highlighting the effectiveness of attention mechanisms in extracting complex water-body patterns and boundaries. The key contributions of this paper include the following: (i) adaptation of CBAM within a UNet-style architecture tailored for remote sensing water-body extraction; (ii) a rigorous ablation study detailing the incremental impact of decoder complexity, attention integration, and loss function choice; and (iii) validation of a high-fidelity, computationally efficient model ready for deployment in large-scale water-resource and ecosystem-monitoring systems. Our findings show that attention-guided segmentation networks provide a robust pathway toward high-fidelity and sustainable water-body mapping. Full article

(This article belongs to the Special Issue Sensor-Based Geoinformatics Solutions for Sustainable Agricultural and Water/Forest Resources Management)

20 pages, 2482 KB

Open AccessArticle

Compression-Efficient Feature Extraction Method for a CMOS Image Sensor

by Keiichiro Kuroda, Yu Osuka, Ryoya Iegaki, Ryuichi Ujiie, Hideki Shima, Kota Yoshida and Shunsuke Okura

Sensors 2026, 26(3), 962; https://doi.org/10.3390/s26030962 (registering DOI) - 2 Feb 2026

Abstract

To address the power constraints of the emerging Internet of Things (IoT) era, we propose a compression-efficient feature extraction method for a CMOS image sensor that can extract binary feature data. This sensor outputs six-channel binary feature data, comprising three channels of binarized [...] Read more.

To address the power constraints of the emerging Internet of Things (IoT) era, we propose a compression-efficient feature extraction method for a CMOS image sensor that can extract binary feature data. This sensor outputs six-channel binary feature data, comprising three channels of binarized luminance signals and three channels of horizontal edge signals, compressed via a run length encoding (RLE) method. This approach significantly reduces data transmission volume while maintaining image recognition accuracy. The simulation results obtained using a YOLOv7-based model designed for edge GPUs demonstrate that our approach achieves a large object recognition accuracy (

{AP}_{L} 50

) of 60.7% on the COCO dataset while reducing the data size by 99.2% relative to conventional 8-bit RGB color images. Furthermore, the image classification results using MobileNetV3 tailored for mobile devices on the Visual Wake Words (VWW) dataset show that our approach reduces data size by 99.0% relative to conventional 8-bit RGB color images and achieves an image classification accuracy of 89.4%. These results are superior to the conventional trade-off between recognition accuracy and data size, thereby enabling the realization of low-power image recognition systems. Full article

(This article belongs to the Special Issue Advanced Signal and Image Processing Techniques for Sensor Applications)

► Show Figures

Figure 1

17 pages, 1038 KB

Open AccessArticle

A Robust Complex α-Sigmoid Affine Projection Algorithm Under Non-Gaussian Noise

by Yaowei Guo, Bin Guo and Guobing Qian

Sensors 2026, 26(3), 961; https://doi.org/10.3390/s26030961 (registering DOI) - 2 Feb 2026

Abstract

To address the performance degradation of traditional adaptive filtering algorithms in environments with correlated input signals and non-Gaussian noise, this paper proposes a complex-valued affine projection algorithm based on the

α

-Sigmoid cost function (

α

-CSAP). The algorithm leverages the nonlinear characteristics [...] Read more.

To address the performance degradation of traditional adaptive filtering algorithms in environments with correlated input signals and non-Gaussian noise, this paper proposes a complex-valued affine projection algorithm based on the

α

-Sigmoid cost function (

α

-CSAP). The algorithm leverages the nonlinear characteristics of the

α

-Sigmoid function and implicitly achieves variable step-size updates by introducing a normalization factor, which effectively suppresses impulsive noise interference and avoids matrix inversion, thereby reducing computational complexity. Theoretical analysis derives the steady-state mean square deviation (MSD) expression for the algorithm. Simulation results demonstrate that the proposed

α

-CSAP algorithm exhibits superior performance compared to traditional complex adaptive filtering algorithms in both system identification and beamforming application scenarios. Full article

(This article belongs to the Special Issue Radar Target Detection, Imaging and Recognition)

► Show Figures

Figure 1

16 pages, 7103 KB

Open AccessArticle

Fluid Pressure Sensing Strategy Suitable for Swallowing Soft Gripper

by Mingge Li, Wenxi Zhang, Quan Liu and Zhongjun Yin

Sensors 2026, 26(3), 960; https://doi.org/10.3390/s26030960 (registering DOI) - 2 Feb 2026

Abstract

Soft grippers exhibit excellent adaptability in handling objects of various shapes. However, due to the large deformation and high compliance of their constituent materials, the integration of sensing capabilities has long been a major research challenge. Based on the swallowing-type soft gripper proposed [...] Read more.

Soft grippers exhibit excellent adaptability in handling objects of various shapes. However, due to the large deformation and high compliance of their constituent materials, the integration of sensing capabilities has long been a major research challenge. Based on the swallowing-type soft gripper proposed in previous work, this study explores the gripper’s capability to perceive object information by leveraging the characteristic that the sealed cavity undergoes volume change due to compression by the object during swallowing, thereby altering the pressure of the internal fluid medium. By establishing the geometric configuration of the sealed cavity composed of elastic membranes, the volume-pressure variation sensing model during the object swallowing process was derived. The performance of this sensing method was tested, and the application of the fluid pressure sensing strategy in closed-loop control was demonstrated, including the classification of objects by shape and sorting by size. This work provides a solution for the object shape-adaptive swallowing-type soft gripper to achieve sensory grasping functionality. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

17 pages, 4308 KB

Open AccessArticle

AGL-UNet: Adaptive Global–Local Modulated U-Net for Multitask Sea Ice Mapping

by Deyang Chen and Fuqiang Zheng

Sensors 2026, 26(3), 959; https://doi.org/10.3390/s26030959 (registering DOI) - 2 Feb 2026

Abstract

The increasing demand for Arctic route planning, climate change studies, and the growing volume of satellite sensor data have made automated sea ice mapping an essential task. In this study, we propose a multi-task sea ice mapping framework based on the U-Net architecture, [...] Read more.

The increasing demand for Arctic route planning, climate change studies, and the growing volume of satellite sensor data have made automated sea ice mapping an essential task. In this study, we propose a multi-task sea ice mapping framework based on the U-Net architecture, which supports multi-sensor data integration and automatically modulates global and local features. The model consists of ARC blocks for enhanced multi-sensor feature fusion, a GLCM block for non-local and local feature modulation, and an adaptive loss weighting strategy to balance multi-task training. The proposed method is evaluated on the AI4Arctic RTT dataset, which includes multi-sensor inputs and ice chart-derived labels. Compared with the best-performing method in the AutoIce Challenge, the proposed approach achieves a 1.33% improvement in the combined score. In addition, the F1 scores for stage of development (SOD) and floe size (FLOE) increase by 2.85% and 3.44%, respectively. Although the

R^{2}

score for SIC shows a slight decrease of 1.25%, this behavior is consistent with the practical trade-offs commonly observed in multi-task optimization. Ablation studies further demonstrate the effectiveness of the proposed blocks and the multi-task adaptive weighting strategy, confirming their potential for handling multi-sensor data and supporting ocean environment monitoring. Full article

(This article belongs to the Special Issue Sensor Technologies for Ocean Environments: Impact Assessment, Monitoring and Protection—Second Edition)

► Show Figures

Figure 1

21 pages, 4327 KB

Open AccessArticle

Engineering-Oriented Ultrasonic Decoding: An End-to-End Deep Learning Framework for Metal Grain Size Distribution Characterization

by Le Dai, Shiyuan Zhou, Yuhan Cheng, Lin Wang, Yuxuan Zhang and Heng Zhi

Sensors 2026, 26(3), 958; https://doi.org/10.3390/s26030958 (registering DOI) - 2 Feb 2026

Abstract

Grain size is critical for metallic material performance, yet conventional ultrasonic methods rely on strong model assumptions and exhibit limited adaptability. We propose a deep learning architecture that uses multimodal ultrasonic features with spatial coding to predict the grain size distribution of GH4099. [...] Read more.

Grain size is critical for metallic material performance, yet conventional ultrasonic methods rely on strong model assumptions and exhibit limited adaptability. We propose a deep learning architecture that uses multimodal ultrasonic features with spatial coding to predict the grain size distribution of GH4099. A-scan signals from C-scan measurements are converted to time–frequency representations and fed to an encoder–decoder model that combines a dual convolutional compression network with a fully connected decoder. A thickness-encoding branch enables feature decoupling under physical constraints, and an elliptic spatial fusion strategy refines predictions. Experiments show mean and standard deviation MAEs of 1.08 and 0.84 μm, respectively, with a KL divergence of 0.0031, outperforming attenuation- and velocity-based methods. Input-specificity experiments further indicate that transfer learning calibration quickly restores performance under new conditions. These results demonstrate a practical path for integrating deep learning with ultrasonic inspection for accurate, adaptable grain-size characterization. Full article

(This article belongs to the Special Issue Ultrasonic Sensors and Ultrasonic Signal Processing)

► Show Figures

Graphical abstract

Journal Description

Sensors

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI