Sensors

26 pages, 10963 KB

Open AccessArticle

Noise-Resilient Whitened Domain Adaptation for Intelligent Mechanical Fault Diagnosis Under Non-Stationary Sensor Signals

by Qinyue Chen and Yunxin Xie

Sensors 2026, 26(10), 3222; https://doi.org/10.3390/s26103222 - 19 May 2026

Abstract

Intelligent mechanical fault diagnosis plays a key role in maintaining rotating machinery. Although data-driven unsupervised domain adaptation methods have achieved considerable progress, their industrial applications are often restricted by low-quality sensor data. Non-stationary vibration signals and background noise easily corrupt target pseudo-labels, while [...] Read more.

Intelligent mechanical fault diagnosis plays a key role in maintaining rotating machinery. Although data-driven unsupervised domain adaptation methods have achieved considerable progress, their industrial applications are often restricted by low-quality sensor data. Non-stationary vibration signals and background noise easily corrupt target pseudo-labels, while conventional methods focusing on global statistical matching usually neglect local structures, leading to confirmation bias under dynamic loads. To improve diagnostic reliability, we propose a Noise-Resilient Whitened Domain Adaptation (NRWDA) framework. To handle covariance fluctuations caused by changing working conditions, a Lipschitz-bounded Temporal Whitening (LTW) module is designed as a low-pass filter. An Entropy-guided Prototype Truncation (EPT) mechanism is adopted to discard ambiguous labels and better calibrate semantic centers. In addition, a Dispersion-Adaptive Contrastive Sharpening (DACS) strategy is introduced to dynamically adjust the contrastive temperature based on predictive dispersion, thus tightening decision boundaries. The proposed method is evaluated on CWRU, PU, and MFPT datasets. The PU dataset, featuring fluctuating loads and non-stationary signals, poses a strict test, yet our model maintains its stability even at a 0 dB SNR—a condition where standard approaches usually break down. During the

P 0 \to P 3

transfer task involving substantial radial force variations, NRWDA secures a 72.36% accuracy and surpasses established baselines. These findings confirm that our technique successfully isolates dependable diagnostic features from corrupted sensor measurements within actual industrial settings. Full article

(This article belongs to the Special Issue Intelligent Sensors for Structural Health Monitoring and Mechanical Fault Diagnosis: 2nd Edition)

29 pages, 11849 KB

Open AccessArticle

Hi-RAGrasp: A Human-in-the-Loop Experience-Augmented Method for Task-Oriented Grasping

by Yaxin Liu, Yue Hu, Yan Liu and Ming Zhong

Sensors 2026, 26(10), 3221; https://doi.org/10.3390/s26103221 - 19 May 2026

Abstract

With the growing demand for assistive robots in aging societies, task-oriented grasping in household environments has become increasingly important. Compared with structured industrial settings, household scenarios are characterized by diverse objects, unstructured layouts, and strong variability in task semantics. However, traditional methods focus [...] Read more.

With the growing demand for assistive robots in aging societies, task-oriented grasping in household environments has become increasingly important. Compared with structured industrial settings, household scenarios are characterized by diverse objects, unstructured layouts, and strong variability in task semantics. However, traditional methods focus on geometric stability and fail to capture task-relevant semantic constraints on manipulation regions, while existing approaches suffer from unstable reasoning and lack effective mechanisms for incorporating human intervention into the reasoning process. To address these challenges, we propose Hi-RAGrasp, a task-oriented grasping framework that integrates progressive multi-stage reasoning, Human-in-the-Loop (HITL) interaction, and Retrieval-Augmented Generation (RAG). A coarse-to-fine pipeline progressively refines predictions from object-level localization to part-level grounding, enabling robust mapping from human instructions to fine-grained task-relevant regions. Meanwhile, a HITL correction mechanism and a structured human experience database are introduced and combined with RAG to form a unified paradigm that aligns with prior experience when available and falls back to reasoning otherwise, enabling experience reuse and future experience accumulation without retraining. In addition, a Geometric Heuristic Segmentation (GHS) method is proposed to improve task-relevant region localization for textureless objects. Experiments show that our method achieves a segmentation success rate of 77.73% on the evaluation dataset and a grasp success rate of 75% in real-world scenarios, significantly outperforming existing methods and demonstrating strong effectiveness and practicality in open environments. Full article

(This article belongs to the Special Issue Intelligent Sensing for Robotic Control and Visual Perception)

► Show Figures

Graphical abstract

20 pages, 40234 KB

Open AccessArticle

Development of an Instrumented Climbing Hold with an Embedded Six-Axis Force Sensor for Speed Climbing

by Akihiro Kawamura, Takumi Shintani, Shimpei Aihara and Ryo Kurazume

Sensors 2026, 26(10), 3220; https://doi.org/10.3390/s26103220 - 19 May 2026

Abstract

Understanding the interaction forces between climbers and climbing holds is important for motion analysis and performance evaluation in sport climbing. In particular, force measurement during speed climbing can provide valuable insights into explosive movements and athlete performance. However, many existing measurement systems require [...] Read more.

Understanding the interaction forces between climbers and climbing holds is important for motion analysis and performance evaluation in sport climbing. In particular, force measurement during speed climbing can provide valuable insights into explosive movements and athlete performance. However, many existing measurement systems require modifications to the climbing wall structure or sensors installed behind the wall, which limits their applicability to existing speed climbing facilities. This study proposes a wireless instrumented climbing hold for speed climbing that enables force-related measurement without modifying the wall structure. The proposed system integrates a six-axis force sensor, a microcomputer, a wireless communication module, and a battery inside the climbing hold. This self-contained configuration allows the hold to wirelessly transmit force and moment data during climbing while maintaining compatibility with standard speed climbing walls and competition environments. In addition, the system enables an estimation of the point of force application on the hold surface by combining measured force and moment data with the three-dimensional hold geometry. Experimental evaluations were conducted to verify the feasibility and performance of the system. External load tests using a digital force gauge confirmed that the embedded sensor can measure static loads and respond to rapidly changing loads with sufficient temporal responsiveness, and the estimated point of force application corresponded closely to the actual loading point. Furthermore, measurements on an actual speed climbing wall demonstrated that the proposed system can successfully capture interaction forces during climbing movements. These results indicate that the proposed system is a practical tool for force-based motion analysis in speed climbing. Full article

(This article belongs to the Special Issue Innovative Sensing Methods for Motion and Behavior Analysis)

22 pages, 3176 KB

Open AccessArticle

Evolutionary Digital Twin for Oil and Gas Pipelines: A Cognitive Multi-Agent Framework with Continuous Feedback Learning

by Ning Shi, Zixuan Li, Qiujuan Li, Jing Zhang, Liangliang Li, Qiaofei Sun, Sijia Liu and Zheng Wang

Sensors 2026, 26(10), 3219; https://doi.org/10.3390/s26103219 - 19 May 2026

Abstract

The structural integrity and risk management of long-distance oil and gas pipelines are critically challenged by multi-source data heterogeneity, complex multi-physics degradation mechanisms, and the dynamic nature of operational environments. Traditional monolithic artificial intelligence models struggle with cross-domain knowledge fusion and often suffer [...] Read more.

The structural integrity and risk management of long-distance oil and gas pipelines are critically challenged by multi-source data heterogeneity, complex multi-physics degradation mechanisms, and the dynamic nature of operational environments. Traditional monolithic artificial intelligence models struggle with cross-domain knowledge fusion and often suffer from historical context forgetting over decades-long infrastructure lifecycles. To address these bottlenecks, this paper proposes an evolutionary digital twin framework driven by a collaborative architecture between small specialized models and a large general model. Specifically, the framework encapsulates physics-informed models (e.g., corrosion prediction and geohazard evaluation) as domain expert agents to guarantee rigorous numerical computation at the edge, keeping sensitive operational data strictly localized. To synthesize conflicting localized risks, a locally deployed, privacy-preserving large language model acts as a central cognitive hub. This hub utilizes external knowledge retrieval and structured reasoning to formulate transparent, multi-objective intervention strategies. Furthermore, a continuous feedback learning mechanism is introduced to capture tacit expert knowledge. By formalizing human operational interventions into historical memory and employing parameter stabilization techniques, the system dynamically updates its knowledge base while effectively mitigating catastrophic forgetting. Ultimately, the proposed framework provides a reliable and privacy-compliant methodology, significantly enhancing the interpretability and predictive foresight of pipeline integrity management. Full article

(This article belongs to the Section Industrial Sensors)

► Show Figures

Figure 1

31 pages, 637 KB

Open AccessArticle

A General Tensorial Formulation of Acoustoelasticity and Its Representation in Cylindrical Coordinates

by Yongjiang Ma, Chunguang Xu, Shuangxu Yang and Changhong Chen

Sensors 2026, 26(10), 3218; https://doi.org/10.3390/s26103218 - 19 May 2026

Abstract

Acoustoelasticity provides the physical sensing principle for ultrasonic stress measurement. However, most existing formulations are restricted to isotropic media, simple stress conditions, and Cartesian coordinate systems, which limits their applicability in practical sensing scenarios involving curved and anisotropic structures. In this work, a [...] Read more.

Acoustoelasticity provides the physical sensing principle for ultrasonic stress measurement. However, most existing formulations are restricted to isotropic media, simple stress conditions, and Cartesian coordinate systems, which limits their applicability in practical sensing scenarios involving curved and anisotropic structures. In this work, a general tensorial formulation of acoustoelasticity is developed based on the theory of incremental deformation. The proposed governing equations describe the motion of incremental displacement with explicit dependence on initial stress or strain, and are applicable to materials with arbitrary symmetry and general initial stress states. Owing to its coordinate-independent tensorial nature, the formulation can be expressed in any curvilinear coordinate system. To facilitate practical ultrasonic sensing applications, the general equations are further expanded in a cylindrical coordinate system for orthotropic materials. This enables the analysis of elastic wave propagation in curved structures such as pipelines, pressure vessels, and boreholes. The formulation establishes a direct relationship between initial stress and effective elastic properties, which determine wave velocities measurable by ultrasonic sensors, such as time-of-flight and phase velocity. The proposed approach provides a rigorous theoretical foundation for ultrasonic stress sensing and nondestructive testing, particularly for curved and anisotropic structures, and supports improved accuracy in sensor-based stress evaluation. Full article

(This article belongs to the Special Issue Acoustic Sensing for Condition Monitoring)

24 pages, 3444 KB

Open AccessArticle

A Supervised Contrastive Variational Autoencoder with Probabilistic Latent Alignment for Cross-Domain EEG Emotion Recognition

by Linna Wu, Yong Yang, Wenhao Wang, Yuanlun Xie, Nan Zhou and Kaibo Shi

Sensors 2026, 26(10), 3217; https://doi.org/10.3390/s26103217 - 19 May 2026

Abstract

Cross-domain emotion recognition based on electroencephalogram (EEG) is a challenging task, as EEG signals collected from different subjects or at different moments exhibit significant differences in distribution. How to enable deep learning model to learn the common feature space and reduce the distribution [...] Read more.

Cross-domain emotion recognition based on electroencephalogram (EEG) is a challenging task, as EEG signals collected from different subjects or at different moments exhibit significant differences in distribution. How to enable deep learning model to learn the common feature space and reduce the distribution differences between the source and target domains is an important research direction. For this problem, we propose a Supervised Contrastive Variational AutoEncoder Network (SCVAE-Net), which possesses enhanced abilities for extracting consistent features across source and target domains, thereby improving cross-domain EEG emotion recognition performance. Specifically, this method utilizes the reconstruction mechanism and latent space probabilization of VAE to obtain intermediate features that are more consistent and transferable. Furthermore, the maximum mean discrepancy loss is employed to further reduce the distribution discrepancy of these features. To alleviate the degradation of discriminative ability during domain alignment, we introduce multi-view supervised contrastive learning in multi-source domains to enhance the intra-class consistency and inter-class separability of latent features. Under the cross-subject and cross-session settings, SCVAE-Net achieves accuracies of 95.01%/96.84% on SEED and 74.94%/79.44% on SEED-IV, respectively. These experimental results demonstrate the effectiveness of the proposed method in cross-domain EEG emotion recognition. Full article

(This article belongs to the Section Biomedical Sensors)

20 pages, 2924 KB

Open AccessArticle

Fabrication and Enhancement of the Gas Sensing Characteristics of Silicon Micropillar NH₃ Sensors Based on MOF-808/rGO Nanocomposites at Room Temperature

by Haoyue Wang, Shaolun Feng, Zhiqiang Fan and Sai Chen

Sensors 2026, 26(10), 3216; https://doi.org/10.3390/s26103216 - 19 May 2026

Abstract

This study develops high-performance ammonia sensors based on composites of metal-organic frameworks (MOF-808 and MOF-818) with reduced graphene oxide (rGO). Two sensor architectures were fabricated: interdigital electrodes and silicon micropillar arrays. The MOF-808/rGO composite demonstrated superior sensing performance for 40 ppm NH₃ [...] Read more.

This study develops high-performance ammonia sensors based on composites of metal-organic frameworks (MOF-808 and MOF-818) with reduced graphene oxide (rGO). Two sensor architectures were fabricated: interdigital electrodes and silicon micropillar arrays. The MOF-808/rGO composite demonstrated superior sensing performance for 40 ppm NH₃ at room temperature, with faster response kinetics and higher sensitivity compared to pristine rGO and MOF-818/rGO. Silicon micropillar array sensors showed enhanced performance through optimized periodic arrangements, while oxygen plasma surface modification improved both sensor types. Comprehensive testing confirmed that the MOF-808/rGO sensor maintains reliable NH₃ detection at concentrations as low as 5 ppm under high humidity conditions, exhibiting excellent stability and selectivity. These findings provide valuable insights for developing advanced gas sensors for environmental monitoring applications. Full article

(This article belongs to the Special Issue Sensor-Based Systems for Environmental Monitoring and Assessment)

► Show Figures

Figure 1

31 pages, 6805 KB

Open AccessArticle

Evaluation Framework for Bruise Detection: Systematic ALS/White-Light Training and Skin-Tone Balancing with Deep Learning

by Kiyarash Aminfar, Katherine Scafide, Janusz Wojtusiak and David Lattanzi

Sensors 2026, 26(10), 3215; https://doi.org/10.3390/s26103215 - 19 May 2026

Abstract

Accurate and consistent forensic bruise assessment is critical in ensuring positive clinical and legal outcomes for victims of violence. In this study, a framework for automated bruise detection is presented that, for the first time, integrates narrowband alternate-light-source (ALS) forensic imaging and ambient [...] Read more.

Accurate and consistent forensic bruise assessment is critical in ensuring positive clinical and legal outcomes for victims of violence. In this study, a framework for automated bruise detection is presented that, for the first time, integrates narrowband alternate-light-source (ALS) forensic imaging and ambient white light imaging. This evaluation framework is designed to address long-standing issues with respect to equitable performance across skin tones and lighting scenarios via a combination of novel model diagnostic strategies. In particular, skin-tone balancing during training and testing, threshold-sensitivity analysis, and embedding-similarity partitioning are employed to quantify the model robustness and deployment trade-offs that arise in forensic image analysis. Models were implemented with ImageNet-pretrained backbones and trained on a unique, multi-annotator full-consensus dataset comprising both white-light and ALS (415 nm and 450 nm) images. The protocol emphasizes three axes of operational relevance: (1) illumination composition in training (W/ALS ratio); (2) subgroup fairness via targeted balancing; and (3) model operating-point selection (confidence and IoU thresholds) informed by confidence-stability metrics and bootstrapped uncertainty estimates. Systematic W/ALS ratio sweeps indicate peak accuracy under ALS-dominant training and declining performance as the proportion of white-light images increases within the training set. Skin-tone balancing reduced failure rates for darker skin tones but increased overprediction in some demographic subgroups. Embedding-similarity and seen/unseen injury analyses demonstrate inflated generalization under image-level partitioning. Ultimately, the findings suggest that future researchers and developers should employ injury-level data partitioning and ensure a weighted balance of ALS images during training. Full article

(This article belongs to the Special Issue AI and Intelligent Sensors for Medical Imaging)

► Show Figures

Figure 1

20 pages, 1983 KB

Open AccessArticle

Machine Anomalous Sound Detection Method Based on Lightweight Temporal Pyramid and ECA-MobileFaceNet

by Yuezhou Wu, Xiaogen Ye, Qiang Fu and Wenan Zhang

Sensors 2026, 26(10), 3214; https://doi.org/10.3390/s26103214 - 19 May 2026

Abstract

To address the challenges of scarce anomaly samples, inadequate modeling of temporal dynamic features, and limited feature selection capability of lightweight models in industrial anomalous sound detection, this paper proposes a method under an unsupervised framework. In the time-domain feature extraction branch, a [...] Read more.

To address the challenges of scarce anomaly samples, inadequate modeling of temporal dynamic features, and limited feature selection capability of lightweight models in industrial anomalous sound detection, this paper proposes a method under an unsupervised framework. In the time-domain feature extraction branch, a Lightweight Temporal Pyramid Module (LTPM) is introduced to enhance the multi-scale temporal modeling capability of TgramNet, capturing both short-term and long-term temporal dependencies. In the classification network, the Efficient Channel Attention (ECA) mechanism is embedded into the bottleneck structure of MobileFaceNet to enable adaptive channel recalibration. Furthermore, three waveform-level data augmentation strategies—noise perturbation, time shifting, and amplitude scaling—are adopted. Experimental results on the DCASE 2020 Task 2 dataset demonstrate that the proposed method achieves competitive performance compared with existing approaches, attaining optimal or highly competitive results across multiple machine types. The minimum Area Under the Curve (mAUC) across different machine IDs, along with ROC curve analysis, verifies the stability and generalization capability of the model. This method offers a promising lightweight approach for industrial anomalous sound detection and condition monitoring applications. Full article

(This article belongs to the Special Issue Fault Diagnosis in Transportation and Industry: Sensors, Methods, and Experimental Applications (2nd Edition))

39 pages, 5039 KB

Open AccessReview

Smart Hydrogel Architectures for Sensors: Narrative Review

by Jūratė Jolanta Petronienė, Tadas Rasimavičius, Darius Viržonis, Andrius Dzedzickis and Vytautas Bučinskas

Sensors 2026, 26(10), 3213; https://doi.org/10.3390/s26103213 - 19 May 2026

Abstract

In sensing technologies, a hydrogel sensor with a specific response to stimuli allows for real-time monitoring of mechanical, thermal, and biochemical signals in wearable and implantable devices. This review discusses the latest advances in hydrogel-based sensors published between 2023 and spring 2026 and [...] Read more.

In sensing technologies, a hydrogel sensor with a specific response to stimuli allows for real-time monitoring of mechanical, thermal, and biochemical signals in wearable and implantable devices. This review discusses the latest advances in hydrogel-based sensors published between 2023 and spring 2026 and the design strategies prevalent in these articles, including the use of polymers, nanomaterial reinforcement, incorporation of ionic solvents, and physical or chemical crosslinking. The influence of supramolecular hydrogels on the quality of sensor parameters, including the impact on mechanical resistance, ionic conductivity, adaptation, and self-healing, is examined. In biomedical engineering, hydrogels, thanks to their biomimetic and programmable properties, enable control of wound repair and soft tissue interfaces. The review concludes by outlining the challenges, opportunities, and advances in the chemistry and mechanics of hydrogels, which may ultimately facilitate the development of multifunctional monitoring systems in healthcare. The abundance of information requires systematic, frequent reviews to accelerate the application of innovative solutions in practice. Carbon nanostructures are a key component that ensures the sensor’s electrical conductivity. 3D printing technology has enabled the creation of individually customizable health monitoring devices. The work also highlights the use of nanodots in sensor production. Full article

(This article belongs to the Special Issue Advanced Sensors for Health and Human Performance Monitoring)

30 pages, 1765 KB

Open AccessReview

Imagined Speech Brain–Computer Interface: A Task-Oriented Review of Neural Decoding

by Haodong Zhang, Wai Ting Siok and Nizhuan Wang

Sensors 2026, 26(10), 3212; https://doi.org/10.3390/s26103212 - 19 May 2026

Abstract

Imagined speech decoding has attracted growing interest in brain–computer interface (BCI) research, as it may enable language-related information to be recovered from non-overt neural activity. Current studies in this area are often treated as a single, unified research problem, despite substantial differences in [...] Read more.

Imagined speech decoding has attracted growing interest in brain–computer interface (BCI) research, as it may enable language-related information to be recovered from non-overt neural activity. Current studies in this area are often treated as a single, unified research problem, despite substantial differences in decoding target, output constraints, and system output forms. This review examines recent imagined speech decoding research from a task-oriented perspective, with a focus on how different neural decoding tasks are defined, constrained by their output spaces, and expressed through different output pathways. The included studies are organized into four main task levels: semantic/intent, phoneme/syllable, word, and sentence/language decoding. They are further compared along two auxiliary dimensions: output-space property and output pathway, with particular attention to closed-set and open-vocabulary settings. The review shows that current studies span markedly different linguistic granularities and communication objectives, from low-bandwidth intent recognition to text or speech reconstruction. Finally, it concludes that imagined speech should not be treated as a single homogeneous decoding problem, and that a task-oriented framework provides a clearer basis for comparing heterogeneous studies and guiding future communication-oriented BCI research. Full article

(This article belongs to the Special Issue Biomedical Signals, Images and Healthcare Data Analysis: 2nd Edition)

► Show Figures

Figure 1

19 pages, 12757 KB

Open AccessArticle

Simulation-to-Real Trip-Fall Detection with Continuous-Wave Doppler Radar via Physics-Informed Kinematic Modeling and Domain Randomization

by Kosuke Okusa

Sensors 2026, 26(10), 3211; https://doi.org/10.3390/s26103211 - 19 May 2026

Abstract

Falls among older adults are a major public health concern, yet collecting large-scale real fall data for radar-based detection is ethically and practically difficult. This study presents a controlled simulation-to-real feasibility study for trip-fall detection using continuous-wave (CW) Doppler radar. The method couples [...] Read more.

Falls among older adults are a major public health concern, yet collecting large-scale real fall data for radar-based detection is ethically and practically difficult. This study presents a controlled simulation-to-real feasibility study for trip-fall detection using continuous-wave (CW) Doppler radar. The method couples a physics-informed kinematic trip-fall model with a CW radar observation model to synthesize I/Q signals and Doppler spectrograms, while domain randomization varies body size, fall direction, initial velocity, sensor placement, aspect angle, amplitude, and noise. Synthetic walking and respiration data were also generated for controlled three-class classification among trip fall, walking, and seated quiet breathing. In Experiment I, the simulated spectrograms reproduced the dominant time–frequency characteristics of measured enacted trip-fall signals acquired with a 24 GHz CW radar; quantitative similarity analysis yielded a mean SSIM of 0.782 and a Doppler-ridge MAE of 24.6 Hz across five fall directions. In Experiment II, a ResNet-18 classifier trained only on simulated spectrograms achieved a macro-F1 score of 0.912 [95% CI: 0.883–0.936] on measured data from ten participants, three start locations, and eight directions. Under the present controlled evaluation, this exceeded the available real-data-trained baseline of 0.748 [95% CI: 0.691–0.805] (paired subject-level permutation test,

p = 0.006

). These findings suggest that physics-informed simulation with domain randomization can reduce dependence on real trip-fall samples under limited-data conditions. The results do not establish robustness to other fall morphologies, fall-like activities of daily living, different environments, different radar devices, or embedded deployment. Full article

(This article belongs to the Section Environmental Sensing)

► Show Figures

Figure 1

24 pages, 554 KB

Open AccessArticle

An Efficient Wi-Fi Sensing Method for Robotic Arm Motion Recognition

by Junyan Zhuo, Qingrui Wang, Yuzhou Sheng, Xi Wang, Yuxuan Zhang and Xiaojing Wan

Sensors 2026, 26(10), 3210; https://doi.org/10.3390/s26103210 - 19 May 2026

Abstract

In recent years, channel state information (CSI)-based sensing technology has gradually attracted widespread attention as a contactless and low-cost approach for robotic arm motion understanding. Despite continuous progress in CSI-based human sensing, existing methods of robotic motion sensing still face two key challenges [...] Read more.

In recent years, channel state information (CSI)-based sensing technology has gradually attracted widespread attention as a contactless and low-cost approach for robotic arm motion understanding. Despite continuous progress in CSI-based human sensing, existing methods of robotic motion sensing still face two key challenges when directly applied to robotic motion sensing: (1) CSI perturbations induced by robotic arm motion are weak and locally distributed, making fine-grained feature extraction difficult. (2) Discriminative information in long robotic arm motion sequences is sparsely concentrated in a few key intervals, and its adaptive temporal selection and enhancement remain challenging. To address the above challenges, this paper proposes an efficient multi-stage robotic arm motion recognition method (named MSPoolNet). The proposed method consists of three key modules: an adaptive temporal downsampling module, a temporal gating module, and a Transformer-based feature encoding module. Specifically, the adaptive temporal downsampling module processes the raw CSI signal at the input stage to achieve local pattern extraction. The temporal gating module adaptively reweights temporal features, dynamically highlighting key temporal segments while suppressing irrelevant information. The proposed Transformer-based feature encoding module replaces conventional self-attention with pooling operations, enabling global information interaction and fine-grained feature representation in a computationally efficient manner. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art performance on two representative public datasets, maintaining a compact model size with an accuracy exceeding 99%. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

14 pages, 22228 KB

Open AccessArticle

Multi-Target Radar Speed Meter Failure Mechanism Research

by Lei Luo, Xin Jiang, Jianwen Shao, Cheng Chen, Cunbin Zhao, Xin Zhang and Xiaomin Shen

Sensors 2026, 26(10), 3209; https://doi.org/10.3390/s26103209 - 19 May 2026

Abstract

Multi-target radar speed measuring instruments play a crucial role in monitoring speeding violations of multiple targets in multiple lanes, ensuring the safety, order, and efficient operation of traffic. In order to verify the stability of these instruments under long-term and complex working conditions, [...] Read more.

Multi-target radar speed measuring instruments play a crucial role in monitoring speeding violations of multiple targets in multiple lanes, ensuring the safety, order, and efficient operation of traffic. In order to verify the stability of these instruments under long-term and complex working conditions, accelerated life testing was conducted, and the failure mechanisms of the radar were studied using optical and scanning electron microscopic analysis methods. The results indicated that at a test temperature of 85 °C and humidity of 79% RH, all five speed measuring specimens failed after testing for 55 days. The primary cause of failure was the malfunction of the microwave signal receiving chip in the radar speed module under the combination of temperature and humidity. The failure modes of the chip were mainly related to its structure, design, selection of soldering materials, and soldering process. This study provides references and insights for the reliability research of other metrological instrument products. Full article

(This article belongs to the Section Radar Sensors)

► Show Figures

Figure 1

31 pages, 44755 KB

Open AccessArticle

LUMEN: A Lightweight UAV Multi-Enhanced Network for PSD-Based RF Fingerprinting on Edge Devices

by Min-Joo Yoon and Ki-Woong Park

Sensors 2026, 26(10), 3208; https://doi.org/10.3390/s26103208 - 19 May 2026

Abstract

Unmanned aerial vehicle (UAV) identification in edge environments requires both high classification accuracy and efficient real-time deployment on lightweight hardware. This study presents LUMEN, a Lightweight UAV Multi-Enhanced Network designed for resource-constrained single-board computer platforms. To enable efficient edge deployment, the proposed method [...] Read more.

Unmanned aerial vehicle (UAV) identification in edge environments requires both high classification accuracy and efficient real-time deployment on lightweight hardware. This study presents LUMEN, a Lightweight UAV Multi-Enhanced Network designed for resource-constrained single-board computer platforms. To enable efficient edge deployment, the proposed method adopts a power spectral density (PSD)-based signal representation together with a lightweight neural network architecture. LUMEN combines multi-channel PSD stacking with multi-scale feature extraction to capture both short-term spectral variations and multi-resolution RF patterns. The proposed pipeline covers UAV RF data collection, including UAV RF data collection, dataset construction, preprocessing, model design, comparative evaluation, and deployment on an RK3582-based edge platform. In the classification experiments, LUMEN achieved the best performance among the four evaluated models, reaching an accuracy of 0.975, compared with 0.775, 0.876, and 0.942 for the baseline models. In the edge deployment test, the model maintained an average inference latency of 1.73 ms and a throughput of 578.95 FPS during a 30-min continuous run, while showing low CPU utilization, low memory usage, and stable thermal behavior. These results demonstrate that LUMEN achieves a practical balance between identification accuracy and runtime efficiency for real-time UAV identification on edge devices. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

13 pages, 232 KB

Open AccessArticle

Comparative Analysis of Physical Demands and Physiological Responses of Different Warm-Up Protocols in Highly Trained Female Football Players

by Ibai Errekagorri, Aratz Olaizola, Julen Castellano, Eduardo Abade and Hugo Silva

Sensors 2026, 26(10), 3207; https://doi.org/10.3390/s26103207 - 19 May 2026

Abstract

This study aimed to describe and compare warm-up (WU) demands of different protocols (with ball, without ball and pre-match) on female football players. Twenty-two players belonging to the same team were monitored throughout 12 training weeks using global navigation satellite system technology sampling [...] Read more.

This study aimed to describe and compare warm-up (WU) demands of different protocols (with ball, without ball and pre-match) on female football players. Twenty-two players belonging to the same team were monitored throughout 12 training weeks using global navigation satellite system technology sampling at 10 Hz. The variables used were duration, total distance, distances covered within 0–45%, 45–60%, 60–85%, and 85–100% of individual maximum speed, maximum speed, maximum acceleration, maximum deceleration, number of accelerations of magnitudes between 1 and 2 m/s², 2 and 3 m/s², 3 and 4 m/s², and above 4 m/s², number of decelerations of magnitudes between −1 and −2 m/s², −2 and −3 m/s², −3 and −4 m/s², and below −4 m/s², Player Load, and TRIMP Edwards. A linear mixed model was carried out for each variable in order to analyze the differences between WU protocols. The main results were that pre-match WU showed higher values in the following variables: (1) duration; (2) distances covered within 60–85% and 85–100% of individual maximum speed; (3) maximum speed, acceleration and deceleration; (4) number of accelerations of magnitudes between 2 and 3 m/s² and between 3 and 4 m/s², and more decelerations of magnitudes between −2 and −3 m/s², −3 and −4 m/s² and below −4 m/s²; and, (5) TRIMP Edwards. These findings underscore the importance of WU design in preparing female football players for high-intensity match demands and contribute to the development of specific WU strategies for them. Full article

(This article belongs to the Special Issue Sensors and Wearable Technologies in Sport Biomechanics—Second Edition)

24 pages, 11519 KB

Open AccessArticle

AD-DETR: A Real-Time Transformer with Multi-Scale Alignment and Spatial–Spectral Fusion for Crop Disease Detection

by Bingyang Wang, Huibo Zhou, Zhi Wang and Ruolan Chen

Sensors 2026, 26(10), 3206; https://doi.org/10.3390/s26103206 - 19 May 2026

Abstract

Agriculture faces significant challenges from crop diseases, which threaten global food security and cause substantial economic losses annually. While deep learning has advanced plant disease detection, existing models often struggle with generalization across heterogeneous environments and real-time deployment constraints, hindering their practical application [...] Read more.

Agriculture faces significant challenges from crop diseases, which threaten global food security and cause substantial economic losses annually. While deep learning has advanced plant disease detection, existing models often struggle with generalization across heterogeneous environments and real-time deployment constraints, hindering their practical application in diverse agricultural settings. This paper proposes AD-DETR, an enhanced real-time detection transformer framework specifically designed for agricultural scenarios. The model incorporates three key innovations to address these issues. First, the Multi-Scale Align Network (MSANet) achieves adaptive feature alignment through an Adapt Fusion Align (AFA) block, effectively preserving disease detail information across varying scales. Second, the Spatial–Spectral Attentive Feature Fusion (SSAFF) module integrates frequency-domain processing with attention mechanisms, enhancing feature representation quality by combining spatial and spectral information. Third, the IPIoUv2 loss function improves bounding-box regression accuracy through an internal perception mechanism and scale-adaptive weighting. Comprehensive experiments demonstrate that AD-DETR achieves strong performance, with 90.2% mean average precision at

I o U = 0.5

on the Crop Disease dataset and 97.4% on the PlantDoc dataset. It maintains high efficiency with 16.4 million parameters, 47.2 GFLOPs computational complexity, and inference speeds of 230–242 frames per second. These results indicate that AD-DETR is robust to domain shift and suitable for resource-constrained applications, such as real-time monitoring on mobile and edge platforms. Full article

(This article belongs to the Section Smart Agriculture)

► Show Figures

Figure 1

17 pages, 872 KB

Open AccessArticle

BATFNet: Boundary-Aware Transformer Fusion Network for RGB-DSM Semantic Segmentation of Remote Sensing Images

by Yilin Tong, Meng Tang, Yu Zhang, Yan Huang, Jing Huang, Yuelin He, Yuxin Liu, Edore Akpokodje and Dan Zheng

Sensors 2026, 26(10), 3205; https://doi.org/10.3390/s26103205 - 19 May 2026

Abstract

Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of [...] Read more.

Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of 84.06% and 85.31%, respectively, outperforming representative RGB–DSM fusion baselines on most land-cover categories. BATFNet is a supervised boundary-aware Transformer fusion network that uses DSM-derived edge priors to guide bidirectional cross-modal attention and decoder refinement. With a dual-branch ResNet-50 backbone for modality-specific feature extraction, the proposed framework effectively integrates RGB and DSM information while recovering fine spatial details. These results show that exploiting DSM-derived structural cues improves boundary delineation and reduces confusion among spectrally similar urban classes. Full article

(This article belongs to the Special Issue Remote Sensing Image Fusion and Object Tracking)

► Show Figures

Figure 1

27 pages, 20183 KB

Open AccessArticle

Piezoresistive Sensing Performance of Smart Layer in Multi-Material 3D-Printed Reinforced Cementitious Beams

by Han Liu, Israel Sousa, Shelby E. Doyle, Antonella D’Alessandro, Filippo Ubertini and Simon Laflamme

Sensors 2026, 26(10), 3204; https://doi.org/10.3390/s26103204 - 19 May 2026

Abstract

3D concrete printing (3DP) enables automated construction with reduced material waste and enhanced geometric flexibility. However, its structural performance remains sensitive to anisotropy, mix design, and printing parameters, thereby complicating quality control. Self-sensing cementitious materials provide a promising approach by enabling intrinsic strain [...] Read more.

3D concrete printing (3DP) enables automated construction with reduced material waste and enhanced geometric flexibility. However, its structural performance remains sensitive to anisotropy, mix design, and printing parameters, thereby complicating quality control. Self-sensing cementitious materials provide a promising approach by enabling intrinsic strain monitoring during fabrication and service. In this study, a hybrid multi-material printing strategy was developed using a conductive cement-based mix incorporating graphite (G), milled carbon microfibers (MCMF), and chopped carbon microfibers (CCMF), alongside a plain cement-based matrix. Based on percolation analysis, an optimal composition of 2 wt.% G, 0.25 wt.% MCMF, and 0.0625 wt.% CCMF was selected. Reinforced beam specimens were fabricated with the conductive material embedded in either the tensile (bottom) or compressive (top) region, combined with two internal architectures: diagonal infill and solid-base configuration. Four configurations were defined: Pattern 1 (bottom/diagonal), Pattern 2 (bottom/solid-base), Pattern 3 (top/diagonal), and Pattern 4 (top/solid-base). Cyclic three-point bending tests with spatially distributed electrical measurements were conducted to evaluate the electromechanical response in the elastic range. Specimens with the conductive layer located in the tensile region (Patterns 1 and 2) consistently exhibited higher gauge factors than those in the compressive region (Patterns 3 and 4). Pattern 2 exhibited the best sensing performance, with an average gauge factor of 556 and SNR of 31. Across all configurations, SNR decreased with increasing electrode spacing, with reductions of up to 31.0%, demonstrating the effect of current path length on sensing performance. Full article

(This article belongs to the Special Issue Novel Sensor Technologies for Civil Infrastructure Monitoring)

► Show Figures

Figure 1

Journal Description

Sensors

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI