Next Issue
Volume 26, June-1
Previous Issue
Volume 26, May-1
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
9.4
4.0
Journals
Sensors
Volume 26
Issue 10
sensors-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Sensors, Volume 26, Issue 10 (May-2 2026) – 361 articles

Cover Story (view full-size image):

Pancreatic islets regulate blood glucose by secreting insulin, making glucose-stimulated insulin secretion the central functional readout for assessing islet function. However, conventional assays such as ELISA require offline processing and typically pool many islets, obscuring single-islet heterogeneity and rapid secretion dynamics. In this work, we present a microscopy-compatible islet-on-a-chip integrated with broadband backscattering confocal microscopy for continuous, label-free optical sensing of insulin secretion from individual human islets. Fabricated by two-photon polymerization, the device stabilizes single islets under continuous perfusion, while the optical readout identifies insulin granule-rich β-cells and tracks granule dynamics during glucose stimulation. View this paper

  • 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:
24 pages, 1439 KB  
Communication
State-Driven Adaptive Deep-Unfolded PGA Algorithm for Hybrid Beamforming in MIMO-JCAS Systems
by Fulai Liu, Zihao Wang, Yan Gao and Zhuoyi Yao
Sensors 2026, 26(10), 3276; https://doi.org/10.3390/s26103276 - 21 May 2026
Viewed by 424
Abstract
In massive multiple-input multiple-output (MIMO) joint communication and sensing (JCAS) systems, hybrid beamforming (HBF) has attracted much attention because it can provide a favorable tradeoff between beamforming gain and hardware cost. However, HBF design in MIMO-JCAS systems is highly challenging. The main reasons [...] Read more.
In massive multiple-input multiple-output (MIMO) joint communication and sensing (JCAS) systems, hybrid beamforming (HBF) has attracted much attention because it can provide a favorable tradeoff between beamforming gain and hardware cost. However, HBF design in MIMO-JCAS systems is highly challenging. The main reasons are the strong coupling between the analog and digital precoders in joint communication-sensing optimization and the high-dimensional search space caused by large-scale antenna arrays. In this paper, a state-driven adaptive deep-unfolded hybrid beamforming algorithm is proposed for MIMO-JCAS systems. Specifically, the analog precoder update is redesigned in a manifold-based form to better match the geometry of the constant-modulus constraint, while the digital precoder update is enhanced by a learnable gradient-balancing mechanism to alleviate the dynamic imbalance between the communication-rate gradient and the sensing-error gradient. Furthermore, a lightweight state-driven control network is introduced to generate scaling factors for the hyperparameters according to the current iteration state, so that the unfolded model can adapt its update behavior during optimization. Different from conventional deep-unfolded methods with static hyperparameters during inference, the proposed method provides a more effective optimization strategy for the dynamic communication-sensing tradeoff in MIMO-JCAS hybrid beamforming. Simulation results demonstrate the effectiveness of the proposed state-driven adaptive deep-unfolded method. Compared with the conventional deep-unfolded projected gradient ascent (PGA) algorithm with 20 inner iterations, the proposed method improves the joint objective, while achieving faster convergence and stronger robustness. Full article
(This article belongs to the Section Communications)
►▼ Show Figures

Figure 1

29 pages, 29219 KB  
Article
Feedback-Driven SLAM with Adaptive Point Cloud Selection and Uncertainty-Aware Pose Optimization
by Yuqi Shi, Fei Zhang, Zijing Zhang, Ying Hu and Zhanrui Hu
Sensors 2026, 26(10), 3275; https://doi.org/10.3390/s26103275 - 21 May 2026
Viewed by 557
Abstract
LiDAR SLAM is widely used in robotic navigation and autonomous driving, but many existing methods still handle frontend point cloud processing and backend pose optimization as two loosely connected stages with fixed settings. This can lead to unnecessary computation and also limits the [...] Read more.
LiDAR SLAM is widely used in robotic navigation and autonomous driving, but many existing methods still handle frontend point cloud processing and backend pose optimization as two loosely connected stages with fixed settings. This can lead to unnecessary computation and also limits the localization performance when the environment or motion changes. To address this issue, we propose a LiDAR–inertial SLAM framework with bidirectional closed-loop coupling between adaptive point cloud processing and pose optimization. In the frontend, depth image resolution is adjusted online according to backend pose uncertainty and loop closure importance, and a comprehensive score integrating point density, depth stability, geometric complexity, and motion consistency is used to select high-quality sparse points. In the backend, the comprehensive score is further combined with depth image quantization error to construct per-point covariance matrices for uncertainty-weighted scan-to-map ICP and factor graph noise modeling. Experiments on the KITTI and M2DGR datasets show that the proposed method reduced the mean RMSE by 15.8% and 15.2%, respectively, compared with FAST-LIO2, while the real-world field test further shows a 26.3% RMSE reduction with respect to the constructed reference trajectory. These results show that the proposed framework improves both mapping quality and localization accuracy. Full article
(This article belongs to the Section Sensors and Robotics)
►▼ Show Figures

Figure 1

14 pages, 876 KB  
Article
An EEG-Based Edge-AI Framework for Alzheimer’s and Creutzfeldt–Jakob Disease Classification
by Muhammad Suffian, Cosimo Ieracitano, Nadia Mammone, Angelo Pascarella, Edoardo Ferlazzo and Francesco Carlo Morabito
Sensors 2026, 26(10), 3274; https://doi.org/10.3390/s26103274 - 21 May 2026
Viewed by 485
Abstract
Electroencephalography (EEG) has emerged as a promising non-invasive tool for the diagnosis of neurodegenerative disorders, and artificial intelligence (AI) has shown significant potential in this domain, as demonstrated by recent studies. However, strong inter-subject variability remains a major challenge, limiting the ability of [...] Read more.
Electroencephalography (EEG) has emerged as a promising non-invasive tool for the diagnosis of neurodegenerative disorders, and artificial intelligence (AI) has shown significant potential in this domain, as demonstrated by recent studies. However, strong inter-subject variability remains a major challenge, limiting the ability of AI-based models to learn disease-specific features that generalize across individuals, thereby hindering the development of clinically deployable subject-independent systems. In this work, we propose a cross-subject, AI-based EEG classification framework to distinguish between Alzheimer’s disease (AD), Creutzfeldt–Jakob disease (CJD), and healthy control subjects using clinical EEG data collected from a local hospital. A lightweight hybrid deep learning model is developed, combining a two-layer one-dimensional convolutional neural network with a two-layer Transformer encoder to capture both local temporal patterns and long-range dependencies in EEG signals. The proposed model achieves an average classification accuracy of 97%, representing a 3% improvement over a baseline model evaluated on a cohort of 36 subjects. To assess deployment feasibility in real-time clinical settings, the trained model is implemented and evaluated on an edge-AI platform (NVIDIA Jetson AGX Orin), demonstrating energy efficiency for the inference with a compact model footprint. These results indicate that the proposed approach provides an accurate, efficient, and practically deployable solution for subject-independent EEG-based classification of neurological disorders. Full article
(This article belongs to the Special Issue Green Deep Learning Techniques for Sensing and Experimental Multimodal Signal Processing)
►▼ Show Figures

Figure 1

24 pages, 4265 KB  
Article
A Robust Deep Learning Framework for Skill Level Discrimination in Tennis Strokes Using Bilateral IMU Measurements
by Enes Halit Aydin and Onder Aydemir
Sensors 2026, 26(10), 3273; https://doi.org/10.3390/s26103273 - 21 May 2026
Viewed by 445
Abstract
In tennis, where performance is governed by complex kinetic chain interactions, objective skill classification is vital for coaching and talent identification. This study presents a hierarchical deep learning framework leveraging synchronized bilateral Inertial Measurement Unit (IMU) data from 39 participants (11 elite, 28 [...] Read more.
In tennis, where performance is governed by complex kinetic chain interactions, objective skill classification is vital for coaching and talent identification. This study presents a hierarchical deep learning framework leveraging synchronized bilateral Inertial Measurement Unit (IMU) data from 39 participants (11 elite, 28 amateur). The proposed system successfully distinguishes expertise levels across a total of 4594 strokes, including augmented samples. A hybrid Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) architecture was developed to autonomously extract spatiotemporal features from the raw kinematic signals of forehand, backhand, service, and volley strokes. The proposed model achieved an accuracy of 95.54%, significantly outperforming both traditional machine learning and state-of-the-art deep learning benchmarks. Qualitative t-distributed Stochastic Neighbor Embedding (t-SNE) analyses revealed that elite athletes form highly homogeneous clusters in the feature space. Furthermore, quantitative Asymmetry Index assessments confirmed that professionals exhibit superior bilateral coordination stability. These findings demonstrate that the proposed end-to-end system offers a robust, field-applicable solution for identifying technical excellence. It provides coaches with reliable digital biomarkers, thereby overcoming the limitations of subjective visual observation. Full article
(This article belongs to the Section Intelligent Sensors)
►▼ Show Figures

Figure 1

17 pages, 864 KB  
Article
Query-Efficient Hard-Label Attack: A Prior-Guided Adam Ray Search Optimization
by Tianyi Ding, Xinjie Xu, Qi Xuan, Hanzhe Yu and Chen Ma
Sensors 2026, 26(10), 3272; https://doi.org/10.3390/s26103272 - 21 May 2026
Viewed by 343
Abstract
Deep neural networks are vulnerable to adversarial examples, even in hard-label black-box settings where only the top-1 prediction is available. To address the challenges of high-dimensional optimization under limited query budgets, we propose two query-efficient attack methods: Adam-OPT, which integrates Adam-based adaptive optimization [...] Read more.
Deep neural networks are vulnerable to adversarial examples, even in hard-label black-box settings where only the top-1 prediction is available. To address the challenges of high-dimensional optimization under limited query budgets, we propose two query-efficient attack methods: Adam-OPT, which integrates Adam-based adaptive optimization into the ray-search framework to stabilize and accelerate zeroth-order gradient updates; Prior-Adam-OPT, which further incorporates transfer-based priors from surrogate models to enhance gradient estimation. Adam-OPT leverages historical gradient information and per-parameter adaptive updates to improve convergence, while Prior-Adam-OPT constructs a prior-guided orthogonal search basis that combines surrogate and random directions, enhancing both gradient accuracy and query efficiency. Our approach demonstrates superior performance across CIFAR-10, ImageNet, and zero-shot CLIP models, consistently reducing perturbation magnitudes and improving attack efficiency compared to state-of-the-art hard-label attacks. Ablation studies highlight the importance of the number of vectors used for gradient estimation and the quality of surrogate models, showing that combining adaptive optimization with transfer-based priors provides a scalable and robust framework for generating high-quality adversarial examples in challenging black-box scenarios. Full article
(This article belongs to the Special Issue Security of AI-Driven Sensing Systems)
►▼ Show Figures

Figure 1

21 pages, 6200 KB  
Article
A Novel MSPLL-Based Method for Frequency Synthesis in Hydrogen MASER
by Dipika Simariya, Sheeba Rani Johnson, Dileep Dharmappa, Suresh Dakkumalla, Prem Ranjan Dubey, Roopa Malali Vasanthakumar, Deva Arul Daniel and Subramanya Ganesh Thirukkodi
Sensors 2026, 26(10), 3271; https://doi.org/10.3390/s26103271 - 21 May 2026
Viewed by 631
Abstract
Frequency synthesis is an important aspect of an atomic clock. It is also imperative that the synthesized frequency exhibits good short term stability or, in other words, exhibits good phase noise. Conventionally single-PLL-system-based approaches have been made for realizing the frequency synthesizers required [...] Read more.
Frequency synthesis is an important aspect of an atomic clock. It is also imperative that the synthesized frequency exhibits good short term stability or, in other words, exhibits good phase noise. Conventionally single-PLL-system-based approaches have been made for realizing the frequency synthesizers required for hydrogen maser atomic clocks. In this article, a novel approach involving a master–slave-based phase-locked loop (MSPLL) method is presented for frequency synthesis in a hydrogen maser atomic clock. The novelty of this paper lies in the fact that the way two phase-locked loops are coupled to obtain advantage in improving the master oscillator’s stability to match maser physics subsystem stability and at the same time achieving lower jitter by the design. The design involves the usage of a master and a slave phase-locked loop with coupled custom designed direct digital synthesizers for ensuring that the hydrogen maser’s frequency stability is transferred to the master oscillator. The slave PLL (SPLL) generates a low jitter clock for the master PLL (MPLL), thereby guaranteeing reliable tracking of the input reference of 10 MHz, obtained by down-converting the maser physics subsystem frequency of ∼1.4 GHz. A novel mathematical model was derived for the proposed MSPLL design which aids in determination of the settling time of phase, which in turn, leads to the investigation of jitter variance in time domain. A detailed study and analysis of the settling time, phase noise in frequency domain, phase jitter in time domain. and stability performance is presented. The results were validated by the experimental data. The realized frequency synthesizer deduced a settling time of phase that can be adjusted between 689 μs to 811 μs. The synthesized frequency’s phase noise is ≤−114 dBc/Hz at 1 Hz offset, and it was observed that this design induces a very low phase noise to the output signal with respect to the physics subsystem. The achieved short-term stability of the output signal at 1 s is approximately (7.66 × 10−12) τ−1/2, which is very close to the physics subsystem stability. In terms of stability degradation factor, the proposed MSPLL design exhibits an excellent short-term stability that is one order better than that of the existing methods. Full article
(This article belongs to the Topic Navigation and Positioning System: Opportunities and Obstacles)
►▼ Show Figures

Figure 1

29 pages, 17170 KB  
Article
Optical Gas Imaging with Cooled and Uncooled Thermal Infrared Cameras
by Gabriel Jobert, Nicolas Vannier, Charlène Lefèvre, Eléa Bourliaud, Adrien Bertrand, Emmanuelle Chazelle and Eric Mallet
Sensors 2026, 26(10), 3270; https://doi.org/10.3390/s26103270 - 21 May 2026
Viewed by 387
Abstract
In a context of greenhouse-gas-reduction for climate-change mitigation, Optical Gas Imaging (OGI) is cited by US and EU regulations as a key technology for detecting methane leaks in the oil and gas industry. The paper outlines the principles of OGI, covering specificity of [...] Read more.
In a context of greenhouse-gas-reduction for climate-change mitigation, Optical Gas Imaging (OGI) is cited by US and EU regulations as a key technology for detecting methane leaks in the oil and gas industry. The paper outlines the principles of OGI, covering specificity of both high-performance cooled cameras and cost-effective thermal infrared uncooled cameras. It explains camera design, the optical-radiometric theory of contrast and sensitivity, and provides a comprehensive description of the key performance indicators (KPIs) such as NETD, NECL, and MDLR; together with parameters that influence them. These theoretical concepts are supported by measurements taken under laboratory conditions and outdoors, with wind and complex scenes. Finally, video-processing methods for visualizing gas leaks are presented, showing how they increase visual sensitivity and reduce the user’s cognitive load. Full article
(This article belongs to the Section Optical Sensors)
►▼ Show Figures

Figure 1

42 pages, 5265 KB  
Article
Hybrid Validation of a Quality-Controlled, Waveform-Centered AI Framework with Optional Multi-Sensor Support for Seismic Monitoring
by Askar Abdykadyrov, Yerik Alipuly, Maxat Mamadiyarov, Bekbolat Tashev, Akerke Yerkinova and Kalmukhamed Tazhen
Sensors 2026, 26(10), 3269; https://doi.org/10.3390/s26103269 - 21 May 2026
Viewed by 351
Abstract
Rapid and reliable seismic monitoring requires accurate waveform inference, together with robustness to noise, incomplete sensing, and unstable predictions. This study investigates a quality-controlled, waveform-centered, AI-assisted framework for seismic event detection, P- and S-phase picking, graph-aware inter-station refinement, and rapid hazard-related characterization. The [...] Read more.
Rapid and reliable seismic monitoring requires accurate waveform inference, together with robustness to noise, incomplete sensing, and unstable predictions. This study investigates a quality-controlled, waveform-centered, AI-assisted framework for seismic event detection, P- and S-phase picking, graph-aware inter-station refinement, and rapid hazard-related characterization. The framework includes optional DAS, MEMS, and high-rate GNSS branches; however, the primary empirical validation is based on real waveform-centered IRIS records from the Almaty seismic region, not on a fully synchronized multimodal field deployment. The dataset includes seven seismic stations, HHZ waveforms sampled at 100 Hz, 219 seismic events, 1260 event traces, and 240 s P-centered windows from 1 January 2023 to 31 December 2024. Optional auxiliary branches are evaluated through controlled branch-availability, reduced-input, fallback, and stress-test scenarios. Under the standard-condition benchmark, the proposed framework achieved a precision of 0.941, recall of 0.932, F1 score of 0.936, false-alarm rate of 0.051, detection latency of 173 ms, and P- and S-pick mean absolute errors of 31 ms and 54 ms. Under controlled low-SNR testing, it retained an F1 score of 0.846. The findings support waveform-centered, quality-controlled monitoring, while broader cross-domain and fully synchronized multimodal validation remain necessary. Full article
(This article belongs to the Section Intelligent Sensors)
►▼ Show Figures

Figure 1

36 pages, 683 KB  
Article
An FPGA-Based Event-Timing Front-End for Time-Resolved Sensing with Dual-Mode Experimental Characterization
by Juan Núñez and Rafaella Fiorelli
Sensors 2026, 26(10), 3268; https://doi.org/10.3390/s26103268 - 21 May 2026
Viewed by 605
Abstract
This work presents an FPGA-based edge-event timing front-end for time-resolved sensing and event-driven measurement scenarios. The proposed design is intended as a detector-independent timing subsystem whose architectural choices are motivated by constraints that are common in single-photon avalanche diode (SPAD)-based and other asynchronous [...] Read more.
This work presents an FPGA-based edge-event timing front-end for time-resolved sensing and event-driven measurement scenarios. The proposed design is intended as a detector-independent timing subsystem whose architectural choices are motivated by constraints that are common in single-photon avalanche diode (SPAD)-based and other asynchronous time-resolved sensing workflows, including event trustworthiness, dead-time sensitivity, and constrained downstream readout. Rather than treating the implementation as an isolated interpolation macro, this work evaluates it as an experimentally observable timing subsystem that combines carry-chain-based fine interpolation, coarse–fine timestamp formation, explicit event-quality assessment, dead-time-aware handling, and lightweight host-visible export. The experimental validation is organized around two complementary modes. An internal ILA-based mode is used to verify coherent front-end behavior under MHz-range short-pulse excitation, while a UART-based campaign identifies practical host-visible operating regions through baseline, repeatability, pulse-width, safe-versus-aggressive, and intermediate frequency-sweep experiments. The results identify a safe export-compatible operating point, a more exploratory high-rate regime, and an experimentally interpretable transition between them that, while not strictly monotonic in all metrics, does not exhibit catastrophic degradation across the explored frequency range. Taken together, the measurements indicate that the proposed architecture is best understood not as a best-case standalone time-to-digital (TDC) benchmark but as an experimentally characterized timing front-end whose practical behavior can be interpreted across complementary internal and export-visible operating regimes. Full article
(This article belongs to the Special Issue SPAD-Based Sensors and Techniques for Enhanced Sensing Applications)
►▼ Show Figures

Figure 1

29 pages, 11781 KB  
Article
MOCA-Net: A Model for Automatic Segmentation of Retrogressive Thaw Slumps from Sentinel-2 Imagery Along the Qinghai–Tibet Engineering Corridor
by Yijiang Li, Qiong Li, Guoxin Chen, Wenqi Li and Changyan Bao
Sensors 2026, 26(10), 3267; https://doi.org/10.3390/s26103267 - 21 May 2026
Viewed by 510
Abstract
Retrogressive thaw slumps (RTSs) serve as key indicators of global climate change and also pose significant risks to critical infrastructure along the Qinghai–Tibet Engineering Corridor (QTEC). Accurate automatic segmentation of RTSs using Sentinel-2 imagery is of great value for climate change research and [...] Read more.
Retrogressive thaw slumps (RTSs) serve as key indicators of global climate change and also pose significant risks to critical infrastructure along the Qinghai–Tibet Engineering Corridor (QTEC). Accurate automatic segmentation of RTSs using Sentinel-2 imagery is of great value for climate change research and risk assessment, owing to the dataset’s ready availability and extensive spatiotemporal coverage. However, this segmentation task remains challenging due to the complex morphology and variable sizes of RTSs, as well as their low contrast and fuzzy boundaries against the surrounding landscape in medium-resolution satellite imagery. To deal with these challenges, this study proposes the Multi-Scale Object-aware Context Attention Network (MOCA-Net), which enhances the Swin Transformer backbone through two critical components: the Feature Enhancement Network and Enhanced Decoder. Evaluation metrics show that MOCA-Net outperforms seven mainstream baseline models, achieving a Mean Intersection over Union (mIoU) of 0.8609 and an RTS-class IoU of 0.7473. The qualitative visual evaluation further confirms MOCA-Net’s improved performance in delineating RTSs through more accurate morphologies and boundaries. Ablation studies confirm that each designed component contributes to the MOCA-Net’s segmentation performance, and their combination yields more balanced results. This model unlocks the capability of Sentinel-2 imagery for accurate RTS segmentation, making it promising for applications over large spatiotemporal extents. Full article
(This article belongs to the Section Remote Sensors)
►▼ Show Figures

Figure 1

22 pages, 3307 KB  
Article
Geometry-Aware Enhanced 6DRepNet for Single-RGB Head Pose Estimation
by Hua Yang, Yuanyuan Li, Mingzhi Mu and Ming Zhao
Sensors 2026, 26(10), 3266; https://doi.org/10.3390/s26103266 - 21 May 2026
Viewed by 436
Abstract
Head pose estimation is a fundamental task in facial analysis and behavior understanding. To address the limitations of 6DRepNet in single-RGB scenarios, particularly in high-level spatial discriminative region modeling, global feature-to-6D rotation representation mapping, and the optimization of large-pose challenging samples, this paper [...] Read more.
Head pose estimation is a fundamental task in facial analysis and behavior understanding. To address the limitations of 6DRepNet in single-RGB scenarios, particularly in high-level spatial discriminative region modeling, global feature-to-6D rotation representation mapping, and the optimization of large-pose challenging samples, this paper proposes a geometry-aware enhanced framework for head pose estimation. While preserving the 6D continuous rotation representation and its SO(3)-based geometric supervision mechanism, the proposed method improves the baseline model through the joint design of a Spatial Recalibration Module, a Residual Pose Mapping Head, and a Pose-Aware Weighted Geodesic Loss. Experiments are conducted using 300W-LP for training and AFLW2000 and BIWI for evaluation. The results show that the proposed method consistently outperforms the baseline 6DRepNet on both datasets, reducing the overall MAE from 3.97 to 3.72 on AFLW2000 and from 3.54 to 3.26 on BIWI. Ablation studies further verify the effectiveness and complementarity of the proposed components. These results demonstrate that the proposed method can effectively improve the accuracy and robustness of single-RGB head pose estimation without introducing additional modalities. Full article
(This article belongs to the Section Sensing and Imaging)
►▼ Show Figures

Figure 1

36 pages, 9783 KB  
Article
Spectral-YOLOv13: A Dual-Domain Vision-Mamba Sensing Framework for Fine-Grained Coral Health Assessment and Continuous Ecological Forecasting
by Litian Yang, Wenkun Chen, Zhuoyue Mo, Xin Gao, Minzhi Mo, Chunlei Xia and Liankuan Zhang
Sensors 2026, 26(10), 3265; https://doi.org/10.3390/s26103265 - 21 May 2026
Viewed by 452
Abstract
Coral reefs are among the most important and vulnerable marine ecosystems worldwide. AI-powered underwater visual monitoring has become essential for effective reef conservation, yet current methods still face severe limitations: spectral ambiguity caused by underwater turbidity, fine-grained confusion in early coral health assessment, [...] Read more.
Coral reefs are among the most important and vulnerable marine ecosystems worldwide. AI-powered underwater visual monitoring has become essential for effective reef conservation, yet current methods still face severe limitations: spectral ambiguity caused by underwater turbidity, fine-grained confusion in early coral health assessment, and discrete forecasting models that cannot represent continuous ecological degradation dynamics. To address these issues, we propose Spectral-YOLOv13, a dual-domain vision-Mamba sensing framework for high-precision coral health evaluation and continuous ecological forecasting. The framework incorporates three novel components: a Wavelet-Integrated Omni-Neck (WIO-Neck) to perform multi-scale spectral filtering and suppress turbidity-induced noise; a Contrastive Prototype Head (CP-Head) to enhance discriminability between visually similar health states; and a Bio-Mamba Predictor based on state-space models to capture long-term continuous health trajectories. Extensive experiments on the CR-Mix++ dataset demonstrate that Spectral-YOLOv13 achieves 53.8% mAP with strong robustness in turbid underwater environments. It reduces four-week forecasting error by 26.8% and maintains real-time inference speed at 112 FPS. This work provides a reliable and high-performance vision framework for practical underwater coral reef monitoring and proactive conservation management. Full article
(This article belongs to the Special Issue AI-Based Computer Vision Sensors & Systems—2nd Edition)
►▼ Show Figures

Figure 1

29 pages, 19163 KB  
Article
Real-Time Small Retail Product Detection in Low-Light Intelligent Cabinets Under Complex Backgrounds
by Moushiqi Yang, Junjie Cai, Yuanyuan Yang, Jian Chen and Kai Xie
Sensors 2026, 26(10), 3264; https://doi.org/10.3390/s26103264 - 21 May 2026
Viewed by 405
Abstract
Intelligent retail cabinets require accurate and real-time detection of small retail products in complex environments, particularly under low-light conditions and large-scale variations. However, existing object detection methods often suffer from insufficient feature representation and unstable performance in small-object retail commodity recognition tasks under [...] Read more.
Intelligent retail cabinets require accurate and real-time detection of small retail products in complex environments, particularly under low-light conditions and large-scale variations. However, existing object detection methods often suffer from insufficient feature representation and unstable performance in small-object retail commodity recognition tasks under low illumination and complex backgrounds. To address these challenges, this paper proposes a real-time small retail product detection framework based on YOLOv26 for low-light intelligent cabinet environments, aiming to improve detection accuracy, robustness, and deployment efficiency. A C3k2-enhanced multi-scale feature extraction module is introduced to strengthen feature representation for small retail products, while a novel detection head integrates minimum-resolution feature layers and an Efficient Multi-scale Attention (EMA) mechanism to enhance feature fitting ability under low-light conditions. In addition, convolution-based downsampling and Content-Aware ReAssembly of Features module (CARAFE) is adopted to improve feature fusion efficiency and reduce computational overhead. Experimental results on the RPC commodity dataset and the 6th Commodity Recognition Competition dataset demonstrate that the proposed method achieves improved detection performance compared with baseline models, with a 0.9% increase in Recall and a 0.2% improvement in mean Average Precision at IoU threshold 0.50 (mAP@50) while maintaining competitive mean Average Precision averaged over IoU thresholds from 0.50 to 0.95 (mAP@50-95). While the GFLOPS value rose from 5.8 to 6.3, deployment on the Jetson Nano platform achieves 25 FPS, demonstrating real-time detection capability in intelligent retail environments. The proposed framework provides a reliable and deployable solution for small retail product detection in low-light intelligent cabinet systems. Full article
(This article belongs to the Special Issue Real-Time Object Detection and Classification Using Advanced Sensing Techniques)
►▼ Show Figures

Figure 1

23 pages, 32417 KB  
Article
Vision-Based Person-Following Algorithm for Assistive Elderly-Care Quadruped Robots
by Vishnudev Kurumbaparambil, Subashkumar Rajanayagam and Stefan Twieg
Sensors 2026, 26(10), 3263; https://doi.org/10.3390/s26103263 - 21 May 2026
Viewed by 485
Abstract
The demographic shift towards an aging population necessitates innovative solutions for care and mobility support. While commercial quadruped robots like the Unitree Go1 offer dynamic stability, their native following modes often lack the safety margins and predictability required, and they do not consistently [...] Read more.
The demographic shift towards an aging population necessitates innovative solutions for care and mobility support. While commercial quadruped robots like the Unitree Go1 offer dynamic stability, their native following modes often lack the safety margins and predictability required, and they do not consistently follow the user, at times deviating and navigating independently. This paper presents a robust, vision-based, person-following algorithm designed to address these limitations. Utilizing a ZED 2 stereo camera and Robot Operating System (ROS), the system employs a finite state machine to ensure deterministic target tracking. A velocity control strategy partitions the robot’s motion into distinct stability, proportional, and braking zones based on depth data to ensure fluid interaction. The framework was validated on a Unitree Go1 quadruped platform in an outdoor environment involving 90-degree turns to evaluate tracking robustness. By operating in a headless mode, the system achieved a mean processing latency of 66.5±4.3 ms. Experimental results demonstrated consistent operational stability, 0.0% intrusion into the intimate safety zone, and effective velocity synchronization between 0.47 and 0.54 m/s. While this study establishes a robust technical baseline using healthy subjects, it serves as a preliminary development platform; further iterative testing with elderly users in clinical settings is required to move toward deployment. Beyond the evaluated trials, the framework maintained reliable functional performance across various care facility workshops, successfully following the target in all deployment scenarios. These findings establish a stable technical foundation for the future development of robotic walking partners. Full article
(This article belongs to the Special Issue Intelligent Sensing for Robotic Control and Visual Perception)
►▼ Show Figures

Figure 1

36 pages, 6977 KB  
Article
SparseTrack: A Physics-Informed Transformer Framework for Real-Time Human Motion Reconstruction from Sparse IMUs
by Adithya Balasubramanyam, Suchir Murali Velpanur, Sushma Edhala Jeevarathnam, Tejasree Chekuri Jayachandra, Prasad Honnavalli and Gowri Srinivasa
Sensors 2026, 26(10), 3262; https://doi.org/10.3390/s26103262 - 21 May 2026
Viewed by 518
Abstract
Wearable inertial measurement units are widely used for human motion analysis due to their portability; however, most IMU-based motion capture systems rely on dense sensor configurations that increase cost, complexity, and usability challenges in real-world applications. To address this limitation, this paper presents [...] Read more.
Wearable inertial measurement units are widely used for human motion analysis due to their portability; however, most IMU-based motion capture systems rely on dense sensor configurations that increase cost, complexity, and usability challenges in real-world applications. To address this limitation, this paper presents a sparse inertial human motion reconstruction framework that uses only five wearable sensors while maintaining real-time performance and biomechanical plausibility. The proposed framework integrates Movella Xsens DOT IMUs with a learning-based inverse kinematics pipeline and a real-time biomechanical digital twin for motion reconstruction and visualization. The evaluation was conducted in two phases: first, a real-time motion streaming system was established to validate sensor alignment, coordinate frame consistency, and end-to-end latency; second, a sparse inference framework was trained using the Virginia Tech Natural Motion Dataset combined with a custom dataset containing hard negative samples. Experimental results show that the system can accurately reconstruct full-body human motion, excluding head movement, with a local Mean Per-Joint Position Error of 5.96 cm using only five sensors. Comparative ablation studies demonstrate that Transformer-based temporal modeling achieves better geometric accuracy and temporal smoothness than recurrent and convolutional baselines, while physics-informed regularization and hard negative mining significantly improve biomechanical consistency and reduce motion jitter. Real-time experiments further demonstrate that the framework operates within interactive latency limits, highlighting its potential for biomechanical digital twin applications. Full article
(This article belongs to the Section Intelligent Sensors)
►▼ Show Figures

Figure 1

18 pages, 5622 KB  
Article
MscaVPR: Multi-Scale Coordinate Attention Network for Robust Visual Place Recognition
by Xiaohan Gao, Zhinong Zhong, Yongjian Tan, Ning Jing, Anran Yang and Qingren Jia
Sensors 2026, 26(10), 3261; https://doi.org/10.3390/s26103261 - 21 May 2026
Viewed by 598
Abstract
Visual place recognition (VPR) aims to localize a query image by matching its visual representation against a geotagged database. One major challenge in VPR is to learn place representations that remain robust under appearance changes, viewpoint variations, and perceptual aliasing. However, existing VPR [...] Read more.
Visual place recognition (VPR) aims to localize a query image by matching its visual representation against a geotagged database. One major challenge in VPR is to learn place representations that remain robust under appearance changes, viewpoint variations, and perceptual aliasing. However, existing VPR methods still show limitations in adaptive multi-scale feature fusion and viewpoint-aware training supervision, which may hinder robustness under severe viewpoint changes. In this paper, we propose MscaVPR, a VPR framework that combines multi-scale feature enhancement with azimuth-aware training. Specifically, a Multi-Scale Spatial Pyramid Attention (MSPA) module is incorporated to aggregate regional features across different spatial scales, and Coordinate Attention (CA) is used to encode positional cues for spatially refined feature learning. To further enhance viewpoint robustness, we design an azimuth-guided training strategy that selects hard positive samples with significant viewpoint discrepancies and optimizes them using an azimuth-aware auxiliary loss function.Experimental results on multiple benchmark datasets indicate that MscaVPR generally outperforms the strong baseline and demonstrates improved performance under challenging conditions. In particular, Recall@1 is improved by 2.1%, 1.9%, and 1.9% on the AmsterTime, SVOX-Night, and SVOX-Sun datasets, respectively. The results demonstrate that explicitly incorporating azimuth cues provides an effective complement to existing multi-scale and attention-based VPR methods. Full article
(This article belongs to the Section Navigation and Positioning)
►▼ Show Figures

Figure 1

32 pages, 1124 KB  
Article
An Inverse Generalized Conversion Filter for State Estimation in Nonlinear Adversarial Sensing Systems
by Yi-An Xi, Xin-Hao Dong and Sun-Yong Wu
Sensors 2026, 26(10), 3260; https://doi.org/10.3390/s26103260 - 21 May 2026
Viewed by 301
Abstract
In adversarial games involving intelligent sensing systems, inverse filtering plays an important role in the defender’s decision-making by estimating the opponent’s perception based on the defender’s sensor observations. Existing inverse nonlinear filters, such as the inverse quadrature Kalman filter and the inverse extended [...] Read more.
In adversarial games involving intelligent sensing systems, inverse filtering plays an important role in the defender’s decision-making by estimating the opponent’s perception based on the defender’s sensor observations. Existing inverse nonlinear filters, such as the inverse quadrature Kalman filter and the inverse extended Kalman filter, are limited in their ability to fully exploit higher-order nonlinear information contained in sensor observations. To address this issue, this paper proposes an inverse generalized-conversion-based filter (I-GCF). Unlike conventional inverse filters, the proposed method not only extracts nonlinear information through deterministic sampling but also constructs a generalized optimal decorrelating transformation function to capture nonlinear observation information that cannot be obtained by the linear minimum mean-square error (LMMSE) estimator. As a result, it enhances the exploitation of higher-order nonlinear sensor information and improves the estimation accuracy and stability of inverse filtering in nonlinear sensing environments. Furthermore, this paper derives general expressions for the time complexities of both GCF and I-GCF, thereby further enriching their theoretical framework. Numerical results demonstrate that, in nonlinear environments, the proposed I-GCF achieves higher estimation accuracy and better stability than conventional inverse filters. Full article
(This article belongs to the Section Electronic Sensors)
►▼ Show Figures

Figure 1

15 pages, 2746 KB  
Article
DGrA: Lightweight Modulation Recognition Based on Hybrid Neural Networks
by Xu Chen, Rui Gao, Ding Xu and Hongbo Zhu
Sensors 2026, 26(10), 3259; https://doi.org/10.3390/s26103259 - 21 May 2026
Viewed by 444
Abstract
Automatic modulation recognition has been recognized as an effective technique for non-cooperative communication and intelligent transmission. In this paper, we propose a new lightweight method for automatic modulation recognition, aiming to extract crucial discriminative features of signals for higher recognition accuracy while reducing [...] Read more.
Automatic modulation recognition has been recognized as an effective technique for non-cooperative communication and intelligent transmission. In this paper, we propose a new lightweight method for automatic modulation recognition, aiming to extract crucial discriminative features of signals for higher recognition accuracy while reducing spatial costs. To enhance the dissimilarity between samples, this paper combines an improved attention block and convolutional operations with the recurrent neural network, focusing on key features during the training phase to efficiently differentiate signal sequences. By replacing standard convolutions with depthwise separable convolutions, the model’s computational complexity is reduced while enhancing its feature extraction capability. Furthermore, the method incorporates pruning to reduce ineffective features, decreasing the model size while maintaining performance. Experimental results on RadioML2016.10a demonstrate that the proposed method outperforms other comparative methods, exhibiting both higher recognition accuracy and smaller model size. To validate real-world applicability, the algorithm was implemented on a software-defined radio platform for signal transmission and reception under practical conditions, achieving an accuracy of 87.22% in the presence of environmental noise, thus confirming its effectiveness in real-world scenarios. Full article
(This article belongs to the Special Issue Intelligent Signal Processing Techniques for Wireless Communications)
►▼ Show Figures

Figure 1

22 pages, 2625 KB  
Article
Lens Antenna Arrays for THz Superconducting HEB Mixers: A Review and a Metasurface Coupling Approach
by Yuner Gan, Ruiguang Peng, Shijia Feng, Maimai Mu and Qian Wang
Sensors 2026, 26(10), 3258; https://doi.org/10.3390/s26103258 - 21 May 2026
Viewed by 586
Abstract
Terahertz hot electron bolometer (HEB) mixers, which offer the highest sensitivity in the frequency range above 1.5 THz, are equipped on space observatories to detect the terahertz radiation emitted from the interstellar medium within galaxies. To increase the mapping speed, it is essential [...] Read more.
Terahertz hot electron bolometer (HEB) mixers, which offer the highest sensitivity in the frequency range above 1.5 THz, are equipped on space observatories to detect the terahertz radiation emitted from the interstellar medium within galaxies. To increase the mapping speed, it is essential to develop large HEB mixer arrays. However, conventional quasi-optical coupling methods, including single large silicon lens approaches and silicon lens array approaches, suffer from the conflict of achieving high filling factor and uniform illumination on the HEB mixer array. This paper reviews the research progress on quasi-optical coupled HEB mixer arrays and proposes an innovative array coupling scheme to overcome the existing limitation. We designed a metasurface beam shaper based on the Gerchberg–Saxton algorithm and COMSOL simulation to transform an incoming Gaussian beam into a flattop beam in the focal plane, thereby forming uniform illumination for an antenna-coupled HEB mixer array. The metasurface is intended primarily for uniform local oscillator (LO) distribution across the array. The simulation of the metasurface beam shaper at 0.6 THz demonstrates a flattop beam with a flat region approximately 3 mm wide, and the intensity across this region varies by only 4.2%. The same simulation is also performed at 1.6 THz, and the flat region is 1.5 mm wide with a 5.5% intensity variation. This work demonstrates the feasibility of using a metasurface to convert a Gaussian beam into a flattop beam at terahertz frequencies as well as a pathway for array-level coupling schemes for HEB mixer arrays with high filling factor and uniform illumination. Full article
(This article belongs to the Section Physical Sensors)
►▼ Show Figures

Graphical abstract

24 pages, 6719 KB  
Article
Design and Initial Evaluation of a Low-Cost Microprocessor-Controlled Ankle Prosthesis
by Zhanar Bigaliyeva, Abu-Alim Ayazbay, Sayat Akhmejanov, Nursultan Zhetenbayev, Aidos Sultan, Yerkebulan Nurgizat, Abu Jazar Ussam, Gulzhamal Tursunbayeva, Arman Uzbekbayev, Kassymbek Ozhikenov, Gani Sergazin and Yelubayeva Lazzat
Sensors 2026, 26(10), 3257; https://doi.org/10.3390/s26103257 - 21 May 2026
Viewed by 598
Abstract
Lower-limb amputation remains a significant clinical and socio-economic challenge, while the high cost of microprocessor-controlled prostheses (MPKs) limits their widespread accessibility. This paper presents the design and preliminary laboratory-scale evaluation of a low-cost microprocessor-controlled ankle prosthesis intended as a feasibility-oriented alternative platform for [...] Read more.
Lower-limb amputation remains a significant clinical and socio-economic challenge, while the high cost of microprocessor-controlled prostheses (MPKs) limits their widespread accessibility. This paper presents the design and preliminary laboratory-scale evaluation of a low-cost microprocessor-controlled ankle prosthesis intended as a feasibility-oriented alternative platform for future active prosthetic system development. Building upon the previously developed V1 mechanical architecture, an updated CAD model was created in the SolidWorks 2024 environment, and the kinematic configuration was refined using a ball-screw transmission (SFU1204-300) driven by a NEMA 17 stepper motor. The electronic control system integrates an ESP32 microcontroller, an MPU9250 inertial measurement unit (IMU), a limit switch for initial-position detection, and a WiFi-based REST API interface for communication and control. Laboratory no-load experiments demonstrated controlled positional behavior, repeatable angular response, and successful operation of the homing procedure within a motion range of 0–4200 motor steps. The prototype actively generated dorsiflexion–plantar flexion motion in the sagittal plane, while a passive inversion–eversion mechanism was incorporated and intended to improve structural adaptability. IMU-based measurements enabled preliminary monitoring of angular displacement and positional behavior during the experiments. The presented prototype represents an initial engineering feasibility study of a low-cost active ankle actuation architecture and provides a foundation for future investigations involving load-bearing experiments, biomechanical gait analysis, and closed-loop control implementation. Full article
(This article belongs to the Section Sensors and Robotics)
►▼ Show Figures

Figure 1

13 pages, 233 KB  
Article
Wearable-Measured Physical Activity Goal Adherence and Body Composition Change in a 12-Month mHealth Weight Loss Trial
by Zhadyra Bizhanova, Lora E. Burke, Maria M. Brooks, Bonny Rockette-Wagner, Jacob K. Kariuki and Susan M. Sereika
Sensors 2026, 26(10), 3256; https://doi.org/10.3390/s26103256 - 21 May 2026
Viewed by 396
Abstract
Background: Wearable activity trackers are commonly used in mHealth weight loss interventions, but evidence linking adherence to moderate-to-vigorous physical activity (MVPA) goals with changes in body composition is limited. We examined associations between adherence to study-prescribed MVPA goals and changes in percent body [...] Read more.
Background: Wearable activity trackers are commonly used in mHealth weight loss interventions, but evidence linking adherence to moderate-to-vigorous physical activity (MVPA) goals with changes in body composition is limited. We examined associations between adherence to study-prescribed MVPA goals and changes in percent body fat and sex-specific waist circumference (WC) over 12 months in the SMARTER trial. Methods: Participants (N = 502, 79.5% female; mean age 45 years; mean BMI 33.7 kg/m2) were randomized to self-monitoring of diet, PA, and weight (SM) or SM plus daily tailored feedback messages (SM + FB). Weekly adherence to ≥300 min/week of MVPA was quantified using Fitbit-derived equivalents. Associations between MVPA adherence and changes in percent body fat and sex-specific WC over 12 months were examined using linear mixed models. Results: Among the full sample, greater MVPA adherence was associated with reductions in body fat (b = −0.01; 95% CI: −0.02, −0.005), but not in WC (women: b = −0.01; −0.03, 0.01; men: b = −0.03; −0.05, 0.0002). Among the completers, higher adherence was associated with decreases in body fat (b = −0.01; −0.02, −0.004) and WC (women: b = −0.02; −0.04, −0.004; men: b = −0.04; −0.08, −0.003). Conclusions: Higher MVPA adherence was associated with favorable changes in adiposity over 12 months, supporting the use of wearable-derived PA measures in long-term mHealth behavioral interventions. Full article
(This article belongs to the Special Issue Wearable Sensors and Signal Processing Technology for Digital Health Applications)
24 pages, 12170 KB  
Article
SA-YOLOv11s: A Slicing-Attention YOLOv11s with U-IoU for Oil Leakage Detection in Power Equipment
by Daoyuan Liu, Chenlei Liu, Zhijuan Wang, Shiji Zhang, Yulong Yang, Tong Zhao and Xiaolong Wang
Sensors 2026, 26(10), 3255; https://doi.org/10.3390/s26103255 - 20 May 2026
Viewed by 411
Abstract
To address the challenges of low detection accuracy and high missed detection rates in insulating oil leakage detection for power equipment—arising from small and densely distributed oil stains, structural occlusion, and complex background interference—this paper proposes a detection method based on an enhanced [...] Read more.
To address the challenges of low detection accuracy and high missed detection rates in insulating oil leakage detection for power equipment—arising from small and densely distributed oil stains, structural occlusion, and complex background interference—this paper proposes a detection method based on an enhanced YOLOv11s (You Only Look Once version 11 small) architecture. First, a dedicated dataset is constructed, encompassing four representative scenarios—small object detection, complex background, multi-object detection and equipment occlusion—to evaluate detection performance. Second, in terms of network design, a proposed attention module, SimAMWS (Simple Attention Module With Slicing), is introduced. This module enhances the model’s sensitivity to subtle and irregular oil stains by utilizing slicing operations and localized energy-based weighting. For bounding box regression, a U-IoU (Unified Intersection over Union) loss is adopted, which incorporates a dynamic scaling mechanism during training to enable the model to focus more effectively on high-quality candidate boxes—leading to improved localization accuracy, particularly suited to the characteristics of oil leakage. Finally, comparative experiments are conducted against mainstream object detectors including SSD (Single Shot MultiBox Detector), Faster R-CNN (Region-based Convolutional Neural Network), YOLOv5s, YOLOv8s, and the baseline YOLOv11s. The proposed method achieves an mAP@0.5 (mean Average Precision at IoU = 0.5) of 97.7% and an mAP@0.5:0.95 of 66.9%, with an inference speed of 96.4 FPS. These results demonstrate that the proposed model delivers higher detection accuracy while maintaining high inference efficiency, making it well-suited for real-time oil leak detection in power equipment and supporting the development of intelligent operation and maintenance systems in the power industry. Full article
(This article belongs to the Special Issue Advances in Sensors and Metering Solutions for Smart Grids)
►▼ Show Figures

Figure 1

17 pages, 3452 KB  
Article
Deep Learning-Based Heartbeat Detection from 3D Seismocardiography for Robust Heart Rate Monitoring
by Sobuz Rana, Jukka A. Lipponen and Mika P. Tarvainen
Sensors 2026, 26(10), 3254; https://doi.org/10.3390/s26103254 - 20 May 2026
Viewed by 494
Abstract
Accurate monitoring of heart rate (HR) is critical for assessing cardiac functions in a wide range of health and wellness applications. Seismocardiography (SCG), which captures subtle chest vibrations using wearable accelerometers, provides a non-invasive and cost-effective approach for resting and nocturnal HR monitoring. [...] Read more.
Accurate monitoring of heart rate (HR) is critical for assessing cardiac functions in a wide range of health and wellness applications. Seismocardiography (SCG), which captures subtle chest vibrations using wearable accelerometers, provides a non-invasive and cost-effective approach for resting and nocturnal HR monitoring. This study presents a deep learning-based approach for accurate heartbeat detection and HR estimation from three-dimensional SCG signals. The model was trained on a large-scale dataset of resting SCG signals collected from 6600 subjects and evaluated on an independent cohort of 947 individuals. For short-term (≤5 min) resting SCG recordings, the model achieved robust performance in heartbeat detection (PPV: 0.979, sensitivity: 0.916, F1-score: 0.946). HR estimation showed high accuracy, with a mean absolute error (MAE) of 0.27 bpm, root mean square error (RMSE) of 1.02 bpm, and correlation of 0.996 with the reference HR. To assess real-world applicability, the model was further evaluated on 28 nocturnal recordings acquired using Apple Watch accelerometer, yielding an MAE of 1.10 bpm, an RMSE of 1.88 bpm, and a correlation of 0.982. The proposed SCG-based deep learning model demonstrates robust and highly accurate HR monitoring in both resting and nocturnal conditions, highlighting its potential for integration with consumer-grade wearable devices in a server-based analysis pipeline. Full article
(This article belongs to the Special Issue Human Signal Processing Based on Wearable Non-Invasive Device: 2nd Edition)
►▼ Show Figures

Figure 1

15 pages, 1273 KB  
Article
Early Detection of Spoofing Threats and Network Resilience Prediction in Drones Based on GRU and LSTM
by ChungMan Oh, JaePil Youn, WonHo Ryu and KyungShin Kim
Sensors 2026, 26(10), 3253; https://doi.org/10.3390/s26103253 - 20 May 2026
Viewed by 404
Abstract
As unmanned aerial vehicles (UAVs) are increasingly deployed in mission-critical domains such as military operations, infrastructure inspection, and disaster response, the threat of GPS and network spoofing attacks has emerged as a fundamental challenge to operational continuity. Existing intrusion detection systems based on [...] Read more.
As unmanned aerial vehicles (UAVs) are increasingly deployed in mission-critical domains such as military operations, infrastructure inspection, and disaster response, the threat of GPS and network spoofing attacks has emerged as a fundamental challenge to operational continuity. Existing intrusion detection systems based on threshold rules or shallow machine learning models are inherently limited in their ability to identify the latent onset of sophisticated, gradually intensifying spoofing campaigns—a gap that motivates the present work. This study proposes a deep learning-based early detection and network resilience prediction framework that employs Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) architectures operating on three spatio-temporal network features—Hop Count Spike Rate (HCS), Packet Drop Volatility (PDV), and Spatial Disconnect Density (SDD)—proposed in this study. To reflect realistic adversarial conditions, we design a Gradual Adaptive Attacker model in which the spoofing intensity escalates progressively across six operational phases, including a second-stage adaptive attack that modulates its gradient upon detecting initial countermeasures. Both models are trained on 1000 simulated runs using sliding-window time-series sequences and evaluated across 500 independent test runs with paired statistical testing. The GRU model achieves a mean ROC-AUC of 0.9915 (±0.0091) and a mean F1-Score of 0.9099 (±0.0462), outperforming LSTM across all metrics with statistical significance at p < 0.001 under both the paired t-test and the Wilcoxon signed-rank test. Critically, GRU detects spoofing onset with an average latency of 0.503 time steps—approximately 29.4% faster than LSTM (0.712 steps)—a difference confirmed as statistically significant (p < 0.001, Cohen’s d = 0.41). Network resilience simulations further demonstrate that integrating GRU-based autonomous evasion maintains a Connectivity Ratio (CR) above 80% even under severe attack phases, whereas passive networks experience total connectivity collapse (CR = 0%). These findings establish GRU as the superior architecture for real-time UAV edge deployment and affirm that the proposed pipeline extends beyond threat alerting to actively preserving mission continuity under adversarial spoofing conditions. Full article
(This article belongs to the Special Issue Advanced Sensing Technologies and Cybersecurity for UAV Systems)
►▼ Show Figures

Figure 1

30 pages, 11018 KB  
Article
A Hybrid Deep Learning Architecture for Content Request Prediction in the Internet of Vehicles
by Assem Rezki, Lyamine Guezouli, Abderrezak Benyahia, Djallel Eddine Boubiche, Mohamed Zohir Mabane, Sohaib Chine, Homero Toral-Cruz, Rafael Martínez-Peláez and Julio Cesar Ramirez-Pacheco
Sensors 2026, 26(10), 3252; https://doi.org/10.3390/s26103252 - 20 May 2026
Viewed by 419
Abstract
Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term [...] Read more.
Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions. Full article
(This article belongs to the Section Vehicular Sensing)
►▼ Show Figures

Figure 1

21 pages, 13837 KB  
Article
Adaptive Template Update and Re-Detection Network Based on Tracking Confidence
by Wanxin Wu, Yuxuan Ding and Kehua Miao
Sensors 2026, 26(10), 3251; https://doi.org/10.3390/s26103251 - 20 May 2026
Viewed by 327
Abstract
Siamese tracking is widely used in object tracking due to its efficient dual-branch symmetric structure, deep feature matching mechanism, and flexible template strategy. Existing mainstream Siamese tracking algorithms typically employ static template matching or linear combination-based template updating to localize the target in [...] Read more.
Siamese tracking is widely used in object tracking due to its efficient dual-branch symmetric structure, deep feature matching mechanism, and flexible template strategy. Existing mainstream Siamese tracking algorithms typically employ static template matching or linear combination-based template updating to localize the target in the next frame. However, these mechanisms often struggle to ensure template accuracy in complex environments involving changes in target appearance, scale, occlusion, and motion blur, thereby compromising robustness and stability. To address these issues, this paper proposes a confidence-guided adaptive template update with a re-detection (CATUR) network. CATUR constructs a tracking confidence assessment module that uses average peak-to-correlation energy (APCE) and a dynamic threshold mechanism to determine the current tracking state, providing a basis for template updates and target re-detection. It also designs an adaptive template update network that effectively combines the initial, historical, and current-frame templates, enhancing adaptation to target appearance variations. By integrating a global search module and a re-detection module, CATUR achieves precise target re-localization, rapid template updating, and tracking recovery. Extensive experiments and ablation studies on LaSOT and TrackingNet demonstrate that CATUR improves AUC, PNorm, and P by 4.0%, 4.0%, and 3.2%, respectively, significantly enhancing tracking accuracy and robustness in complex environments. Full article
(This article belongs to the Section Sensing and Imaging)
►▼ Show Figures

Figure 1

18 pages, 5182 KB  
Article
Photonics-Aided 20 m Wireless Transmission of 56-GBaud OFDM Signals at 138 GHz in the D-Band for 6G Applications
by Hanyu Zhang, Zhongxiao Pei, Qinyi Zhang, Yifan Chen and Jianjun Yu
Sensors 2026, 26(10), 3250; https://doi.org/10.3390/s26103250 - 20 May 2026
Viewed by 305
Abstract
To meet the demand for high-capacity indoor wireless access in future 6G systems, we propose and experimentally demonstrate a photonics-aided D-band wireless transmission scheme operating at 138 GHz. At the transmitter, two external-cavity lasers together with an I/Q modulator are used to generate [...] Read more.
To meet the demand for high-capacity indoor wireless access in future 6G systems, we propose and experimentally demonstrate a photonics-aided D-band wireless transmission scheme operating at 138 GHz. At the transmitter, two external-cavity lasers together with an I/Q modulator are used to generate a modulated D-band carrier. At the receiver, homodyne down-conversion is employed to directly recover the received signal to baseband, thereby relaxing the requirements on ultra-wideband analog components and high-speed sampling hardware. A 20 m indoor line-of-sight wireless link is established to transmit a 56-Gbaud-rate OFDM-QPSK signal. The transmitted and received spectra, received constellations and bit-error-rate (BER) performance are functions of optical power at different symbol rates, and the channel amplitude and phase responses are systematically analyzed. The results show that broadband D-band signal generation, transmission, and recovery can be stably achieved in the proposed system. After receiver-side digital signal processing (DSP), clear QPSK constellations are obtained. BER measurements reveal an optimal optical-power operating range, and the 32-GBaud OFDM signal outperforms the 56-Gbaud-rate signal because its narrower occupied bandwidth makes it less sensitive to frequency-selective distortion. For 56-Gbaud-rate OFDM transmission, the BER approaches the 20% low-density parity-check forward-error-correction threshold at an optical power of approximately −1 dBm. Further analysis indicates that the current link performance is mainly limited by frequency-selective amplitude and phase distortions under bandwidth-constrained conditions, together with slight nonlinear effects at high power. These results verify the feasibility of a photonics-aided D-band wireless architecture with homodyne reception for medium-range, high-symbol-rate indoor transmission and provide an experimental basis for future 6G sub-THz wireless links. Full article
(This article belongs to the Special Issue Recent Development of Millimeter-Wave Technologies)
►▼ Show Figures

Figure 1

52 pages, 7231 KB  
Systematic Review
The Evolution of Data-Driven Management Zone Delineation: A Systematic Review
by Roghayeh Heidari, Reza Khanmohammadi and Faramarz F. Samavati
Sensors 2026, 26(10), 3249; https://doi.org/10.3390/s26103249 - 20 May 2026
Viewed by 441
Abstract
By partitioning agricultural fields into units with similar yield-limiting factors, Management Zone (MZ) delineation provides the spatial basis for variable-rate application of inputs such as nitrogen, seed, and irrigation. To evaluate the operational implementation of MZ methodologies, this paper analyzes 137 peer-reviewed papers [...] Read more.
By partitioning agricultural fields into units with similar yield-limiting factors, Management Zone (MZ) delineation provides the spatial basis for variable-rate application of inputs such as nitrogen, seed, and irrigation. To evaluate the operational implementation of MZ methodologies, this paper analyzes 137 peer-reviewed papers published between 2000 and 2025, extracting data on agronomic contexts, sensing inputs, computational workflows, and validation strategies. Our analysis reveals a clear methodological shift: while early studies relied heavily on data such as soil properties, recent literature is dominated by multisource data fusion that combines static soil proxies (e.g., apparent electrical conductivity) with dynamic remote sensing vegetation indices. Methodologically, the literature relies heavily on similarity-based clustering, specifically fuzzy c-means and k-means, often applied to raw spatial grids or Principal Component Analysis (PCA) transformations. Although machine learning and optimization-based approaches have increased in recent years, rigorous agronomic and economic validation remains limited, while internal cluster validity indices (e.g., FPI, NCE) and inferential statistical tests (e.g., ANOVA) are widely used to assess delineated zones, only 13 of the reviewed papers explicitly evaluated the economic or environmental net returns of the delineated zones. To transition MZ delineation from a classification problem to an operational decision-support tool, the current literature suggests a need to shift validation efforts away from internal clustering metrics toward multi-year yield stability assessments and direct economic cost–benefit analyses. Full article
(This article belongs to the Special Issue Innovations in Remote Sensing and AI-Enabled Sensing for Smart Agriculture)
►▼ Show Figures

Figure 1

23 pages, 5342 KB  
Article
A High-Performance Ultraviolet Optical Sensing System for Rotating Detonation Extreme Combustion
by Wen Dai, Yingchen Shi, Junhui Ma, Mingyang Bu, Lingxue Wang, Qiaofeng Xie, Haocheng Wen and Bing Wang
Sensors 2026, 26(10), 3248; https://doi.org/10.3390/s26103248 - 20 May 2026
Viewed by 377
Abstract
Extreme combustion features strong unsteadiness, heterogeneity and multi-physics coupling, which is of great significance for advanced propulsion systems. High-performance sensing of such extreme combustion flow fields is critical to revealing physical mechanisms and capturing fine flow structures. However, it faces severe challenges: rich [...] Read more.
Extreme combustion features strong unsteadiness, heterogeneity and multi-physics coupling, which is of great significance for advanced propulsion systems. High-performance sensing of such extreme combustion flow fields is critical to revealing physical mechanisms and capturing fine flow structures. However, it faces severe challenges: rich multi-band spectral characteristics require multi-spectral observation; ultra-transient processes demand high-frequency imaging; and high-performance photoelectric enhancement is necessary under short gate width and high frame rates. To solve these problems, this study developed a high-performance ultraviolet optical sensing system (HUOSS), which achieves megahertz-level imaging at a 1608 × 1104 full-frame resolution and provides a 107 electron gain in the ultraviolet band. The HUOSS has been applied to chemiluminescence sensing of a hydrogen/ammonia-air rotating detonation as a representative extreme combustion system. Based on the analysis of representative influencing factors (e.g., the transmission characteristic of the bandpass filter and the intensifier gate width) in the HUOSS, the filter transmission loss and its influence on the gate width settings have been revealed. From the chemiluminescence sensing images captured in the experiments, the fine structure and evolution of detonation waves have been clearly identified, verifying the high-speed imaging capability. Furthermore, simultaneous OH* and NH* multi-spectral observation has been realized, and the effects of ammonia addition have been analyzed, validating the multi-spectral diagnostic capacity of the system. This study provides an effective diagnostic method for extreme transient combustion research, and comprehensively verified the multi-spectral, extremely transient and high signal-to-noise ratio sensing capabilities of this system. Full article
(This article belongs to the Section Sensing and Imaging)
►▼ Show Figures

Figure 1

22 pages, 2148 KB  
Article
Autonomous UAV Target Search Method Based on Lightweight YOLOv8n and Coverage Path Planning
by Haoyan Duan, Zhenhua Wang, Mengtong Li, Zhenbo He and Haoxuan Zhang
Sensors 2026, 26(10), 3247; https://doi.org/10.3390/s26103247 - 20 May 2026
Viewed by 479
Abstract
Unmanned aerial vehicles (UAVs) have wide application prospects in disaster search and rescue, ecological monitoring and environmental inspection tasks, where target search is a key link to realize autonomous task execution. UAVs often face challenges related to limited onboard computational resources and inefficient [...] Read more.
Unmanned aerial vehicles (UAVs) have wide application prospects in disaster search and rescue, ecological monitoring and environmental inspection tasks, where target search is a key link to realize autonomous task execution. UAVs often face challenges related to limited onboard computational resources and inefficient environmental coverage when used for target search. To address these issues, this paper proposes an autonomous search method for UAVs based on combined lightweight target detection and coverage path planning. In this method, the target search task was decomposed into two core parts: target recognition and path planning. Firstly, in terms of target recognition, the YOLOv8n model was subjected to channel pruning and INT8 quantization to reduce its computational complexity, while HSV space data augmentation was incorporated to enhance recognition robustness in complex environments. Secondly, path planning was formulated as a dual-layer task comprising “spatial coverage + target confirmation.” A grid-based search environment model was constructed, and a coverage path planning strategy was put forward that integrated breadth-first search (BFS) with local greedy optimization to achieve efficient traversal of predefined search areas. Simultaneously, the A* algorithm was employed for path backtracking to cover omitted regions. Finally, a simulation platform for UAV target search was built to validate the recognition performance and search efficiency of the proposed method. The experimental results demonstrated that the proposed method significantly improved the UAV target search efficiency and reduced the path redundancy while ensuring the recognition accuracy, thereby offering an effective solution for autonomous UAV search on resource-constrained embedded platforms. Full article
(This article belongs to the Section Navigation and Positioning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-361
Previous Issue
Next Issue
Back to TopTop