IEEE Sensors Journal最新文献

{"title":"Low-Cost Magnetorheological Elastomer-Based Capacitive Flexible Sensor Arrays for Human--Machine Interaction and Wearable Sensing","authors":"Benyuan Fu;Hao Wang;Lin Jia;Xinxin Yuan;Zhiyuan Zou;Zhengqiu Xie","doi":"10.1109/JSEN.2026.3728160","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728160","url":null,"abstract":"Flexible tactile sensor arrays are widely used in human–machine interaction (HMI) and wearable sensing; however, achieving both high sensitivity and a wide detection range while maintaining a simple fabrication process remains challenging. This work presents a cost-effective flexible piezocapacitive sensor array based on a bilayer magnetorheological elastomer (MRE) dielectric architecture. The device consists of a carbonyl nickel-filled silicone rubber layer and a polyvinyl alcohol hydrogel (PVA-H) layer, forming a mechanically heterogeneous interface that enhances pressure-induced capacitance modulation through improved mechanical–dielectric coupling. In addition, magnetically induced particle structuring within the MRE promotes interfacial polarization and contributes to the dielectric response under compression. Compared with conventional single-layer capacitive sensors, the proposed architecture improves sensing performance without requiring complex microstructuring processes. The fabricated <inline-formula> <tex-math>$6times 6$ </tex-math></inline-formula> sensor array demonstrates stable operation, achieving sensitivities of 0.713 kPa ^-1 in the low-pressure range (0–60 kPa) and 2.483 kPa ^-1 in the high-pressure range (60–100 kPa), together with response and recovery times of approximately 120 ms. The device also exhibits good repeatability and consistency among sensing units. Practical demonstrations, including spatial pressure mapping, motion trajectory recognition, and human activity monitoring, verify its capability for real-time tactile sensing. This work provides a simple and scalable MRE-based bilayer dielectric design strategy for flexible capacitive sensors and shows potential for applications in wearable electronics, electronic skin, and intelligent human–machine interfaces.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30173-30181"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149175979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Microscale Perception and Dynamic Label Assignment Object Detection Network for UAV Visual Sensing Systems","authors":"Jiawu Hu;Congwen Peng","doi":"10.1109/JSEN.2026.3729613","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3729613","url":null,"abstract":"To address the annihilation of high-frequency features and the dense overlapping of small targets captured by uncrewed aerial vehicle (UAV)-borne visual sensors in complex high-altitude environments, this article proposes PCS-you only look once (YOLO), an end-to-end sensing data processing and physical signal optimization network. First, a microscale perception reconstruction mechanism is designed. By constructing a high-resolution P2 branch coupled with the content-aware physical feature reassembly operator (CARAFE), weak physical features are extracted from the bottom architecture for sensing feature alignment and spatial resampling, effectively overcoming spatial faults and signal aliasing. Second, to resolve bounding box matching conflicts triggered by weak features in dense sensor clutter, the simplified optimal transport assignment (SimOTA) dynamic label assignment strategy is introduced. It adaptively assigns optimal perception anchor boxes for elusive tiny targets based on global optimal transport. Experiments on the VisDrone2019 sensing dataset demonstrate that the improved algorithm achieves 49.4% precision and 42.4% recall. The mean average precision (mAP)@0.5 and mAP@0.5:0.95 reach 41.8% and 23.3%, outperforming the baseline YOLOv5s by 7.9% and 4.8%, respectively. As an efficient software compensation scheme, PCS-YOLO overcomes hardware optical resolution limits while ensuring the real-time performance of UAV edge sensing nodes, significantly enhancing the detection precision of dense, tiny physical targets.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"31618-31632"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Event Vision Datasets: A Review","authors":"Kiyadokht Moniri;Maria Martini","doi":"10.1109/JSEN.2026.3714055","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3714055","url":null,"abstract":"Event-based sensors asynchronously record changes in a scene, with high temporal resolution. This results in very low power consumption and high dynamic range, and their use is very promising in a wide range of applications, such as video surveillance and autonomous navigation. In order to develop appropriate tools (in particular based on machine learning) for the processing of this type of data, appropriate datasets are required. This article provides a comprehensive review of publicly available datasets composed of data captured using event-based visual sensors. We first categorize the existing datasets based on camera motion, that is, distinguishing datasets captured with fixed cameras, moving cameras, or both moving and fixed cameras; we consider separately synthetic ones. We further classify them based on sensor spatial resolution (high, low, and medium) and also distinguish datasets based on their main use case. Furthermore, we present comparative tables with key characteristics of each dataset, including camera type and lens specifications, resolution, recording modality, 3-D versus 2-D, content format, and file durations. A description of selected datasets is reported, including a description and first visualization of the data of the very recent (first) dataset. Our findings are intended to assist researchers in selecting appropriate datasets for their specific applications, including the development of novel machine-learning models and compression methods.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"29995-30010"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Lower Limb Joint Angles Based on Muscle Synergy Theory","authors":"Dingzhe Li;Xiaorong Guan;Meng Zhu;Zheng Wang;Changlong Jiang;Yu Bai;Xiwang Mao","doi":"10.1109/JSEN.2026.3728089","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728089","url":null,"abstract":"Rapid and accurate prediction of lower limb joint angles is crucial for exoskeleton control. This paper introduces a multidimensional Gumbel Copula function during preprocessing to enhance the statistical dependency among synergistic muscles, and proposes a method for predicting lower limb joint angles based on muscle synergy theory. In the experiments, surface electromyography (sEMG) signals were collected during squatting, running, level walking, and uphill walking. The collected data underwent preprocessing, and features were extracted from the sEMG signals using a sliding window method. Muscle synergy theory reflects the movement mechanisms and regulatory mechanisms of muscles during human motion. By utilizing muscle synergy weights to perform dimensionality reduction on the sEMG signal features, the number of features input into the Convolutional Neural Networks–iTransformer(CNN–iTransformer) prediction model was selected based on the magnitude of the synergy weights. Finally, the trained regression model was evaluated using the metrics root-mean-square error (RMSE), R², mean absolute error (MAE), and Pearson correlation coefficient (PCC). For the 16 participants, the average RMSE and MAE for knee joint angle prediction were 0.61° and 0.45°, respectively, while the average R² and PCC were 0.998 and 0.996, respectively. Compared with results from currently common muscle synergy-based dimensionality reduction methods, the method proposed in this article achieved the best prediction accuracy within an optimal prediction time. The results demonstrate the superior performance of the proposed method in knee joint angle prediction, which can facilitate the future development of lower limb exoskeletons and provide more precise assistance to users in medical and industrial fields.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"31583-31598"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intersection Traffic Flow Estimation Using Distributed Acoustic Sensing on Buried Road-Crossing Telecommunication Fibers","authors":"Fei Peng;Qing Dai;Yujie Zhang;Qiang Miao","doi":"10.1109/JSEN.2026.3731080","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3731080","url":null,"abstract":"Existing distributed acoustic sensing (DAS)-based traffic monitoring studies mainly use telecommunication fibers deployed parallel to roadways. In this geometry, vehicle-induced responses are indirectly coupled from the road surface to the buried fiber, and the signal quality can degrade under weak road–fiber coupling, low vehicle speed, light vehicles, or congested traffic. This limitation is particularly relevant at intersections, where vehicles frequently decelerate, queue, and turn, while reliable section-level traffic counting is still required. This article investigates an alternative sensing geometry enabled by existing urban telecommunication networks: buried telecommunication fiber segments that cross the roadway at intersections. An elasticity-based quasi-static strain model is first used to analyze the response mechanism of vehicles passing over road-crossing fiber segments. Field DAS measurements at a campus T-intersection show that such segments generate localized high-SNR strain responses near the crossing position, together with polarity reversal between adjacent sensing channels. Based on these sensor-response characteristics, a spatially constrained spatiotemporal imaging and crossing-event detection workflow is developed for vehicle counting at the intersection section. HS-FPN-YOLOv12 is used as the event detector and achieves an mAP@0.5 of 0.995 for the crossing class on the validation set. On an independent 48 h DAS dataset collected at the same road section, the proposed method captures the long-duration variation of intersection traffic flow. For the manually reviewed video periods, the estimated hourly counts achieve a MAPE of 2.82%. The results indicate that buried road-crossing telecommunication fibers can serve as practical distributed sensing units for low-cost infrastructure-side traffic monitoring at intersections.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"31185-31194"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fiber Optic Biosensors Exploiting Localized Surface Plasmon Resonance From Nonspherical Nanostructures: A Review","authors":"Amin Moslemi;Flavio Esposito;Stefania Campopiano;Michele Giordano;Lucia Sansone;Agostino Iadicicco","doi":"10.1109/JSEN.2026.3727701","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3727701","url":null,"abstract":"Fiber optic biosensors have emerged as powerful platforms for label-free detection due to their high sensitivity, compactness, chemical stability, and compatibility with remote and multiplexed operation. The integration of plasmonic nanostructures with optical fibers enables localized surface plasmon resonance (LSPR)-based transduction, enhancing detection performance through strong light-matter interactions at the nanoscale. In this context, while spherical gold nanoparticles (GNPs) have been extensively investigated, growing attention is now directed toward nonspherical geometries that offer improved spectral tunability and surrounding medium refractive index (SRI) sensitivity. This review provides a comprehensive assessment of recent advances in fiber optic biosensors exploiting LSPR from unconventional nanostructures, including nanorods, nanostars, nanotriangles, nanodiscs, and hollow nanoparticles. The discussion highlights how nanoparticle morphology governs resonance characteristics, SRI sensitivity, and detection limits across different fiber architectures from the last 15 years. Emphasis is placed on the entire development chain, covering fiber transducer design, nanostructure synthesis and characterization, surface functionalization, and bio-recognition strategies. Finally, the review offers a comprehensive framework for critically comparing the principal classes of nonspherical plasmonic nanostructures integrated with optical fibers, discussing their advantages, limitations, technology maturity, and future research directions toward novel biosensing systems.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"29960-29971"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multicomponent Trace Gas Detection Based on Multiorder Angular Resonance Modes in a Spherical--Cylinder Resonator With Microphone Array Enhancement","authors":"Dong Li;Lufang Liu;Qinduan Zhang;Tingting Zhang;Jiqiang Wang;Hongzhen Yu;Guo Sun;Minghe Wu;Sheng'ao Zhang;Hao Liu;Bo Zhao","doi":"10.1109/JSEN.2026.3727112","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3727112","url":null,"abstract":"A photoacoustic (PA) gas sensing system based on a spherical–cylindrical resonator (SCR) with multiorder angular resonance modes and a multiple microphone array enhancement strategy is proposed for trace detection of CH₄ and C₂H₂. By simultaneously exciting the 2nd- and 4th-order angular resonance modes, highly sensitive dual-gas detection was achieved. Finite element simulation results demonstrate that, compared with the conventional spherical resonator (SR), the acoustic pressure amplitudes of the SCR are enhanced by factors of 4.2 and 3.84 under the 2nd- and 4th-order angular resonance modes, respectively. In addition, the cylindrical structure shifts the acoustic pressure antinodes from the spherical cavity to the end of the cylinder. Combined with the unique acoustic field distribution of the angular resonance modes, a multiple microphone array system was designed, resulting in an approximately 7.33-fold increase in the PA signal amplitude compared with that of a single microphone. The excellent performance of the proposed system was experimentally validated. Allan deviaton analysis indicates that minimum detection limits (MDLs) of 23.27 ppb for CH₄ and 4.53 ppb for C₂H₂ were achieved at averaging times of 556 and 237 s, respectively, corresponding to normalized noise equivalent absorption (NNEA) coefficients of <inline-formula> <tex-math>${6.83}~times ~{10}^{-{9}}$ </tex-math></inline-formula> and <inline-formula> <tex-math>${1.48}~times ~{10}^{-{9}}$ </tex-math></inline-formula> <inline-formula> <tex-math>${mathrm {cm}}^{-{1}}{,}cdot $ </tex-math></inline-formula> W<inline-formula> <tex-math>${,}cdot $ </tex-math></inline-formula> <inline-formula> <tex-math>${mathrm {Hz}}^{-{1}/{2}}$ </tex-math></inline-formula>. The proposed SCR provides a new approach for multicomponent trace gas detection based on angular acoustic resonance modes.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30401-30408"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Object-Preserving Weather Translation for Automotive Synthetic Sensor Data Generation","authors":"Ahmad Mohammad;Tunc Alkanat;Mykola Pechenizkiy;Ashish Pandharipande","doi":"10.1109/JSEN.2026.3732282","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3732282","url":null,"abstract":"Deep generative models have enabled data synthesis and domain translation across sensing modalities. Weather-conditioned translation for automotive ranging sensor synthetic data generation, however, is an underexplored problem. In this work, we study weather translation as a sensor-domain synthesis problem for LiDAR and radar bird’s-eye-view representations. We propose WeatherTranslate, a conditional flow matching (CFM) model that performs translation between clear, rain, and snow conditions while preserving dynamic objects for cross-condition consistency. We present qualitative results and intrinsic quantitative evaluation on the Boreas dataset, demonstrating realistic addition and removal of weather artifacts in LiDAR and radar data.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"29950-29959"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11692444","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time-Domain Adversarial Network for High-Fidelity Radar Signal Separation Under Interrupted Sampling Repeater Jamming","authors":"Weiyu Zha;Jianyin Cao;Hao Wang;Wenming Yu","doi":"10.1109/JSEN.2026.3725273","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3725273","url":null,"abstract":"To achieve high-fidelity single-channel radar signal separation in complex electromagnetic environments heavily corrupted by coherent interference, this article proposes a time-domain network based on adversarial learning for interrupted sampling repeater jamming (ISRJ) suppression. With the complex-valued radar baseband signals represented as dual-channel real tensors to fully preserve phase information, a 1-D encoder–decoder generator augmented with an attention mechanism is designed to adaptively extract temporal dependencies and filter jamming features within the high-dimensional latent space. To ensure precise waveform reconstruction, two independent multiresolution discriminators (MRDs) are established to provide hierarchical adversarial supervision across multiple temporal scales. Furthermore, a physics-informed hybrid loss framework is introduced, which optimizes waveform shapes via a scale-invariant signal-to-noise ratio (SI-SNR) metric while simultaneously enforcing physical boundaries through multidomain constraints. Experimental results on simulated ISRJ data indicate that the proposed network achieves a signal distortion ratio (SDR) of 8.44 dB and a signal-to-jamming-plus-noise ratio (SJNR) of 14.81 dB after pulse compression (PC), outperforming representative traditional and deep-learning-based baselines under the tested simulation settings. Under the tested implementation environment, the proposed network achieves an average single-sample inference time of 8 ms, demonstrating its potential for low-latency radar signal processing.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30765-30777"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FATrack: Frequency Alignment for Robust Visual Object Tracking in Hazy Conditions","authors":"Haotai Sun;Jingyu Li;Zhenhai Zhang;Yilei Huang;Ruosong Wang;Yipan Cheng","doi":"10.1109/JSEN.2026.3732489","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3732489","url":null,"abstract":"Visual object tracking (VOT) methods for hazy conditions have advanced rapidly in recent years, effectively alleviating the pronounced performance degradation of conventional trackers caused by reduced contrast and loss of fine details in hazy conditions. However, most existing hazy condition tracking methods focus on feature extraction in the spatial domain, with limited exploitation of frequency-domain information. Even when frequency-domain features are introduced, the role of different frequency bands is rarely modeled explicitly, making it difficult to obtain stable and highly discriminative target representations when details are degraded in hazy scenes. To address this issue, we propose a frequency alignment tracker (FATrack), which incorporates frequency-domain information while preserving spatial-domain features. It constructs a multibranch feature mapping that jointly models spatial and frequency representations and explicitly captures the complementary contributions of different frequency bands, thereby enabling robust object tracking in hazy conditions. Specifically, we design a frequency representation alignment (FRA) module that enhances robustness under haze by enforcing consistency of frequency representations. In addition, we propose an enhanced consistency distillation (ECD) strategy, which imposes a consistency distillation constraint using supervision signals from augmented views to mitigate response shifts induced by degradation. Extensive experiments demonstrate that FATrack achieves superior performance to mainstream state-of-the-art trackers on hazy VOT benchmarks.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"31216-31226"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}