{"title":"A Multiclass Time-Series Signal Recognition Method Based on a Large Active Radar Jamming Database","authors":"Xiaoying Feng;Xiaoyu Zhang;Kunpeng He;Panlong Tan;Yutong Tang","doi":"10.1109/JSEN.2025.3561367","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3561367","url":null,"abstract":"Active radar jamming recognition is a crucial technology in electronic countermeasures (ECMs). To tackle the challenge of intelligent recognition of complex radar jamming signals, we introduce the large-scale active radar jamming database (LARJD). This comprehensive database includes 19 distinct types of jamming signals and contains a total of 66500 time-series samples across five radar frequency bands, providing a robust dataset for radar jamming signal recognition. In parallel, we propose the multiclass time-series signal recognition network (MTSS-2DCNN), a deep learning architecture designed for classifying multiple types of time-series signals, including radar jamming signals. The MTSS-2DCNN architecture comprises three 2-D convolutional neural networks (2DCNNs), which extract features from both the time- and frequency-domain representations of the time-series data. By using a 2-D network structure to process 1-D signals, MTSS-2DCNN captures high-dimensional features from sequential signals while preserving the inherent characteristics of the temporal data. The model’s generalization capability is further enhanced through K-fold cross-validation and an adaptive learning rate adjustment strategy. Experimental results demonstrate that the proposed method achieves an impressive accuracy of over 99.67% on the LARJD, with significantly shorter training times compared to existing approaches. Moreover, by pretraining radar jamming signal recognition models, ECM applications can substantially improve the efficiency of intelligent recognition systems in both engineering and military contexts.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20051-20066"},"PeriodicalIF":4.3,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205905","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}
Bo Li;Keshuai Yang;Yizhao Zhou;Chengbing Fang;Chengqi Zhang;Xian Song;Yaoran Sun;Pengyu Wang;Tong Li;Yuxin Peng;Fang Han
{"title":"Pressure Sensor Based on Melamine Frame Graphene Aerogel for Pulse Recording and Identification in Traditional Chinese Medicine","authors":"Bo Li;Keshuai Yang;Yizhao Zhou;Chengbing Fang;Chengqi Zhang;Xian Song;Yaoran Sun;Pengyu Wang;Tong Li;Yuxin Peng;Fang Han","doi":"10.1109/JSEN.2025.3561953","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3561953","url":null,"abstract":"In this article, we developed a graphene-melamine graphene aerogel sensor to integrate the traditional Chinese medicine (TCM) pulse diagnosis with modern information technologies. Owing to the reduced graphene oxide (GO) network embedded in the melamine frame, the sensor demonstrates a high gauge factor (GF) of 596.2 with high repeatability, enhancing the accuracy of pulse signal detection. Moreover, the porous structure of the sensing material augments its piezoresistive properties, exhibiting a “fast-then-slow” pattern in resistance changes. The reasonable pulse signal is collected by experienced TCM practitioners accurately locating specific pulse points—Cun, Guan, and Chi—and applying the optimal pressure with the proposed sensor adhered on their fingertip. By employing continuous wavelet transform (CWT) and ResNet-50 for advanced signal processing and classification, the study attains a classification accuracy of 90.1% in differentiating pulse patterns between pregnant and nonpregnant women. This high level of accuracy demonstrates the potential of integrating this technology to standardize and validate TCM diagnostic techniques, potentially broadening the acceptance of TCM in global health systems.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 12","pages":"21185-21193"},"PeriodicalIF":4.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308534","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":"Impact of By-Products From Metal Welding on the Temperature Measurement of MEMS-Based Thermoelectric Infrared Sensors","authors":"Changwen Shi;Yu Gao;Haozhu Chen;Jiagen Cheng;Weihuang Yang;Chaoran Liu;Linxi Dong","doi":"10.1109/JSEN.2025.3564062","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3564062","url":null,"abstract":"In metal welding processes, micro-electromechanical system (MEMS)-based thermoelectric infrared sensors are widely employed for real-time temperature monitoring to ensure weld quality. However, welding by-products, particularly fumes and molten metal spatter particles, introduce significant measurement errors in these sensors. This study investigates the mechanistic interaction between welding by-products and MEMS sensor performance, followed by systematic experimental analysis under varying operating conditions (object temperatures: <inline-formula> <tex-math>$30~^{circ }$ </tex-math></inline-formula>C–<inline-formula> <tex-math>$110~^{circ }$ </tex-math></inline-formula>C; measurement distances: 10–40 cm). A novel characterization method is proposed using binary classification of spatter-induced filter screen damage to quantify particle impact severity. Furthermore, a mathematical model is developed to correlate measurement error with temperature and distance variables, enabling real-time error compensation for by-product interference. Experimental validation demonstrates that the proposed compensation compensation algorithm reduces temperature measurement errors by up to 80.9% in high-spatter welding scenarios, demonstrating its practical utility in enhancing sensor reliability for industrial applications.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 12","pages":"22756-22764"},"PeriodicalIF":4.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299197","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":"A Lightweight and Explainable Hybrid Deep Learning Model for Wearable Sensor-Based Human Activity Recognition","authors":"Pratibha Tokas;Vijay Bhaskar Semwal;Sweta Jain","doi":"10.1109/JSEN.2025.3564045","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3564045","url":null,"abstract":"Human activity recognition (HAR) is critical for rehabilitation and clinical monitoring, but robust recognition using wearable sensors (e.g., sEMG or IMU) remains challenging due to signal noise and variability. We propose X-LiteHAR, a lightweight, explainable hybrid deep learning framework for real-time HAR, combining adaptive EEMD for noise-robust signal enhancement and a multihead CNN-LSTM for spatio-temporal feature learning. The optimized framework demonstrates efficient edge deployment through structured pruning and quantization, achieving 70% model size reduction while maintaining competitive performance, with on-device validation on an Android OnePlus 6T smartphone showing 9 ms inference latency. The model was trained and evaluated independently on two distinct datasets: 1) the UCI sEMG dataset (muscle activity signals) and 2) the IMU-only MHealth dataset (motion signals), demonstrating the architecture’s adaptability to different sensor modalities. On the UCI dataset, X-LiteHAR achieved 99.0% accuracy (healthy subjects) and 98.7% (pathological), while on MHealth (IMU-only), it reached 99.2% accuracy. Leveraging explainable AI (XAI), we interpret muscle activation patterns for personalized rehabilitation insights. By unifying signal processing, efficient deep learning, and interpretability, X-LiteHAR advances real-time HAR for clinical and wearable applications.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 12","pages":"22618-22628"},"PeriodicalIF":4.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299405","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":"Laser Interferometer With Harmonic Contrast Demodulation for Nanometer Distance Measurement","authors":"Jialin Jiang;Wentao Liu;Yang Xia;Zhaochun Deng;Xiaohua Lei;Zinan Wang;Weimin Chen","doi":"10.1109/JSEN.2025.3564166","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3564166","url":null,"abstract":"High-precision 3-D topography is essential for surface profile detection in chips, precision optical lenses, and other components. A nanometer-scale laser interferometric distance sensor serves as a key component in such applications. In this kind of sensor, displacement of the target or the measurement position change induces phase shifts in the laser interference signal. Piezoelectric ceramic transducers (PZTs) are commonly used as modulators, but their lifespan, linearity, and frequency response—key factors determining the sensor’s performance—are closely tied to the modulation depth. This article introduces a harmonic contrast (HC) method to demodulate phase changes with high speed, minimal modulation depth, and single-channel detection. For scenarios involving nonstandard phase modulation functions, such as those influenced by loaded PZTs, a novel calibration approach is proposed. This method enables precise calibration without relying on expensive nanometer-precision multistep mirrors, thereby reducing the dependence on stringent modulation depth and linearity requirements. As a result, the same modulator can achieve an extended lifespan and higher sensing frequencies, making it more suitable for industrial applications. Experimental results demonstrate a resolution of 0.7 nm for step displacement signals, showcasing the good performance of the proposed scheme.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 12","pages":"21617-21623"},"PeriodicalIF":4.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299165","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":"Age of Information in IoT Devices With Integrated Heterogeneous Sensors Under Slotted ALOHA","authors":"Show-Shiow Tzeng;Ying-Jen Lin;Sheng-Wei Wang","doi":"10.1109/JSEN.2025.3563452","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3563452","url":null,"abstract":"Sensors deployed in environments transmit status update data using the slotted ALOHA for radio channel access. The age-of-information (AoI) metric, representing the time elapsed since the last data received by a destination (e.g., base station) was generated at a sender, quantifies data freshness, which is crucial in diverse Internet of Things (IoT). Recent advancements have integrated heterogeneous sensors into IoT devices, with each sensor potentially sensing and generating status updates with different probabilities, impacting both AoI and energy consumption levels. This creates a complex challenge in balancing tradeoffs among various sensors’ sensing probabilities, AoI constraints, and energy efficiency. Yet, the AoI impact of IoT devices equipped with heterogeneous sensors using slotted ALOHA remains largely unexplored. This study investigates the AoI performance of IoT devices equipped with heterogeneous sensors within a slotted ALOHA framework. We present three data generation and transmission schemes: multisensor device with independent sensing (MSDIS), multisensor device with simultaneous sensing (MSDSS), and multisensor device with probabilistic simultaneous sensing (MSDPSS). We analyze and prove that MSDSS and MSDPSS achieve a lower average AoI (AAoI) compared with other schemes. Furthermore, we show that AAoI solutions for systems with at least five sensors per type cannot be expressed in radical form. Hence, we further design a low-time-complexity procedure for MSDPSS to determine optimal data sensing and generation probabilities that meet diverse AAoI requirements of various sensors while minimizing energy consumption. Our analysis, validated by simulations, indicates that MSDPSS demonstrates superior energy efficiency while meeting the diverse AAoI requirements of various sensors.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20842-20853"},"PeriodicalIF":4.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196616","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}
Paris Vélez;Ferran Paredes;Pau Casacuberta;Xavier Canalias;Lijuan Su;Ferran Martín
{"title":"A Microwave Sensor System for the Unattended Control of Corrosion in Urban Metallic Infrastructures","authors":"Paris Vélez;Ferran Paredes;Pau Casacuberta;Xavier Canalias;Lijuan Su;Ferran Martín","doi":"10.1109/JSEN.2025.3564003","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3564003","url":null,"abstract":"This article presents a microwave sensor system (including the electromagnetic module and the associated electronics for signal generation and processing) useful for unattendedly monitoring the corrosion level in urban metallic infrastructures, particularly, streetlights and traffic lights. The electromagnetic module consists of a microstrip line loaded with a slot resonator, the sensitive element, transversely etched in the ground plane. To make the electromagnetic module conformal, a necessity for the intended application, the slot-loaded line has been implemented in a narrow (and hence flexible) low-loss microwave substrate. To adapt it to the circular shape of the metallic infrastructure, streetlights with different curvature shapes in the reported example cases, a conformal 3-D-printed piece of polylactic acid (PLA) has been fabricated. By sandwiching the electromagnetic module between such PLA piece and the surface of the streetlight subjected to corrosion control, perfect contact of it with the sensing element is achieved. The output variable of the sensor is the magnitude of the transmission coefficient of the slot-loaded line at a specific frequency (correlated with the level of corrosion of the surface) converted to a voltage by means of an envelope detector. The functionality of the proposed sensor is validated by means of a complete system, including the associated electronics.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 11","pages":"20455-20465"},"PeriodicalIF":4.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205860","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}
Youngwoo Lee;Seyeon Kim;Jinha Kim;Suhwan Kim;Jaehoon Jun
{"title":"A Low Power Digitizer Array With Adaptive Split Current Source for 3-D-Stacked 100 MP High Dynamic Range Imager","authors":"Youngwoo Lee;Seyeon Kim;Jinha Kim;Suhwan Kim;Jaehoon Jun","doi":"10.1109/JSEN.2025.3563964","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3563964","url":null,"abstract":"The increasing demand for high dynamic range (HDR), power efficiency, and high resolution has driven the adoption of single-exposure dual conversion gain (DCG) techniques. This article proposes an adaptive split current source to optimize power consumption in single-exposure DCG readouts. By splitting the comparator bias current, the power consumption of the digitizer array can be adaptively optimized based on the conversion gain (CG) of pixel in single-exposure DCG operation. Additional power-saving features including decision-feedback and auto-zeroing (AZ) power-down techniques are also implemented to further improve power efficiency. The proposed digitizer chip was fabricated in a 28 nm CMOS process, achieving a power consumption reduction of 44.5% in comparator. The integral nonlinearity (INL) was measured as +2.67/–2.34 LSB in high CG (HCG) and +2.95/–1.92 LSB in low CG (LCG). The input-referred random noise (RN) values of 2.17 LSB (HCG) and 2.41 LSB (LCG) were measured at an analog gain of 16, corresponding to <inline-formula> <tex-math>$93~mu ! {V}_{text {rms}}$ </tex-math></inline-formula> and <inline-formula> <tex-math>$103~mu ! {V}_{text {rms}}$ </tex-math></inline-formula>, respectively. The prototype chip shows a highly competitive figure of merit (FoM) of 2.41 mV<inline-formula> <tex-math>$cdot $ </tex-math></inline-formula>pJ/pixel/frame.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 12","pages":"22609-22617"},"PeriodicalIF":4.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299233","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}