IEEE Sensors Letters最新文献_第4页

ZMP Estimation From Wearable Sensor Using Deep Learning for Gait Analysis 基于深度学习的可穿戴传感器ZMP估计

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-27 DOI: 10.1109/LSENS.2026.3668832

Nilesh Maske;Pratibha Tokas;Vijay Bhaskar Semwal;Neha Gaud

{"title":"ZMP Estimation From Wearable Sensor Using Deep Learning for Gait Analysis","authors":"Nilesh Maske;Pratibha Tokas;Vijay Bhaskar Semwal;Neha Gaud","doi":"10.1109/LSENS.2026.3668832","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3668832","url":null,"abstract":"Zero moment point (ZMP) is a key biomechanical indicator of dynamic gait stability, conventionally measured using force plates or pressure insoles that are costly and impractical for continuous wearable use. This work presents a low-cost wearable framework for ZMP estimation using only thigh–shank inertial measurement units (IMUs) and knee joint kinematics. A custom flex sensor-based insole was used solely to compute reference ZMP during training and evaluation. Data were collected from healthy subjects walking on flat and inclined treadmills. A bidirectional long short-term memory–artificial neural network model trained on synchronized IMU and knee angle data achieved subjectwise fivefold cross-validation RMSEs of 0.56 cm (mediolateral) and 0.09 cm (anterior–posterior), with corresponding <inline-formula><tex-math>$R^{2}$</tex-math></inline-formula> values of 0.82 and 0.90. Leave-one-subject-out evaluation demonstrated subject-independent generalization with a modest increase in error due to intersubject variability. Real-time deployment on an NVIDIA Jetson Nano achieved an average inference time of 9.2 ms with a quantized model size of 1.8 MB, enabling on-device ZMP estimation in controlled gait settings.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Large-Scale Fabrication of Fully Printed, Photoactivated Au Decorated Tin Oxide Based Room-Temperature NO2 Sensors With Ultrahigh Response on Paper Substrates 全印刷、光活化金修饰氧化锡基室温二氧化氮传感器在纸基上的超高响应的大规模制备

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-23 DOI: 10.1109/LSENS.2026.3667078

Siri Chandana Amarakonda;Manvendra Singh;Mohammed Hadhi Pazhaya Puthanveettil;Subho Dasgupta

{"title":"Large-Scale Fabrication of Fully Printed, Photoactivated Au Decorated Tin Oxide Based Room-Temperature NO2 Sensors With Ultrahigh Response on Paper Substrates","authors":"Siri Chandana Amarakonda;Manvendra Singh;Mohammed Hadhi Pazhaya Puthanveettil;Subho Dasgupta","doi":"10.1109/LSENS.2026.3667078","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3667078","url":null,"abstract":"Conventional metal oxide gas sensors require high-temperature operation (200 °C–300 °C), which limits integration with sustainable and biodegradable substrates and contributes to electronic waste. Herein, we demonstrate fully screen printed, room-temperature NO2 sensors using ultraviolet (UV)-photoactivated Au decorated SnO/SnO2 nanoparticles on paper. Tin oxide nanoparticles have been synthesized via precipitation and annealing, followed by controlled Au decoration (0.5 wt.%) through ascorbic acid reduction. Subsequently, screen printing enables scalable device fabrication with interdigitated Ag electrodes and Au-SnO/SnO2 sensing layers on photo paper. Under 365 nm UV illumination (2.1 mW/cm2), the sensors have exhibited an excellent response of 871 for 3.2 ppm NO2 at room temperature. The devices demonstrate remarkable sensitivity across 1.4–3.2 ppm level. Response and recovery times have been 253 s and 1120 s, respectively. Excellent selectivity toward NO2 has been demonstrated against five interfering gases, with stable performance over repeated cycles and reliable operation across a wide humidity range (9% –62% RH). Successful integration into a portable USB-powered module has been demonstrated to showcase practical deployment capability. This approach offers a sustainable, scalable route for room-temperature gas sensing suitable for environmental and occupational health monitoring.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147383084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of the Impact of Contact Force on Phonocardiogram Signal Quality Using Different Detection Devices 不同检测装置接触力对心音图信号质量的影响分析

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-23 DOI: 10.1109/LSENS.2026.3667007

Zifei He;Anjie Huang;Jianqing Li;Chengyu Liu;Chenxi Yang

{"title":"Analysis of the Impact of Contact Force on Phonocardiogram Signal Quality Using Different Detection Devices","authors":"Zifei He;Anjie Huang;Jianqing Li;Chengyu Liu;Chenxi Yang","doi":"10.1109/LSENS.2026.3667007","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3667007","url":null,"abstract":"Phonocardiogram (PCG) signal quality is influenced by the contact force between the PCG sensor and the skin, but the optimal contact force range has not yet been precisely and fully investigated. This work presents an experimental protocol to systematically analyze the impact of contact force on PCG signal quality. A high-precision force-control system and three devices for different scenarios were used to collect PCG signals at contact forces ranging from 0.2 N to 3.0 N. The contact force levels were divided into three classes: Loose (0.2–1.0 N), Normal (1.2–2.0 N), and Heavy (2.2–3.0 N). Signal quality was analyzed from three perspectives, including visual analysis, power spectral density analysis, and noise level analysis. Visual inspection showed that signals at the loose level contained the fewest recognizable PCG features. For all devices, most PCG energy was concentrated between 20 Hz and 100 Hz, where the main heart sounds S1 and S2 are located. The noise-based signal quality index combining signal-to-noise ratio, normalized root-mean-square error, and ratio of zero crossing indicated that contact forces at Normal and Heavy levels caused lower noise separately for devices with or without soft buffer for contact. These findings suggest the systematic protocol to investigate the optimal contact force range for PCG acquisition and potentially support the design of future PCG systems with contact force detection.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147383086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Magnetite-Integrated Electrochemical Sensor for Efficient Detection of PET Microplastics in Water 高效检测水中PET微塑料的磁铁矿集成电化学传感器

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-20 DOI: 10.1109/LSENS.2026.3666572

Hamid Khosravi;Karen Tatiana Bayona-Puentes;Ajeet Kaushik;Jasmina Casals-Terré

{"title":"Magnetite-Integrated Electrochemical Sensor for Efficient Detection of PET Microplastics in Water","authors":"Hamid Khosravi;Karen Tatiana Bayona-Puentes;Ajeet Kaushik;Jasmina Casals-Terré","doi":"10.1109/LSENS.2026.3666572","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3666572","url":null,"abstract":"Plastic pollution, particularly from microplastics, poses serious risks to ecosystems and human health. Polyethylene terephthalate (PET), a widely used polymer, commonly leaches into food and water sources, necessitating effective monitoring. This study presents a simple electrochemical sensor for trace detection of PET microplastics in water. The sensor was developed by modifying a screen-printed gold electrode (SPAuE) with magnetite (Fe3O4) nanoparticles valorized from mill scale. Electrochemical analysis revealed a fully irreversible, diffusion-controlled oxidation response. Under optimized conditions, the SPAuE/Fe3O4 sensor successfully detected PET in the concentration range of 6.25 to 500 mg/L, with a detection limit of 3.6 mg/L. The improved performance is attributed to the high conductivity and surface area of Fe3O4 nanoparticles. The sensor exhibited excellent sensitivity, selectivity, reproducibility, stability, and practical applicability in both synthetic and real water samples, supporting its potential as a simple, portable, and cost-effective tool for monitoring PET pollution in aquatic environments.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11404163","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147383085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust Pseudolabel Subspace Learning for E-Nose Drift Compensation 电子鼻漂移补偿的鲁棒伪标签子空间学习

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-19 DOI: 10.1109/LSENS.2026.3666520

Feng-Jie Zou;Jia Yan

{"title":"Robust Pseudolabel Subspace Learning for E-Nose Drift Compensation","authors":"Feng-Jie Zou;Jia Yan","doi":"10.1109/LSENS.2026.3666520","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3666520","url":null,"abstract":"Sensor drift severely degrades the long-term reliability of electronic nose (E-nose) systems, as temporal and device-induced variations distort the feature distributions of gas responses. Existing drift compensation approaches often require labeled target-domain or calibration samples, which are difficult to obtain in practical deployments, and conventional pseudolabeling strategies are vulnerable to noisy labels under severe drift. To address these challenges, this letter proposes a robust pseudolabel-based subspace learning (RPSL) method for unsupervised E-nose drift compensation. RPSL employs a dual-stage pseudolabel filtering mechanism that selects high-confidence target samples via support vector machine margins and further enforces prediction consistency through prototype learning. On the basis of these reliable samples, a unified subspace learning model is constructed to align source and target distributions by minimizing the mean, covariance, and prototype discrepancies while integrating graph embedding linear discriminant analysis to increase discriminability in the projected space. Experiments on two benchmark E-nose drift datasets under multiple transfer settings show that RPSL achieves stable and high classification accuracy without requiring any target-domain labels, demonstrating its effectiveness and robustness for practical drift compensation.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fully Inkjet-Printed Glucose Sensor on Flexible Polyimide Substrate 柔性聚酰亚胺基板上全喷墨印刷葡萄糖传感器

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-10 DOI: 10.1109/LSENS.2026.3663168

Aditi Ghosh;Sushree Sangita Priyadarsini;Subho Dasgupta

{"title":"Fully Inkjet-Printed Glucose Sensor on Flexible Polyimide Substrate","authors":"Aditi Ghosh;Sushree Sangita Priyadarsini;Subho Dasgupta","doi":"10.1109/LSENS.2026.3663168","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3663168","url":null,"abstract":"Continuous and reliable glucose monitoring is essential for effective diabetes management and point-of-care (POC) healthcare applications. In this work, we report a fully inkjet-printed, flexible, nonenzymatic glucose sensor fabricated on a polyimide substrate using a soft template-assisted manganese oxide (Mn3O4) ink deposited on an interdigitated planar electrode architecture. Unlike conventional Mn3O4-based glucose sensors, here the sensing response is governed primarily by adsorption-induced surface blocking effects, leading to measurable capacitance variation in the presence of glucose at the Mn3O4/ analyte interface. The choice of Mn3O4 is motivated by its chemical stability, abundant surface-active sites, and compatibility with low-temperature inkjet printing. The fully printed device demonstrates mechanical flexibility, low material consumption, and scalable fabrication, making it suitable for wearable POC applications. The fabricated sensor exhibited a linear detection range of 0.2 mM–7 mM and achieved a limit of detection of 0.546 mM, demonstrating stable and reliable sensing performance.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 4","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147383087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Underwater Acoustic Target Classification Using Hybrid Temporal–Spectral Feature Learning Network 基于混合时谱特征学习网络的水声目标分类

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-10 DOI: 10.1109/LSENS.2026.3663431

Wei Yan;Junjie Yang;Jiahui Ding;Zhenyu Zhang;Peifen Lu

{"title":"Underwater Acoustic Target Classification Using Hybrid Temporal–Spectral Feature Learning Network","authors":"Wei Yan;Junjie Yang;Jiahui Ding;Zhenyu Zhang;Peifen Lu","doi":"10.1109/LSENS.2026.3663431","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3663431","url":null,"abstract":"Underwater acoustic target classification (UATC) seeks to identify unknown acoustic sources through passive sonar in oceanic remote sensing applications. However, the highly dynamic marine environment and various background noise pose significant challenges to improving UATC performance. To address these challenges, we develop a hybrid temporal–spectral feature learning neural network that integrates three core components: a Fourier analysis network (FAN)-based temporal feature learner, a mixture of expert networks (MoEN)-based spectral feature learner, and an adaptive feature fusion (AFF) module. Specifically, the FAN-based learner encodes temporal feature by capturing multiple periodic patterns associated with underwater acoustic targets. In parallel, the MoEN-based learner models spectral dependencies and emphasizes spectral-selective patterns. The AFF dynamically then balance the contributions of the dual-branch learners through an adaptive weighting mechanism. The proposed algorithm achieves 98.58% accuracy on ShipsEar dataset, outperforming six state-of-the-art methods with moderate model parameters and computational cost.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 3","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Precision-Driven AI Smartphone-Based Sensor System for Fingernail-Based Noninvasive Disease Detection 基于精准驱动的AI智能手机传感器系统，用于基于指甲的无创疾病检测

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-10 DOI: 10.1109/LSENS.2026.3663338

Neha S. Ingole;Aadarsh Nagrikar;Bhuvan Patle;Rutuja Karemore;Gitesh Sawatkar;Richa R. Khandelwal

{"title":"Precision-Driven AI Smartphone-Based Sensor System for Fingernail-Based Noninvasive Disease Detection","authors":"Neha S. Ingole;Aadarsh Nagrikar;Bhuvan Patle;Rutuja Karemore;Gitesh Sawatkar;Richa R. Khandelwal","doi":"10.1109/LSENS.2026.3663338","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3663338","url":null,"abstract":"Liver disease and nail psoriasis can manifest through secondary nail changes, yet conventional diagnostic methods, such as blood tests and biopsies remain invasive, costly, and painful for patients, highlighting the need for more accessible, noninvasive alternatives. This research introduces a novel deep learning (DL)-based approach for the noninvasive detection of these diseases using fingernail image analysis. Various DL models, including convolutional neural networks (CNN), VGG16, MobileNet, MobileNetV2, and InceptionV3, were evaluated, and accuracy of 82.66%, 91.33%, 90.00%, 90.67%, and 95.71%, respectively, for each model was achieved. The models were trained on a dataset of fingernail images, and their performance was assessed based on classification accuracy. The accuracy of InceptionV3 achieved was the highest. Building upon this model's success, a mobile application integrated with sensor-based functionality was developed allowing users to upload fingernail images and receive instant diagnostic feedback conveniently enabling early detection. This research demonstrates the transformative potential of DL and sensor technology in healthcare by providing a fast, reliable, and noninvasive diagnostic tool for early diagnosing liver and nail psoriasis disease in clinical and remote applications.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 3","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147362356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-Speed Detection of Moving Objects Using FMCW Radar Sensor 基于FMCW雷达传感器的运动目标高速检测

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-03 DOI: 10.1109/LSENS.2026.3660746

Andrey Dergachev;Alexander Osinsky;Vladimir Kalinin;Roman Bychkov;Andrey Ivanov

引用次数: 0

A Lightweight Fourier Block Transformer for Android-Based Edge-Enabled Detection of Osteopenia and Osteoporosis Using X-Ray Sensor Imaging Data 使用x射线传感器成像数据进行基于android的骨质减少和骨质疏松边缘检测的轻量级傅立叶块变压器

IF 2.2

IEEE Sensors Letters Pub Date : 2026-02-03 DOI: 10.1109/LSENS.2026.3660889

Rishab Kumar Pattnaik;Rajesh Kumar Tripathy;Ram Bilas Pachori

{"title":"A Lightweight Fourier Block Transformer for Android-Based Edge-Enabled Detection of Osteopenia and Osteoporosis Using X-Ray Sensor Imaging Data","authors":"Rishab Kumar Pattnaik;Rajesh Kumar Tripathy;Ram Bilas Pachori","doi":"10.1109/LSENS.2026.3660889","DOIUrl":"https://doi.org/10.1109/LSENS.2026.3660889","url":null,"abstract":"The early detection of osteoporosis (OPRS) and osteopenia (OPNA) is crucial for preventing bone fractures and other bone-related complications in the aging population. The existing deep learning methods rely on cloud-based processing, which limits their suitability for point-of-care deployment for real-time detection of OPRS and OPNA using knee X-ray images. This letter proposes an Android-based edge-enabled lightweight Fourier block-based transformer (LFBBT) model for real-time detection of OPRS and OPNA diseases using knee X-ray images or X-ray sensor imaging data. The LFBBT model comprises a patch embedding layer, a discrete Fourier transform block layer, a dense layer, a dropout layer, and an output layer. The knee X-ray images from a publicly available database are used to evaluate the performance of the proposed LFBBT model. The results show that the suggested LFBBT model has achieved an overall accuracy of 88.41%, which is higher than that of various transfer learning techniques and pretrained transformers in detecting OPRS and OPNA diseases. The Android-based implementation of the LFBBT model has achieved a throughput of 60 images per minute for detecting OPRS and OPNA in real-time using knee X-ray images.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 3","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0