Yuanjing Zhang;Shuai Li;Jie He;Yang Wu;Hao Wang;Kai Liu;Jiafeng Yao
{"title":"Regional Identification of Breast Tumors Using Multichannel Bioimpedance Spectroscopy","authors":"Yuanjing Zhang;Shuai Li;Jie He;Yang Wu;Hao Wang;Kai Liu;Jiafeng Yao","doi":"10.1109/JSEN.2025.3596237","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596237","url":null,"abstract":"A multichannel bioimpedance spectroscopy (MC-BIS) method is proposed for regional identification of breast tumors. First, the sensor is partitioned to scan the breast across nine subregions, and an empty-field calibration algorithm is applied to normalize the impedance spectra. Next, numerical simulations are conducted to investigate the relationship between the electrical characteristics of unifocal tumors and their regional distribution. Subsequently, the performance of three classifiers—support vector machine (SVM), random forest (RF), and feedforward neural network (FNN)—is evaluated for bifocal tumor localization. The simulation results indicate significant differences in the impedance characteristics between tumor regions and normal tissue regions (<inline-formula> <tex-math>${P} lt 0.001$ </tex-math></inline-formula>). When a tumor is present in a subregion, the corresponding imaginary part relaxation impedance <inline-formula> <tex-math>${Z} _{text {imag-relax}}$ </tex-math></inline-formula> exceeds <inline-formula> <tex-math>$2.004~Omega $ </tex-math></inline-formula>. For bifocal breast tumor localization, the FNN classifier achieved the best performance, with a classification accuracy of 95.46% through fivefold cross-validation. To validate the simulation results, biological tissues with distinct electrical properties were selected to simulate tumor and normal tissue. The experimental accuracy reached 86.94%. The MC-BIS method enables rapid and accurate localization of tumor regions, providing a new technological approach for early screening and diagnosis of breast cancer.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35438-35446"},"PeriodicalIF":4.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073443","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":"Lightweight Gesture Recognition Model Based on CWT and Enhanced CBAM","authors":"Zhaoxia Zhang;Zhibin Liang;Xiaoyu Wang;Xuchao Feng","doi":"10.1109/JSEN.2025.3596600","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596600","url":null,"abstract":"As an interaction method, gesture is widely used in various fields because of its simplicity and intuition. At present, most radar-based gesture recognition methods use short-time Fourier transform (STFT) to process radar echo information, but STFT cannot improve time resolution and frequency resolution simultaneously. To fully utilize effective information, the continuous wavelet transform (CWT) is used to process the radar echo signals. In view of the complexity of gesture recognition networks, a novel network incorporating CWT and an enhanced convolutional block attention module (CBAM) mechanism is proposed. First, features are pre-extracted using a feature extraction network. Then, the CBAM module is improved and integrated. Finally, the classification result is formed. To verify the model’s effectiveness, experiments collected data for nine distinct gestures. The results demonstrate a recognition accuracy of 96.3% via participant-stratified cross validation. Moreover, the model parameters are optimized, facilitating relatively simple implementation. It also exhibits strong performance on unknown datasets, proving its excellent generalization capability.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35631-35641"},"PeriodicalIF":4.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145100405","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}
Shavika Rastogi;Nik Dennler;Michael Schmuker;André van Schaik
{"title":"Neuromorphic Circuit for Temporal Odor Encoding in Turbulent Environments","authors":"Shavika Rastogi;Nik Dennler;Michael Schmuker;André van Schaik","doi":"10.1109/JSEN.2025.3596564","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596564","url":null,"abstract":"Natural odor environments present turbulent and dynamic conditions, causing chemical signals to fluctuate in space, time, and intensity. While many species have evolved highly adaptive behavioral responses to such variability, the emerging field of neuromorphic olfaction continues to grapple with the challenge of efficiently sampling and identifying odors in real-time. In this work, we investigate metal-oxide (MOx) gas sensor recordings of constant airflow-embedded artificial odor plumes. We discover a data feature that is representative of the presented odor stimulus at a certain concentration, irrespective of temporal variations caused by the plume dynamics. Furthermore, we design a neuromorphic electronic nose front-end circuit for extracting and encoding this feature into analog spikes for gas detection and concentration estimation. The design is loosely inspired by the spiking output of parallel neural pathways in the mammalian olfactory bulb (OB). We test the circuit for gas recognition and concentration estimation in artificial environments, where either single gas pulses or prerecorded odor plumes were deployed in a constant flow of air. For both environments, our results indicate that the gas concentration is encoded in—and inversely proportional to—the time difference of analog spikes emerging out of two parallel pathways. The resulting neuromorphic nose could enable data-efficient, real-time robotic plume navigation systems, advancing the capabilities of odor source localization in applications such as environmental monitoring and search-and-rescue.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35622-35630"},"PeriodicalIF":4.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145100406","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}
Dejvi Cakoni;Laurent Storrer;Bruno Cornelis;Philippe De Doncker;François Horlin
{"title":"Complementarity and Fusion of FMCW and Wi-Fi Passive Radars for Pedestrian Flow Monitoring","authors":"Dejvi Cakoni;Laurent Storrer;Bruno Cornelis;Philippe De Doncker;François Horlin","doi":"10.1109/JSEN.2025.3595215","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3595215","url":null,"abstract":"This study explores the complementarity and fusion of two sensing technologies for pedestrian flow estimation: ubiquitous Wi-Fi based passive radar (WPR) and deployable frequency-modulated continuous wave (FMCW) active radar, both combined with a convolutional neural network (CNN) for postprocessing. Wi-Fi signals, already widespread in many environments, enable passive, wide-area motion sensing without requiring additional infrastructure. FMCW radars, by contrast, offer high-resolution range-Doppler measurements and can be selectively deployed in target locations, such as pedestrian streets. We begin by individually evaluating the performance of FMCW and Wi-Fi passive radar systems in estimating pedestrians flow, highlighting their respective strengths, limitations, and complementarity. To further improve the system performance, we propose a fusion approach at both the decision and feature levels. For decision-level fusion, we implement majority voting and probability averaging strategies to combine the predictions from both radars. For feature-level fusion, we extract features from both radar systems using CNNs and merge them before classification. Our experimental results, from measurements collected on the same scene by the two radars, show that the fusion approaches significantly enhance the flow estimation accuracy compared to using either radar system alone. The feature-level fusion method, in particular, demonstrates superior performance by effectively integrating the spatial and motion information captured by both radar types. This work demonstrates the value of hybrid sensing systems that combine opportunistic and purpose-built technologies for reliable pedestrian counting and flow estimation in diverse urban scenarios and provides a robust framework for future developments in multisensor data fusion.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35053-35065"},"PeriodicalIF":4.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145078582","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":"An Effective Action Recognition Method Based on Image Coding and a Dual-Channel Fusion Network","authors":"Yukun Wang;Junlong Zhu","doi":"10.1109/JSEN.2025.3596568","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596568","url":null,"abstract":"Action recognition is a research hotspot in artificial intelligence, with significant applications in intelligent sports analysis, health monitoring, and human–computer interaction. Traditional methods rely on high-frame-rate cameras or complex motion capture systems, which are costly and highly dependent on environmental conditions. In contrast, data-driven methods based on wearable sensors have gained widespread attention due to their portability and cost-effectiveness. In this article, we propose an action recognition method based on image encoding and a dual-channel feature extraction network. We convert time-series data collected from wearable sensors into color images through image encoding, fully preserving the temporal information and multidimensional feature relationships in the data. Then, we design a dual-channel feature extraction network that extracts complex features using a multiscale spatial channel attention (MSCA) module, a dual-stream alternating feature fusion (DAF) module, and a weighted loss function (WFL). We conducted experiments on the USC-HAD and PAMAP2 datasets, demonstrating that our method outperforms several state-of-the-art methods. Ablation studies further verify the contributions of the backbone network, fusion module, classifier, and loss function to the overall performance. Overall, our method provides a new solution for action recognition tasks and shows broad application prospects.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35144-35156"},"PeriodicalIF":4.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145078662","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":"The Effect of Piezoresistive Film Parameters on High-Pressure Lubricant Film Measurement Performance and Optimization Design","authors":"Hongkai Li;Mingshang Chen;Xiuqi Yuan;Zidong Han;Jing Li;Tong Zhang","doi":"10.1109/JSEN.2025.3596562","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596562","url":null,"abstract":"Accurate measurement of high-pressure lubricant film pressure is essential to detect the lubrication condition. Aimed at measuring gauge pressures from 0 to 60 MPa, this study establishes a simulation model of a piezoresistive film to analyze stress and strain distributions. According to the calculation results, it is revealed that the rectangular pressure diaphragm exhibits a more pronounced stress concentration effect compared with the other geometries, which is particularly suitable for high-pressure measurements. Furthermore, the effect of the main design parameters is analyzed, including the length–width ratio (<inline-formula> <tex-math>$alpha text {)}$ </tex-math></inline-formula> and thickness (<inline-formula> <tex-math>${t}text {)}$ </tex-math></inline-formula> of the rectangular diaphragm, as well as the distribution, number (<inline-formula> <tex-math>${n}_{p}text {)}$ </tex-math></inline-formula>, and length (<inline-formula> <tex-math>${l}_{p}text {)}$ </tex-math></inline-formula> of the piezoresistors on the measurement performance. Based on the above research, the optimal design parameters are determined, and a significant improvement in the sensor’s sensitivity and linearity is obtained. Then, a piezoresistive pressure sensor is fabricated using MEMS technology, and a series of lubricant film pressure measurement experiments has been conducted. The experimental results show that the sensor achieves a sensitivity of 3.9848 mV/MPa, with a linearity of 0.56%. Furthermore, it exhibits excellent repeatability, with a repeatability coefficient of 0.3088% and a hysteresis coefficient of 0.462%, indicating high-precision and stable measurements of high-pressure lubricant films. This study contributes to the optimization design of high-performance piezoresistive pressure sensors for high-pressure lubricant film measurements, which also helps in the miniaturized design of the sensor device and integration of multiple sensing units in in situ detection systems.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"34510-34518"},"PeriodicalIF":4.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090004","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":"Research on Mechanical Performance Degradation Modeling and Remaining Useful Life Prognosis Method of AC High-Voltage Circuit Breakers","authors":"Jinglong Zhou;Yanan Qian;Hongshan Zhao","doi":"10.1109/JSEN.2025.3596724","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596724","url":null,"abstract":"This article proposes a data-driven degradation modeling and remaining useful life prognosis method for ac high-voltage circuit breakers that addresses uncertainty in the degradation process. First, the Nadaraya–Watson method is used to reduce measurement error by smoothly estimating the closing-time dataset of high-voltage circuit breakers. Second, the functional principal component analysis (FPCA) is applied to extract the common degradation-trend component and deviation component from the smoothed data, to construct a degradation model. Finally, the model parameters are dynamically updated using Bayesian inference to predict the degradation trend and estimate the remaining useful life of high-voltage circuit breakers. Experimental results show that the proposed method offers timely identification of degradation trends and accurate estimation of remaining useful life. This not only enhances equipment reliability and reduces maintenance costs but also provides essential technical support for implementing intelligent operation and maintenance strategies for high-voltage circuit breakers, demonstrating strong engineering applicability and practical significance.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"34519-34528"},"PeriodicalIF":4.3,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090126","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}
Minsu Kim;Eunkyu Oh;Yoosung Kim;Seonho Kim;Dasom Park;Jung-Hwan Kim;Suhye Kim;Hyunjin Ahn;Chang-Hwan Im
{"title":"Development of a New Around-the-Ear Electroencephalography Device for Passive Brain–Computer Interface Applications","authors":"Minsu Kim;Eunkyu Oh;Yoosung Kim;Seonho Kim;Dasom Park;Jung-Hwan Kim;Suhye Kim;Hyunjin Ahn;Chang-Hwan Im","doi":"10.1109/JSEN.2025.3596292","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596292","url":null,"abstract":"As interest in passive brain–computer interface (pBCI) technology for everyday applications increases, the development of practical wearable electroencephalography (EEG) recording devices has become increasingly essential. Among the various form factors to implement wearable EEG systems, ear-EEG is frequently employed owning to its usefulness in everyday scenarios. In this study, a new wearable around-the-ear EEG recording device for pBCI applications was developed. The performance of the developed device was validated through two pBCI experiments. During the ear-EEG device design, an alpha attenuation test was conducted to determine the optimal location of a pair of EEG electrodes. The two practical pBCI applications tested in this study were the prediction of users’ preferences for short video clips and drowsiness detection during online learning. The experimental results showed an accuracy of 85.71% in terms of preference prediction and a success rate of 80% in terms of drowsiness detection, effectively demonstrating the practicality of the newly developed around-the-ear EEG device for daily life scenarios.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"34226-34235"},"PeriodicalIF":4.3,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11123617","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073410","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":"Sensing Depth Analysis of Different Permittivity Materials Based on Open-Ended Coaxial Probes at Different Input Powers","authors":"Guifeng Yang;Shaohua Zhou;Hui Huang;Jianhua Yang","doi":"10.1109/JSEN.2025.3591245","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3591245","url":null,"abstract":"Existing studies have only qualitatively analyzed the relationship between input power and depth of induction of open-ended coaxial probe. Along with the development of science and technology, the measurement of permittivity requires the quantification of the relationship between the input power and the sensing depth of an open-ended coaxial probe. In this article, for the first time, the effect of different power and materials with different permittivity on the sensing depth of the probe is quantitatively analyzed and the maximum sensing depth of 2.2-mm aperture probe is derived. More importantly, to better handle small amounts of sample materials, thin and multilayer materials, and ensure measurement accuracy, we have also established a sensing depth calculation model. The calculation formula of the model can be used to quickly and accurately calculate the sensing depth of the probe for different permittivity materials under different input powers. This is the industry’s first computational model for the sensing depth of open-end coaxial probes, which provides a strong guarantee of the method’s accurate measurement. Finally, this article validates the model formulation for sensing depth calculation by experimental means. Results show that in the range of −20 to 20 dBm (5.8-GHz frequency) for materials with permittivity between 1 and 80, the computational model is accurately valid and that the maximum depth of sensing for a 2.2-mm aperture probe is 2.8 mm.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35248-35254"},"PeriodicalIF":4.3,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145078679","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":"Advanced Charger Placement Strategies in Sensor Networks Using Graph Theory and Evolutionary Algorithms","authors":"P. Neelagandan;S. Balaji;R. Pavithra","doi":"10.1109/JSEN.2025.3596399","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3596399","url":null,"abstract":"Efficient recharging of sensors is essential to ensure uninterrupted operation across a wide range of applications, and the strategic placement of chargers plays a crucial role in achieving this objective. This article addresses the optimization of wireless sensor recharging by focusing on two key phases: determining the minimum number of chargers required and identifying their optimal placement. In the first phase, the minimum number of chargers is determined using the Grundy coloring algorithm (GCA). In the second phase, the blackhole algorithm is applied to optimally position the chargers, aiming to maximize coverage and minimize redundancy. The effectiveness of the proposed method was validated through simulation experiments. Performance comparisons were conducted between the blackhole algorithm, which achieved 98.15% coverage including Haar (95.85%), Daubechies 2 (95.50%), Biorthogonal (96.01%), Symlets 8 (95.98%) wavelets, and the raindrop algorithm (96.24%). The results indicate that the proposed algorithm outperforms these methods in terms of coverage efficiency and optimal charger deployment, highlighting its potential for significantly enhancing the recharging process in wireless sensor networks.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35609-35621"},"PeriodicalIF":4.3,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073423","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}