IEEE Sensors Journal最新文献

{"title":"A Novel Bearing Remaining Useful Life Prediction Methodology With Slope-Based Change Point Detection and WOA-Attention-BiLSTM Model","authors":"Guangqi Qiu;Binlu Ye;Yingkui Gu;Peng Huang;He Li;Zifei Xu","doi":"10.1109/JSEN.2025.3530111","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3530111","url":null,"abstract":"Appropriate health indicator (HI) and efficient prediction models are critical factors for accurate remaining useful life (RUL) prediction, particularly when dealing with fluctuations and redundant information in the HI curve. To address these challenges, this study proposed an HI construction method for better characterization of the degradation behavior based on the entropy weight method and kernel entropy component analysis (EWM-KECA). The HI construction method can eliminate the fluctuations in HI and identify the fault change point position in HI. For RUL estimation, a bearing RUL prediction method was developed by integrating slope-based change point detection with a whale optimization algorithm (WOA)-Attention-bidirectional long short-term memory (BiLSTM) model. By eliminating more than 85% of duplicate data that are not useful for RUL prediction, this approach achieves more accurate RUL predictions while reducing computational resource requirements. The reliability and effectiveness of the proposed method are validated using the bearing degradation dataset. The results from comparative analysis and ablation experiments demonstrate that the proposed method consistently achieves superior performance. Compared with models such as CNN-Attention-BiGRU, WOA-CNN-BiGRU, and WOA-Attention-CNN, the mean absolute error (MAE), mean absolute percentage error (MAPE), and root-mean-squared error (RMSE) values have been reduced by more than 50%, indicating that the proposed RUL prediction methodology represents an advanced and effective approach.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 6","pages":"10417-10431"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620024","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":"Analytical Modeling of Cuboid Microfluidic Multilayered Glass Structure for Microwave Permittivity Sensors","authors":"Teguh Firmansyah;Syah Alam;Slamet Widodo;Muhammad Iqbal;Rocky Alfanz;Alimuddin Alimuddin;Toto Supriyanto;Yuyu Wahyu;Adi Mahmud Jaya Marindra;Aloysius Adya Pramudita;Gunawan Wibisono;Mudrik Alaydrus;Jun Kondoh","doi":"10.1109/JSEN.2025.3532844","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3532844","url":null,"abstract":"A microfluidic structure plays a crucial role in supporting liquid sensors. However, modeling a multilayered microfluidic structure faces challenges for permittivity sensor applications, particularly concerning the non monotonic behavior of multilayered dielectrics. These challenges arise due to the varying characteristics of the electric field (E) direction in dielectrics with low and high permittivity. The existing models exhibit significant deviations from measurement results across a wide permittivity range. To address the issue, this article proposes a quasi-static conformal approach with exponentially tapered capacitance to minimize deviations caused by nonlinear behavior. This study uses the exponential tapered permittivity ratio to adjust and modify the capacitance value. The proposed model was examined across samples with a wide range of permittivity, spanning from air of 1.0 to water of 80.0. To verify the proposed model, finite element method (FEM) simulations and experimental measurements were conducted. A three-layer configuration was prepared, i.e., glass (<inline-formula> <tex-math>$varepsilon _{{r}{2}} =7.3$ </tex-math></inline-formula>)/liquid sample (<inline-formula> <tex-math>$varepsilon _{{r}{3}} =1.0$ </tex-math></inline-formula>–80.0)/glass (<inline-formula> <tex-math>$varepsilon _{{r}{4}} =7.3$ </tex-math></inline-formula>). The sample was positioned at the middle layer by using a microfluidic channel with a cuboid shape. As a result, the comparison of the quasi-static conformal approach without and with the exponentially tapered capacitance model reveals deviations in the effective permittivity (<inline-formula> <tex-math>$varepsilon _{{r}text {-eff}}$ </tex-math></inline-formula>) of 27.7% and 1.3%, in the characteristic impedance (<inline-formula> <tex-math>${Z} _{{0}}$ </tex-math></inline-formula>) of 11.1% and 0.8%, and in the total capacitance (<inline-formula> <tex-math>${C} _{text {T}}$ </tex-math></inline-formula>) of 28.5% and 1.4%, respectively. Subsequently, the proposed sensor structure was fabricated and measured for permittivity sensor application using the resonant frequency shift approach. The measurement results, ranging from the air (<inline-formula> <tex-math>$varepsilon _{{r}{3}} =1.0$ </tex-math></inline-formula>) to the water sample (<inline-formula> <tex-math>$varepsilon _{{r}{3}} =80.0$ </tex-math></inline-formula>), showed a frequency shift of 425.50 MHz and an average normalized sensitivity (NS) of 0.64%. This study presents a robust and accurate model, offering a practical solution for permittivity sensing. The proposed approach meets the high accuracy and sensitivity demands in diverse industrial and environmental applications. Additionally, the model is recommended for various sectors, including the biomedical industry, medicine, and material quality control.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 6","pages":"9727-9737"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621665","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 Shin-Mounted Inertial Navigation System for Pedestrian Walking and Running Gait","authors":"Jian Kuang;Dazhou Xia;Yan Wang;Xianmei Meng;Xiaoji Niu","doi":"10.1109/JSEN.2025.3533138","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3533138","url":null,"abstract":"Accurately and reliably estimating the position of pedestrians with complex gaits is a primary challenge for current positioning solutions using wearable inertial sensors. This article proposes a novel zero-velocity detection method tailored for walking and running using a shin-mounted IMU, resulting in a shin-mounted inertial navigation system (Shin-INS) suitable for pedestrians with walking and running gaits. The proposed method divides pedestrian motion into stationary, walking, and running stages, and designs zero-velocity detection signal features and methods according to the gait. On this basis, the zero-velocity update technique (ZUPT) and the zero-position increment update method are used to achieve reliable pedestrian position estimation. We conducted over 30 tests, encompassing various running speeds, trajectory shapes, and transitions between walking and running gaits. The results demonstrate that the proposed method accurately estimates pedestrian motion trajectories, reducing positioning errors by more than 30% under conditions of walking and running gait transitions compared to the foot-mounted INS (Foot-INS) based on adaptive threshold.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 6","pages":"9449-9458"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621783","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":"CUDLE: Learning Under Label Scarcity to Detect Cannabis Use in Uncontrolled Environments Using Wearables","authors":"Reza Rahimi Azghan;Nicholas C. Glodosky;Ramesh Kumar Sah;Carrie Cuttler;Ryan McLaughlin;Michael J. Cleveland;Hassan Ghasemzadeh","doi":"10.1109/JSEN.2025.3528030","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3528030","url":null,"abstract":"Wearable sensor systems have demonstrated great potential for real-time, objective monitoring of physiological health to support behavioral interventions. However, obtaining accurate labels in free-living environments remains challenging due to limited human supervision and reliance on self-labeling by patients, complicating data collection and supervised learning. To address this, we introduce cannabis use detection with label efficiency (CUDLE), a novel framework that leverages self-supervised learning with real-world wearable sensor data to automatically detect cannabis consumption in free-living environments. CUDLE identifies consumption moments using sensor-derived data through a contrastive learning framework, first learning robust representations via a self-supervised pretext task with data augmentation. These representations are then fine-tuned in a downstream task with a shallow classifier, allowing CUDLE to outperform traditional supervised methods, especially with limited labeled data. To evaluate our approach, we conducted a clinical study with 20 cannabis users, collecting over 500 h of wearable sensor data and user-reported cannabis use moments through ecological momentary assessment (EMA) methods. Our analysis shows that CUDLE achieves a higher accuracy of 73.4% compared to 71.1% for the supervised approach, with the performance gap widening as the number of labels decreases. Notably, CUDLE not only surpasses the supervised model while using 75% fewer labels but also reaches peak performance with far fewer subjects, indicating its efficiency in learning from both limited labels and data. These findings have significant implications for real-world applications, where data collection and annotation are labor-intensive, offering a path to more scalable and practical solutions in computational health.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 5","pages":"9093-9100"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553450","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 Monocular Structured Light-Based System for 3-D Reconstruction and Defect Detection of Municipal Pipeline Inner Walls","authors":"Han Chen;Guojun Wen;Xin He;Shuang Mei","doi":"10.1109/JSEN.2025.3532038","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3532038","url":null,"abstract":"Municipal underground pipelines are closely intertwined with the daily lives of citizens. However, as a result of manufacturing imperfections and prolonged usage, pipelines frequently develop defects such as bulges, cracks, and damage. These issues can lead to leaks or complete failures, resulting in significant inconvenience for the public and substantial economic losses. Therefore, regular inspection and quality assessment of the inner walls of pipelines are essential. This article presents a monocular structured light-based system for the 3-D reconstruction of pipeline inner walls. The proposed system uses a laser emission unit and an industrial camera acquisition unit to generate a 3-D point cloud of the pipeline’s inner surface, enabling the quantitative detection of defects. The system only requires a single calibration and can achieve a 360° unobstructed reconstruction of the entire inner wall. The camera is triggered by an encoder to produce real-time point cloud data. The system underwent testing on pipelines without defects, pipelines with quantified defects, and pipelines with irregular defects. The experimental results demonstrate that the generated point clouds can effectively quantify defects and assess the quality of the pipeline’s inner walls with millimeter-level accuracy.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 6","pages":"10309-10319"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621870","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":"DAMNet: A Lightweight Dual-Modal Network for Wi-Fi-Based Human Activity Recognition","authors":"Liyuan Lin;Jingpeng Yan;Aolin Wen;Shun Zhang;Shuxian Zhao;Leguang Wang;Xin Wang;Qiqi Wang;Weibin Zhou;Yuan Zhou","doi":"10.1109/JSEN.2025.3532444","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3532444","url":null,"abstract":"Wi-Fi signals have played an important role in human activity recognition (HAR) due to widespread usage and noninvasive nature. Whereas the single-modal feature of channel state information (CSI) is usually used but fails to fully provide the time-frequency characteristics of the Wi-Fi signal, which affects the classification accuracy of HAR. Therefore, this article proposes a lightweight dual-modal network DAMNet, which can extract and fuse the characteristics of the wireless signal in the time domain and frequency domain. The DAMNet enhances the complementarity between different modals to improve the representation ability of the model by constructing an inverted residual coordinate attention block (IRCAB) and local convolutional aggregation structures. Hence, it can more effectively capture the time-frequency characteristics of Wi-Fi signals and enhance the ability to recognize different activities. The experimental results on the ACSID dataset show that the accuracy of the proposed model is 98.10%, which is significantly better than those of the other most advanced models. Meanwhile, the generalization validation on the WiAR and Glasgow datasets is conducted, whose accuracy reaches 95.91% and 95.15%, respectively. It is proved that the method proposed in this article has excellent generalization performance, with important practical value and promotion significance.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 5","pages":"9197-9207"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553441","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 Novel Filtering Framework for High-Density sEMG Based on Variational Mode Decomposition and Independent Vector Analysis","authors":"Zeming Zhao;Weichao Guo;Miaojuan Xia;Xinjun Sheng","doi":"10.1109/JSEN.2025.3532689","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3532689","url":null,"abstract":"During the acquisition process, surface electromyography (sEMG) recordings are unavoidably contaminated by different types of noise signals, including baseline noise (BLN), powerline interference (PLI), and white Gaussian noise (WGN). The inclusion of these noise signals significantly diminishes the quality of sEMG signals and impairs the accuracy and resilience of their subsequent utilization. There are two significant issues concerning existing filters: 1) the primary technique for filters targeting BLN and PLI remains IIR filters. However, this methodology makes it challenging to prevent the filters from suppressing sEMG signals in the stopband and 2) the noise signals that are filtered out by the filters targeting WGN do not adhere to a Gaussian distribution. In this study, we propose a novel filtering framework that combines split spectrum processing (SSP) and mix source separation (MSS) to effectively eliminate the three types of noise signals and address the two aforementioned concerns. In this article, other four well-designed filtering methods, including the infinite impulse response (IIR) filter, ensemble empirical mode decomposition (EEMD) method, variational mode decomposition (VMD) method and the independent vector analysis (IVA) method, were evaluated for comparison. The proposed filtering framework demonstrated superior performance in eliminating all three types of noise signals. The simulated signals showed an improvement in SNR of 29.7, 22.4, and 12.9 dB for sEMG signals corrupted by BLN, PLI, and WGN with input SNRs of −10 dB, respectively. The experimental results indicated that the proposed method achieved an average improvement in SNR of 15.9 dB. The proposed filter is highly effective in eliminating all three types of noise and can be utilized for various applications that necessitate sEMG signals, such as gesture recognition and sEMG decomposition.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 6","pages":"9831-9841"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621987","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":"Additive Strategies to Mitigate Humidity Interference Effects on PEDOT:PSS Sensors for Ammonia Detection","authors":"Ajay Beniwal;Priyanka Ganguly;Gaurav Khandelwal;Rahul Gond;Brajesh Rawat;Chong Li","doi":"10.1109/JSEN.2025.3533298","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3533298","url":null,"abstract":"Development of precise and accurate ammonia sensors suitable for healthcare (point-of-care devices) and environmental monitoring is imperative and absolute necessity. However, a persistent challenge in the gas sensor technology is sensitivity degradation due to humidity interference. To address this challenge, this study presents a screen-printed, flexible, and disposable sensor based on poly(3,4-ethylenedioxythiophene): poly(styrenesulfonate) (PEDOT:PSS) mixed with additives having reduced humidity interference tailored for ammonia (NH3) gas detection. Polar solvents such as ethylene glycol (EG), dimethylformamide (DMF), and dimethyl sulfoxide (DMSO) are used as additives with the base material PEDOT:PSS. Enhanced hydrophobicity is confirmed via contact angle measurements. Current-voltage (I–V) characteristic assessments reveal a linear ohmic behavior, emphasizing the heightened conductivity of the samples with additives compared to the PEDOT:PSS sensor. When assessing the humidity response, the DMF-modified PEDOT:PSS sensor exhibited minimal % response, registering only 37.01% at 90% humidity. This was a marked improvement over the pristine PEDOT:PSS sensor, which recorded 118.5% at the same humidity level, and outperformed other additive variants. Regarding ammonia detection, the PEDOT:PSS/DMF sensor demonstrated an experimental detection ability up to 0.1 ppm with 0.91% response and outperformed the ammonia sensing ability of pristine PEDOT:PSS. Effect of relative humidity (~5%RH–80%RH) on ammonia gas sensing performance of PEDOT:PSS/DMF sensor is also conducted and compared with pristine PEDOT:PSS. The increment in sensor conductivity with rising ammonia concentrations is theorized due to the charge transfer, where ammonia’s lone pair of electrons interacts with the covalent backbone of PEDOT:PSS, suggesting a plausible sensing mechanism.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 6","pages":"9357-9366"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654903","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 Novel AlGaN/GaN SBD Thermal Sensor With Ultralow Power, Excellent Linearity, and High Sensitivity","authors":"Yuhan Sun;Kangyao Wen;Fangzhou Du;Chenkai Deng;Wenmao Li;Jiaqi He;Qiaoyu Hu;Yang Jiang;Robert Sokolovskij;Qing Wang;Yu-Long Jiang;Hong-Yu Yu","doi":"10.1109/JSEN.2025.3532657","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3532657","url":null,"abstract":"A novel AlGaN/GaN Schottky barrier diode (SBD) thermal sensor featuring a recessed anode and a thin Al0.25Ga0.75N barrier layer is fabricated, which is demonstrated to have ultralow power, excellent linearity, and high sensitivity for thermal sensing. The AlGaN layer thickness is employed to trade-off the tunneling current proportion against the 2-D electron gas (2DEG) density for the thermionic emission (TE)-dominated electron transportation with better linearity and high sensitivity of thermal sensing at ultralow power. A sensitivity of 1.39 mV/K with a linearity of 0.995 operating at 0.082–0.324 V for a constant current of <inline-formula> <tex-math>$10^{-{7}}$ </tex-math></inline-formula> A is revealed. The proposed SBD sensor shows the great potential application for on-chip, low-power, and high-performance thermal sensing in monolithic AlGaN/GaN heterostructure-based power ICs.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 5","pages":"8024-8031"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553095","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":"DiffKPD: A Robust Key Point Detection Algorithm With a Diffusion Process for Automatic Pin Welding","authors":"Zhiyong Dai;Chunhua Gu;Heng Yao;Jianjun Yi;Fangqin Xu","doi":"10.1109/JSEN.2025.3531794","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3531794","url":null,"abstract":"Recent advancements in vision-guided automatic pin welding methods have garnered significant attention for their high productivity and performance. However, these applications still face considerable challenges in achieving the robustness and precision required for pin recognition and key point localization, which impedes their adoption in intelligent automation and manufacturing, particularly for electric vehicle motor production. In this article, we introduce a novel automatic pin key point detection model, namely, DiffKPD, designed to overcome these challenges. Our solution uses a two-stage detector: a base detector for localizing pin key points, followed by a lightweight, fast diffusion process that leverages time steps and local spatial context information to refine prior key point detections. Finally, we demonstrate the effectiveness and efficiency of our proposed method through extensive experimental results in terms of both localization precision and inference speed.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 6","pages":"10444-10453"},"PeriodicalIF":4.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621565","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}