A wireless passive flexible sensor has been developed to measure the surface temperature of bearings and transmit wireless signals. The sensor employs a dielectric film sandwiched by a double-layer reverse-helical inductor structure to enhance magnetic field coupling with a ferrite composite material at the bottom of the layers. Both the permittivity of the dielectric material and the permeability of the ferrite demonstrate temperature-sensitive characteristics. This configuration establishes a synergistic mechanism that enables both inductance–capacitance (LC) sensitive to the change in temperature simultaneously. The ferrite substrate effectively prevents the spiral inductor antenna from electromagnetic absorption caused by metallic components. The type of dual-layer reverse-helical inductive wireless passive sensor enables efficient wireless transmission in a metallic environment. The sensitivity of this configuration can reach 237.34 kHz/°C with the maximal coupling distance extending to 21 mm. The exceptional stability of the resonant frequency of this dual-layer reverse-helical inductive structure was achieved through the mutual inhibition of LC variations when the flexible sensor is subjected to bending on the surface of the bearing. The sensor of composite structure establishes dual-sensitive units and optimizes electromagnetic field coupling, achieving an integrated system with electromagnetically synergistic properties. The integration of ferrite into a dual-layer reverse-helical inductor represents a novel approach to wireless passive sensing technology for temperature monitoring in metallic environments and a wider range of applications.
{"title":"A Dual-Layer Reverse-Helical Inductive Wireless Passive Flexible Temperature Sensor Integrated With Ferrite for Bearings Monitoring","authors":"Zhicheng Dong;Qiancheng Xu;Jingyi Tu;Yunlong Zhu;Jian Li;Yi Hu;Hangliang Ren;Peimei Dong;Xudong Cheng;Zhenyu Xue","doi":"10.1109/JSEN.2025.3601899","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3601899","url":null,"abstract":"A wireless passive flexible sensor has been developed to measure the surface temperature of bearings and transmit wireless signals. The sensor employs a dielectric film sandwiched by a double-layer reverse-helical inductor structure to enhance magnetic field coupling with a ferrite composite material at the bottom of the layers. Both the permittivity of the dielectric material and the permeability of the ferrite demonstrate temperature-sensitive characteristics. This configuration establishes a synergistic mechanism that enables both inductance–capacitance (<italic>LC</i>) sensitive to the change in temperature simultaneously. The ferrite substrate effectively prevents the spiral inductor antenna from electromagnetic absorption caused by metallic components. The type of dual-layer reverse-helical inductive wireless passive sensor enables efficient wireless transmission in a metallic environment. The sensitivity of this configuration can reach 237.34 kHz/°C with the maximal coupling distance extending to 21 mm. The exceptional stability of the resonant frequency of this dual-layer reverse-helical inductive structure was achieved through the mutual inhibition of <italic>LC</i> variations when the flexible sensor is subjected to bending on the surface of the bearing. The sensor of composite structure establishes dual-sensitive units and optimizes electromagnetic field coupling, achieving an integrated system with electromagnetically synergistic properties. The integration of ferrite into a dual-layer reverse-helical inductor represents a novel approach to wireless passive sensing technology for temperature monitoring in metallic environments and a wider range of applications.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37276-37287"},"PeriodicalIF":4.3,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145204542","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}
Pub Date : 2025-08-28DOI: 10.1109/JSEN.2025.3601590
Wanyu Chang;Defeng Chen;Huawei Cao;Linsheng Bu;Chao Wang;Tuo Fu
This article focuses on the midcourse track association scenario of ballistic target groups (BTGs) observed by ground-based pulse-Doppler radar. It proposes a BTG track association neural network (BTGTANN) to perform track detection and association for individual targets within a BTG. First, time–range profile (TRP) samples generated by performing pulse compression (PC) on raw echo signals are used to represent the spatial distribution of multiple targets over time. Second, a feature selection and aggregation (FSA) module and a context-aware enhancement (CAE) module are developed based on a convolutional neural network (CNN) architecture. These modules enhance the feature fusion and context awareness capabilities of the network. Finally, the target detection branch of the BTGTANN is used to detect multiple target tracks in TRP samples, yielding track detection boxes. An instance segmentation branch is then employed to accurately extract the contours of the tracks within the detection boxes, thereby determining the track positions at each pulse time. Unlike traditional methods, this approach formulates the multitarget track association problem as an object detection and instance segmentation task, providing an innovative solution within a deep learning framework. Experimental results on simulated datasets demonstrate that the detection probability (${P}_{d}$ ), the false alarm probability (${P}_{f}$ ), and the root-mean-square error (RMSE) of the BTGTANN reached 93.81%, 0.11%, and 8.43 m, respectively. Relative to the baseline, ${P}_{d}$ was increased by 5.70%, while ${P}_{f}$ and RMSE were decreased by 0.06% and 3.97 m, respectively. Moreover, the robustness of the BTGTANN is validated across different target scenarios, with the results indicating its substantial performance and generalizability under multiple targets, low-signal-to-noise ratio (SNR), and low-signal-to-clutter ratio (SCR) environments.
{"title":"Simulation of Deep Learning-Based Multitarget Track Association for Ballistic Target Groups","authors":"Wanyu Chang;Defeng Chen;Huawei Cao;Linsheng Bu;Chao Wang;Tuo Fu","doi":"10.1109/JSEN.2025.3601590","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3601590","url":null,"abstract":"This article focuses on the midcourse track association scenario of ballistic target groups (BTGs) observed by ground-based pulse-Doppler radar. It proposes a BTG track association neural network (BTGTANN) to perform track detection and association for individual targets within a BTG. First, time–range profile (TRP) samples generated by performing pulse compression (PC) on raw echo signals are used to represent the spatial distribution of multiple targets over time. Second, a feature selection and aggregation (FSA) module and a context-aware enhancement (CAE) module are developed based on a convolutional neural network (CNN) architecture. These modules enhance the feature fusion and context awareness capabilities of the network. Finally, the target detection branch of the BTGTANN is used to detect multiple target tracks in TRP samples, yielding track detection boxes. An instance segmentation branch is then employed to accurately extract the contours of the tracks within the detection boxes, thereby determining the track positions at each pulse time. Unlike traditional methods, this approach formulates the multitarget track association problem as an object detection and instance segmentation task, providing an innovative solution within a deep learning framework. Experimental results on simulated datasets demonstrate that the detection probability (<inline-formula> <tex-math>${P}_{d}$ </tex-math></inline-formula>), the false alarm probability (<inline-formula> <tex-math>${P}_{f}$ </tex-math></inline-formula>), and the root-mean-square error (RMSE) of the BTGTANN reached 93.81%, 0.11%, and 8.43 m, respectively. Relative to the baseline, <inline-formula> <tex-math>${P}_{d}$ </tex-math></inline-formula> was increased by 5.70%, while <inline-formula> <tex-math>${P}_{f}$ </tex-math></inline-formula> and RMSE were decreased by 0.06% and 3.97 m, respectively. Moreover, the robustness of the BTGTANN is validated across different target scenarios, with the results indicating its substantial performance and generalizability under multiple targets, low-signal-to-noise ratio (SNR), and low-signal-to-clutter ratio (SCR) environments.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37429-37444"},"PeriodicalIF":4.3,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11143873","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145204551","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}
Pub Date : 2025-08-28DOI: 10.1109/JSEN.2025.3595188
Jiaqi Zeng;Hongji Xu;Hao Zheng;Yipeng Xu;Yiran Li;Dongyu Li
Recent years have witnessed the conspicuous prosperity of deep neural networks in sensor-based human activity recognition (HAR). Nonetheless, some existing HAR frameworks based on deep learning (DL) architectures still face challenges in effectively extracting valid features and adaptively capturing complex dynamic information. Accordingly, most of the methods struggle to classify confusable activities. To settle the above challenges, a novel HAR framework for multidimensional feature extraction and fusion based on aggregation and temporal adaptation (MFEF-ATA) is proposed in this article. To construct the framework, initially, an aggregation transformation-based dual path module (ATDPM) is developed. Besides, a residual temporal bidirectional module (ResTBM) is presented, which is the residual connection of the temporal adaptive module (TAM) and bidirectional gated recurrent unit (Bi-GRU). Meanwhile, we construct a smart home activity (SHA) dataset to enrich the HAR sensor datasets from different application scenarios. The evaluation experiments of the MFEF-ATA framework are carried out on the wireless sensor data mining (WISDM) dataset, the University of California, Irvine HAR (UCI-HAR) dataset, and the SHA dataset. The experimental results show that the MFEF-ATA framework can derive better recognition performance than other state-of-the-art HAR frameworks with recognition accuracies of 99.12%, 97.77%, and 98.52% on the WISDM dataset, the UCI-HAR dataset, and the SHA dataset, respectively, which proves the effectiveness and superiority of the proposed framework.
{"title":"A Multidimensional Feature Extraction and Fusion Framework Based on Aggregation and Temporal Adaptation for Human Activity Recognition","authors":"Jiaqi Zeng;Hongji Xu;Hao Zheng;Yipeng Xu;Yiran Li;Dongyu Li","doi":"10.1109/JSEN.2025.3595188","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3595188","url":null,"abstract":"Recent years have witnessed the conspicuous prosperity of deep neural networks in sensor-based human activity recognition (HAR). Nonetheless, some existing HAR frameworks based on deep learning (DL) architectures still face challenges in effectively extracting valid features and adaptively capturing complex dynamic information. Accordingly, most of the methods struggle to classify confusable activities. To settle the above challenges, a novel HAR framework for multidimensional feature extraction and fusion based on aggregation and temporal adaptation (MFEF-ATA) is proposed in this article. To construct the framework, initially, an aggregation transformation-based dual path module (ATDPM) is developed. Besides, a residual temporal bidirectional module (ResTBM) is presented, which is the residual connection of the temporal adaptive module (TAM) and bidirectional gated recurrent unit (Bi-GRU). Meanwhile, we construct a smart home activity (SHA) dataset to enrich the HAR sensor datasets from different application scenarios. The evaluation experiments of the MFEF-ATA framework are carried out on the wireless sensor data mining (WISDM) dataset, the University of California, Irvine HAR (UCI-HAR) dataset, and the SHA dataset. The experimental results show that the MFEF-ATA framework can derive better recognition performance than other state-of-the-art HAR frameworks with recognition accuracies of 99.12%, 97.77%, and 98.52% on the WISDM dataset, the UCI-HAR dataset, and the SHA dataset, respectively, which proves the effectiveness and superiority of the proposed framework.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37339-37351"},"PeriodicalIF":4.3,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145204480","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}
Pub Date : 2025-08-28DOI: 10.1109/JSEN.2025.3601742
Alexandar R. Todorov;Huanghao Dai;Emily Yiu Hui Ko;Louay S. Abdulkarim;Naipapon Chupreecha;James Fuller;Emma Corden;Ying X. Teo;Russel N. Torah;Michael R. Ardern-Jones;Stephen P. Beeby
Recent advances in sensor technology offer the potential to transform dermatology by enabling continuous monitoring and objective, data-driven assessment of skin conditions. This work presents a novel wearable device for non-invasive assessment of atopic dermatitis (AD) severity in patients. The device uses a bespoke interdigitated capacitor (IDC) sensor, sensitive only to biomarkers of AD, namely stratum corneum (SC) hydration. The sensor is integrated into a flexible textile armband and paired with a compact readout circuit, capable of transmitting real-time SC hydration data via a custom graphical user interface (GUI). The device exhibited excellent measurement repeatability and stability under different environmental conditions. It was tested on 13 patients with the condition and demonstrated strong correlation with the standard clinical assessment tools such as the Corneometer ($r =0.595$ , $plt 0.05$ ). The e-textile IDC sensor identified a difference of 3–5 pF between skin with symptoms of the condition compared to skin without, while showing significantly less variability compared to the Corneometer. The improved stability and accuracy, combined with the conformal form-factor and ability to perform continuous measurements make the e-textile IDC sensor a much better candidate for at-home monitoring of AD in patients, compared to the current standard tools.
{"title":"Wearable System Using Printed Interdigitated Capacitive Sensor for Monitoring Atopic Dermatitis in Patients","authors":"Alexandar R. Todorov;Huanghao Dai;Emily Yiu Hui Ko;Louay S. Abdulkarim;Naipapon Chupreecha;James Fuller;Emma Corden;Ying X. Teo;Russel N. Torah;Michael R. Ardern-Jones;Stephen P. Beeby","doi":"10.1109/JSEN.2025.3601742","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3601742","url":null,"abstract":"Recent advances in sensor technology offer the potential to transform dermatology by enabling continuous monitoring and objective, data-driven assessment of skin conditions. This work presents a novel wearable device for non-invasive assessment of atopic dermatitis (AD) severity in patients. The device uses a bespoke interdigitated capacitor (IDC) sensor, sensitive only to biomarkers of AD, namely stratum corneum (SC) hydration. The sensor is integrated into a flexible textile armband and paired with a compact readout circuit, capable of transmitting real-time SC hydration data via a custom graphical user interface (GUI). The device exhibited excellent measurement repeatability and stability under different environmental conditions. It was tested on 13 patients with the condition and demonstrated strong correlation with the standard clinical assessment tools such as the Corneometer (<inline-formula> <tex-math>$r =0.595$ </tex-math></inline-formula>, <inline-formula> <tex-math>$plt 0.05$ </tex-math></inline-formula>). The e-textile IDC sensor identified a difference of 3–5 pF between skin with symptoms of the condition compared to skin without, while showing significantly less variability compared to the Corneometer. The improved stability and accuracy, combined with the conformal form-factor and ability to perform continuous measurements make the e-textile IDC sensor a much better candidate for at-home monitoring of AD in patients, compared to the current standard tools.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37266-37275"},"PeriodicalIF":4.3,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145204558","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}
Distributed optical fiber sensing (DOFS) systems have gained significant attention for their ability to monitor and detect various events through vibration signals. However, real-world environments are often complex and noisy, which poses significant challenges to accurate event recognition. In this article, we propose a novel deep learning framework to address these issues by integrating a Fourier transform-based time–frequency adaptive denoising (TFAD) module and a multiscale feature extraction (MSFE) network. The TFAD module transforms vibration signals from the time domain to the frequency domain, leveraging the powerful learning capabilities of deep learning to distinguish between noise components and the relevant vibration signal components. This allows for the filtering of frequency components that interfere with event recognition. Additionally, the time-series reconstructor is used to rebuild any missing information from the filtered signal, thereby improving the signal quality. The MSFE module employs fast Fourier convolution (FFC) with a global receptive field, combining it with standard convolution and incorporating frequency attention (FA) to enable lightweight and efficient extraction as well as fusion of both global and local features. Extensive experiments are conducted on a private distributed fiber sensing dataset and several public datasets. Results show that the proposed method achieves state-of-the-art performance while maintaining high efficiency, making it well-suited for edge deployment in real-world scenarios.
{"title":"Event Recognition in Distributed Optical Fiber Sensing Systems Using a Fourier-Enhanced Deep Learning Framework","authors":"Shilong Zhu;Bo Yin;Yue-Ting Sun;Tonglei Han;Hongao Zhao;Jiahe Zhu","doi":"10.1109/JSEN.2025.3601500","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3601500","url":null,"abstract":"Distributed optical fiber sensing (DOFS) systems have gained significant attention for their ability to monitor and detect various events through vibration signals. However, real-world environments are often complex and noisy, which poses significant challenges to accurate event recognition. In this article, we propose a novel deep learning framework to address these issues by integrating a Fourier transform-based time–frequency adaptive denoising (TFAD) module and a multiscale feature extraction (MSFE) network. The TFAD module transforms vibration signals from the time domain to the frequency domain, leveraging the powerful learning capabilities of deep learning to distinguish between noise components and the relevant vibration signal components. This allows for the filtering of frequency components that interfere with event recognition. Additionally, the time-series reconstructor is used to rebuild any missing information from the filtered signal, thereby improving the signal quality. The MSFE module employs fast Fourier convolution (FFC) with a global receptive field, combining it with standard convolution and incorporating frequency attention (FA) to enable lightweight and efficient extraction as well as fusion of both global and local features. Extensive experiments are conducted on a private distributed fiber sensing dataset and several public datasets. Results show that the proposed method achieves state-of-the-art performance while maintaining high efficiency, making it well-suited for edge deployment in real-world scenarios.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37255-37265"},"PeriodicalIF":4.3,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255947","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}
High-quality cardiopulmonary resuscitation (CPR) is a critical determinant of survival following cardiac arrest. In recent years, mechanical compression has become increasingly prevalent in the emergency management of cardiac arrest. The settings of key compression parameters strongly influence the effectiveness of chest compression. This study developed a semi-physical simulation platform and evaluation criteria to assess the optimal parameters for CPR. A multispring system was designed to simulate the risk of sternal fractures during chest compression. In addition, a blood flow model was constructed to simulate blood perfusion. The evaluation criteria, which include quantifying sternal fracture risk and blood perfusion, are used to calculate the compression effect by inputting the compression force and depth data into the evaluation model. Analysis of variance (ANOVA) demonstrated statistically significant impacts of different compression parameters on compression outcomes. The results demonstrated that the mechanical waveform data more accurately reflected the compression dynamics encountered in real-world CPR circumstances. The trapezoidal compression waveform demonstrated clear superiority over triangle and sine waveforms, enhancing blood circulation. This study’s exploration of the trapezoidal waveform fills a gap in American Heart Association (AHA) guidelines. In addition to the waveform, the study confirmed that a compression depth of 50 mm and a frequency of 120 compressions/min yielded the most effective hemodynamic outcomes. These findings validated and expanded upon the AHA guidelines, offering a novel and comprehensive approach by optimizing CPR effectiveness, improving both patient survival rates and the quality of mechanical resuscitation.
{"title":"A Semi-Physical Simulation System for Evaluation of Cardiopulmonary Resuscitation Mechanical Compression Parameters Based on Fracture Risk and Blood Perfusion","authors":"Yiming Chen;Yifeng Pan;Jiefeng Xu;Yufeng Hu;Mao Zhang;Peng Zhao","doi":"10.1109/JSEN.2025.3589561","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3589561","url":null,"abstract":"High-quality cardiopulmonary resuscitation (CPR) is a critical determinant of survival following cardiac arrest. In recent years, mechanical compression has become increasingly prevalent in the emergency management of cardiac arrest. The settings of key compression parameters strongly influence the effectiveness of chest compression. This study developed a semi-physical simulation platform and evaluation criteria to assess the optimal parameters for CPR. A multispring system was designed to simulate the risk of sternal fractures during chest compression. In addition, a blood flow model was constructed to simulate blood perfusion. The evaluation criteria, which include quantifying sternal fracture risk and blood perfusion, are used to calculate the compression effect by inputting the compression force and depth data into the evaluation model. Analysis of variance (ANOVA) demonstrated statistically significant impacts of different compression parameters on compression outcomes. The results demonstrated that the mechanical waveform data more accurately reflected the compression dynamics encountered in real-world CPR circumstances. The trapezoidal compression waveform demonstrated clear superiority over triangle and sine waveforms, enhancing blood circulation. This study’s exploration of the trapezoidal waveform fills a gap in American Heart Association (AHA) guidelines. In addition to the waveform, the study confirmed that a compression depth of 50 mm and a frequency of 120 compressions/min yielded the most effective hemodynamic outcomes. These findings validated and expanded upon the AHA guidelines, offering a novel and comprehensive approach by optimizing CPR effectiveness, improving both patient survival rates and the quality of mechanical resuscitation.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 17","pages":"32301-32311"},"PeriodicalIF":4.3,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144990081","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}
Pub Date : 2025-08-22DOI: 10.1109/JSEN.2025.3598798
Chien-Fu Cheng;Wen-Hao Lin
This study addresses the target-barrier coverage problem in a deterministic deployment setting, considering targets with varying levels of importance. Taking the surveillance of oil exploitation infrastructure in the Industrial Internet of Things (IIoT) as an example, different oil-related facilities within the exploitation area may have distinct levels of importance. To prevent potential damage, target-barriers must be constructed around these infrastructures. Targets of higher importance require target-barriers with extended response times, necessitating distance constraints that vary according to importance levels. To the best of our knowledge, this is the first work to address the target-barrier coverage problem while incorporating different levels of target importance. The primary objective is to minimize the number of deployed sensors needed to construct target-barriers in a deterministic manner while ensuring coverage requirements based on target importance. The minimum number of sensors required for target-barrier construction is analytically determined and formally proven. Additionally, the problem is shown to be NP-hard. Finally, simulation results are presented to evaluate the performance of the proposed algorithm.
{"title":"Deterministic Target-Barrier Coverage With Importance-Aware Sensor Deployment in IIoT","authors":"Chien-Fu Cheng;Wen-Hao Lin","doi":"10.1109/JSEN.2025.3598798","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3598798","url":null,"abstract":"This study addresses the target-barrier coverage problem in a deterministic deployment setting, considering targets with varying levels of importance. Taking the surveillance of oil exploitation infrastructure in the Industrial Internet of Things (IIoT) as an example, different oil-related facilities within the exploitation area may have distinct levels of importance. To prevent potential damage, target-barriers must be constructed around these infrastructures. Targets of higher importance require target-barriers with extended response times, necessitating distance constraints that vary according to importance levels. To the best of our knowledge, this is the first work to address the target-barrier coverage problem while incorporating different levels of target importance. The primary objective is to minimize the number of deployed sensors needed to construct target-barriers in a deterministic manner while ensuring coverage requirements based on target importance. The minimum number of sensors required for target-barrier construction is analytically determined and formally proven. Additionally, the problem is shown to be NP-hard. Finally, simulation results are presented to evaluate the performance of the proposed algorithm.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37370-37382"},"PeriodicalIF":4.3,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145204545","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}
Pub Date : 2025-08-21DOI: 10.1109/JSEN.2025.3599187
Lin Zhou;Zheng Zhao;Jiayuan Yan;Yong Jin;Yongjin Huo
In a multisensor collaborative tracking system, rational multisensor management methods can achieve optimal system performance. However, the complexity and variability of environmental risks will lead to reduced accuracy and safety of the tracking system. Therefore, this article proposes a multisensor management method based on multistep prediction of a bidirectional joint risk to rationally allocate limited sensor resources. First, this article comprehensively considers three risks, including the radiation risk of our multisensors, the risk of detection loss, and the threat risk of opposing targets, meanwhile constructing a bidirectional joint risk model. Second, adaptive weights for the three risks are proposed to adjust the three risks in the above model. Then, based on the framework of time-series prediction, the bidirectional joint risk is predicted. Finally, based on this, the problem of minimizing the multistep prediction bidirectional joint risk is proposed and then achieving the rational allocation of multisensor resources. The simulation results demonstrate that the proposed method is feasible, as it can effectively allocate limited sensor resources in a multirisk environment, improving the accuracy and security of the tracking system.
{"title":"Multisensor Management Method Based on Multistep Prediction of Bidirectional Joint Risk","authors":"Lin Zhou;Zheng Zhao;Jiayuan Yan;Yong Jin;Yongjin Huo","doi":"10.1109/JSEN.2025.3599187","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3599187","url":null,"abstract":"In a multisensor collaborative tracking system, rational multisensor management methods can achieve optimal system performance. However, the complexity and variability of environmental risks will lead to reduced accuracy and safety of the tracking system. Therefore, this article proposes a multisensor management method based on multistep prediction of a bidirectional joint risk to rationally allocate limited sensor resources. First, this article comprehensively considers three risks, including the radiation risk of our multisensors, the risk of detection loss, and the threat risk of opposing targets, meanwhile constructing a bidirectional joint risk model. Second, adaptive weights for the three risks are proposed to adjust the three risks in the above model. Then, based on the framework of time-series prediction, the bidirectional joint risk is predicted. Finally, based on this, the problem of minimizing the multistep prediction bidirectional joint risk is proposed and then achieving the rational allocation of multisensor resources. The simulation results demonstrate that the proposed method is feasible, as it can effectively allocate limited sensor resources in a multirisk environment, improving the accuracy and security of the tracking system.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37407-37418"},"PeriodicalIF":4.3,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145204553","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}
Pub Date : 2025-08-21DOI: 10.1109/JSEN.2025.3599435
Qi Zhang;Huicong Li;Shicheng Zhu;Xiaoshuai Dong
Wireless sensor networks (WSNs), with advantages, such as easy deployment and efficient data collection, constitute a critical component of the Internet of Things. However, WSNs face significant challenges in energy efficiency and prolonging network lifetime. To mitigate these identified limitations, the present work introduces a differential evolution optimized fuzzy logic controller and D-star (DEFLCD) algorithm for clustering routing in WSNs. First, the differential evolution (DE) algorithm is enhanced by integrating a population initialization method based on the SPM chaotic map, along with adaptive scaling factors, crossover probabilities, and an elite individual selection strategy, thereby improving the algorithm’s exploitation capability. Second, the optimized DE algorithm is employed to refine the output membership functions of the fuzzy logic controller (FLC). An innovative fitness metric is formulated to quantify the optimized FLC’s efficacy in improving cluster performance, thereby enhancing operational adaptability and robustness in dynamic networking environments. In the packet forwarding stage, the D-star methodology dynamically classifies congested nodes as routing barriers and establishes power-efficient multihop links between cluster heads (CHs) and the base station, achieving balanced energy utilization and improved scalability across large-scale network infrastructures. The simulation outcomes show that DEFLCD surpasses the existing algorithms in various network performance assessment metrics, offering an energy-efficient routing solution for large-scale monitoring applications.
{"title":"Differential Evolution Optimized Fuzzy Logic Controller and D-Star Algorithm for Clustering Routing in WSNs","authors":"Qi Zhang;Huicong Li;Shicheng Zhu;Xiaoshuai Dong","doi":"10.1109/JSEN.2025.3599435","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3599435","url":null,"abstract":"Wireless sensor networks (WSNs), with advantages, such as easy deployment and efficient data collection, constitute a critical component of the Internet of Things. However, WSNs face significant challenges in energy efficiency and prolonging network lifetime. To mitigate these identified limitations, the present work introduces a differential evolution optimized fuzzy logic controller and D-star (DEFLCD) algorithm for clustering routing in WSNs. First, the differential evolution (DE) algorithm is enhanced by integrating a population initialization method based on the SPM chaotic map, along with adaptive scaling factors, crossover probabilities, and an elite individual selection strategy, thereby improving the algorithm’s exploitation capability. Second, the optimized DE algorithm is employed to refine the output membership functions of the fuzzy logic controller (FLC). An innovative fitness metric is formulated to quantify the optimized FLC’s efficacy in improving cluster performance, thereby enhancing operational adaptability and robustness in dynamic networking environments. In the packet forwarding stage, the D-star methodology dynamically classifies congested nodes as routing barriers and establishes power-efficient multihop links between cluster heads (CHs) and the base station, achieving balanced energy utilization and improved scalability across large-scale network infrastructures. The simulation outcomes show that DEFLCD surpasses the existing algorithms in various network performance assessment metrics, offering an energy-efficient routing solution for large-scale monitoring applications.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"37394-37406"},"PeriodicalIF":4.3,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145204564","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}
The accurate train positioning is essential for ensuring safety and operational efficiency in modern rail systems. Traditional methods based on trackside infrastructure or satellite signals often suffer from limited precision or high cost, especially in Global Navigation Satellite Systems (GNSS)-denied environments. To address these challenges, this article proposes a hybrid vision–inertial train positioning method that combines the visual absolute positioning with inertial measurement unit (IMU)-based relative positioning. An enhanced you only look once (YOLO)-based object detection algorithm and an end-to-end text recognition network are employed to identify and interpret railway landmarks. The absolute position of the train is then retrieved by matching recognized text with a preconstructed database. To achieve continuous and robust localization, a differential evolution Kalman filter (DE-KF) is introduced to adaptively fuse IMU data with the vision-derived observations, dynamically tuning the process noise covariance in response to environmental variation. The proposed method was validated at Beijing National Railway Experimental Center. Experimental results demonstrate that the system maintains positioning errors within 3.5 m and achieves high recognition performance, with an mAP50 of 98.0%. These findings confirm the effectiveness of the proposed fusion framework for real-time, accurate, and resource-efficient train localization.
{"title":"Vision and Inertial Sensors Fusion for Train Positioning in GNSS-Denied Environments","authors":"Haifeng Song;Haoyu Zhang;Xiaoqing Wu;Wangzhe Li;Hairong Dong","doi":"10.1109/JSEN.2025.3597772","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3597772","url":null,"abstract":"The accurate train positioning is essential for ensuring safety and operational efficiency in modern rail systems. Traditional methods based on trackside infrastructure or satellite signals often suffer from limited precision or high cost, especially in Global Navigation Satellite Systems (GNSS)-denied environments. To address these challenges, this article proposes a hybrid vision–inertial train positioning method that combines the visual absolute positioning with inertial measurement unit (IMU)-based relative positioning. An enhanced you only look once (YOLO)-based object detection algorithm and an end-to-end text recognition network are employed to identify and interpret railway landmarks. The absolute position of the train is then retrieved by matching recognized text with a preconstructed database. To achieve continuous and robust localization, a differential evolution Kalman filter (DE-KF) is introduced to adaptively fuse IMU data with the vision-derived observations, dynamically tuning the process noise covariance in response to environmental variation. The proposed method was validated at Beijing National Railway Experimental Center. Experimental results demonstrate that the system maintains positioning errors within 3.5 m and achieves high recognition performance, with an mAP50 of 98.0%. These findings confirm the effectiveness of the proposed fusion framework for real-time, accurate, and resource-efficient train localization.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 18","pages":"35323-35334"},"PeriodicalIF":4.3,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073342","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：