The Internet of Things wireless sensor networks (IOTWSNs) are crucial in modern smart systems, where self-organizing sensor nodes enable efficient and flexible network structures for applications like environmental monitoring and smart cities. The task allocation problem in IOTWSNs is NP-hard, making effective strategies essential for optimal network performance. This article proposes an improved artificial jellyfish search algorithm (CECJS) that integrates chaotic initialization, elite, and cloning strategies to enhance global search ability and convergence speed. To evaluate CECJS’s efficiency, the article introduces network gain, reflecting both network effectiveness and task completion quality. Experimental results show that CECJS significantly outperforms traditional algorithms like genetic algorithm (GA), simulated annealing (SA), and particle swarm optimization (PSO) in task allocation gains, achieving improvements of several to tens of percentage points. In addition, CECJS exhibits faster convergence, finding near-optimal solutions more efficiently, making it an effective solution for large-scale IOTWSNs task optimization.
{"title":"A Chaotic Elite Cloning Artificial Jellyfish Algorithm for Efficient Task Allocation in IOTWSNs","authors":"Dikun Wen;Qike Cao;ShouRui Feng;Zhehao Zhang;Peng Zhou","doi":"10.1109/JSEN.2024.3523710","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3523710","url":null,"abstract":"The Internet of Things wireless sensor networks (IOTWSNs) are crucial in modern smart systems, where self-organizing sensor nodes enable efficient and flexible network structures for applications like environmental monitoring and smart cities. The task allocation problem in IOTWSNs is NP-hard, making effective strategies essential for optimal network performance. This article proposes an improved artificial jellyfish search algorithm (CECJS) that integrates chaotic initialization, elite, and cloning strategies to enhance global search ability and convergence speed. To evaluate CECJS’s efficiency, the article introduces network gain, reflecting both network effectiveness and task completion quality. Experimental results show that CECJS significantly outperforms traditional algorithms like genetic algorithm (GA), simulated annealing (SA), and particle swarm optimization (PSO) in task allocation gains, achieving improvements of several to tens of percentage points. In addition, CECJS exhibits faster convergence, finding near-optimal solutions more efficiently, making it an effective solution for large-scale IOTWSNs task optimization.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"6905-6919"},"PeriodicalIF":4.3,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446243","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 : 2025-01-06DOI: 10.1109/JSEN.2024.3522990
Xianglong Zhao;Yuntao He;Xinrui Wang;Jing Liu;Xianggui Kong;Wenying Shi
Pressure-induced optical materials show great potential in optical devices, pressure sensing, and information anticounterfeiting. However, pressure-induced room temperature phosphorescent (RTP) molecules in a thermodynamic steady state are insensitive to external stimuli, limiting their practical application. Here, layered double hydroxide (LDH) with a 2-D topological structures can bring carbon dots (CDs) into a thermodynamic nonequilibrium state, which is a prerequisite for the enhancement in pressure sensitivity. Furthermore, considering the inherent rigidity of LDH contradicts the pressure sensitivity, the dual buffering layers are introduced, where the borate ions and polymer polyvinyl alcohol (PVA) as internal and external buffer layers, respectively. The dual buffering layers can help interlayer molecules to achieve highly anisotropic arrangement and induce the initial formation of thermodynamic nonequilibrium arrays. Thus, the CDs@BO3-LDH-PVA film can change the RTP intensity significantly under the extremely low pressure of 12 MPa. This strategy links the nonequilibrium state with the buffer layer, which provides a new idea for the design of pressure-induced optical sensing material.
{"title":"Two-Dimensional Topological Structures Boost the Construction of Nonequilibrium Array for Optical Pressure Sensing","authors":"Xianglong Zhao;Yuntao He;Xinrui Wang;Jing Liu;Xianggui Kong;Wenying Shi","doi":"10.1109/JSEN.2024.3522990","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3522990","url":null,"abstract":"Pressure-induced optical materials show great potential in optical devices, pressure sensing, and information anticounterfeiting. However, pressure-induced room temperature phosphorescent (RTP) molecules in a thermodynamic steady state are insensitive to external stimuli, limiting their practical application. Here, layered double hydroxide (LDH) with a 2-D topological structures can bring carbon dots (CDs) into a thermodynamic nonequilibrium state, which is a prerequisite for the enhancement in pressure sensitivity. Furthermore, considering the inherent rigidity of LDH contradicts the pressure sensitivity, the dual buffering layers are introduced, where the borate ions and polymer polyvinyl alcohol (PVA) as internal and external buffer layers, respectively. The dual buffering layers can help interlayer molecules to achieve highly anisotropic arrangement and induce the initial formation of thermodynamic nonequilibrium arrays. Thus, the CDs@BO3-LDH-PVA film can change the RTP intensity significantly under the extremely low pressure of 12 MPa. This strategy links the nonequilibrium state with the buffer layer, which provides a new idea for the design of pressure-induced optical sensing material.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"6114-6121"},"PeriodicalIF":4.3,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422863","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 : 2025-01-06DOI: 10.1109/JSEN.2024.3523569
Jung Hyun Lee;Taek Hyun Ko;Dong-Wook Lee
Autonomous driving (AD) perception technology integrates images from variously positioned cameras to comprehend the surrounding environment. To accurately perceive these surroundings, it is essential to know both the precise pose of each camera and their exact alignment. Traditional online calibration methods are inadequate for AD perception because they either overlook the alignment between cameras with different fields of view (FoVs) or only consider alignment among cameras with the same FoV. This article introduces a spatiotemporal calibration method that analyzes both spatial and temporal information of cameras to estimate the poses of all cameras and their interrelationships without any restrictions on the camera mounting poses and FoVs. Temporal and spatial data are used separately to estimate camera poses, and the outcomes are merged to determine the optimized camera positions for seamless multicamera fusion (MCF). To assess the effectiveness of our proposed method, we compared it with an existing method using a specialized calibration facility and found that our results closely match those of the facility. Moreover, real-world driving tests show that our method surpasses existing methods that rely on a specialized calibration facility.
{"title":"Spatiotemporal Calibration for Autonomous Driving Multicamera Perception","authors":"Jung Hyun Lee;Taek Hyun Ko;Dong-Wook Lee","doi":"10.1109/JSEN.2024.3523569","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3523569","url":null,"abstract":"Autonomous driving (AD) perception technology integrates images from variously positioned cameras to comprehend the surrounding environment. To accurately perceive these surroundings, it is essential to know both the precise pose of each camera and their exact alignment. Traditional online calibration methods are inadequate for AD perception because they either overlook the alignment between cameras with different fields of view (FoVs) or only consider alignment among cameras with the same FoV. This article introduces a spatiotemporal calibration method that analyzes both spatial and temporal information of cameras to estimate the poses of all cameras and their interrelationships without any restrictions on the camera mounting poses and FoVs. Temporal and spatial data are used separately to estimate camera poses, and the outcomes are merged to determine the optimized camera positions for seamless multicamera fusion (MCF). To assess the effectiveness of our proposed method, we compared it with an existing method using a specialized calibration facility and found that our results closely match those of the facility. Moreover, real-world driving tests show that our method surpasses existing methods that rely on a specialized calibration facility.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"7227-7241"},"PeriodicalIF":4.3,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430410","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}
Diagnosis of tuberculosis (TB) is time-consuming, cumbersome, and expensive. Moreover, there is a lack of real-time monitoring of screening and testing as well as data management and storage. Serological screening point-of-care tests, which are rapid and affordable, have been viewed as a desirable method for TB diagnosis for a long time, although they cannot be used to confirm the disease. Three novel antigens of mycobacterium TB (MTB), the causative agent of TB, have been considered for the colorimetric diagnosis. The immunochromatic flowthrough test (ICT) devices were developed to screen the suspected cases of active TB with high sensitivity and specificity. In this work, using these ICT devices, we have now developed an image sensing method based on dataset of images and trained a model to create a custom-made phone application for the accurate detection of TB with real-time reporting. The image sensing of the colorimetric outcome was integrated with different classifications, of which feedforward neural network (FNN) allowed us to make predictions with an overall accuracy of ~82%, and this is on par with the results of existing literature. With a sensitivity of 87%, a specificity of 82%, an AUC score of 0.84, and an ${F}1$ -score of 81% (No TB) and 82% (with TB), the suggested approach demonstrates enhanced efficiency compared to naked eye results. This image sensing technique can significantly reduce the possibility of errors resulting from visual results and color ambiguity.
{"title":"Quantitative Image Sensing of Tuberculosis Biomarkers Using Rapid Diagnostic Test Kit","authors":"Subham Das;Arti Shrivas;Payal Soni;Anil Kumar Gupta;Sarman Singh;Mitradip Bhattacharjee","doi":"10.1109/JSEN.2024.3523750","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3523750","url":null,"abstract":"Diagnosis of tuberculosis (TB) is time-consuming, cumbersome, and expensive. Moreover, there is a lack of real-time monitoring of screening and testing as well as data management and storage. Serological screening point-of-care tests, which are rapid and affordable, have been viewed as a desirable method for TB diagnosis for a long time, although they cannot be used to confirm the disease. Three novel antigens of mycobacterium TB (MTB), the causative agent of TB, have been considered for the colorimetric diagnosis. The immunochromatic flowthrough test (ICT) devices were developed to screen the suspected cases of active TB with high sensitivity and specificity. In this work, using these ICT devices, we have now developed an image sensing method based on dataset of images and trained a model to create a custom-made phone application for the accurate detection of TB with real-time reporting. The image sensing of the colorimetric outcome was integrated with different classifications, of which feedforward neural network (FNN) allowed us to make predictions with an overall accuracy of ~82%, and this is on par with the results of existing literature. With a sensitivity of 87%, a specificity of 82%, an AUC score of 0.84, and an <inline-formula> <tex-math>${F}1$ </tex-math></inline-formula>-score of 81% (No TB) and 82% (with TB), the suggested approach demonstrates enhanced efficiency compared to naked eye results. This image sensing technique can significantly reduce the possibility of errors resulting from visual results and color ambiguity.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"7242-7249"},"PeriodicalIF":4.3,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430544","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 : 2025-01-06DOI: 10.1109/JSEN.2024.3523475
Shoudong Han;Ziwen Zhang;Xinpeng Yuan;Delie Ming
Occlusion scenarios pose a great challenge to person re-identification (ReID) task because various occlusions may weaken the discriminative features and introduce interference. Recently, transformer-based networks, which can aggregate features of all the image patches to construct global features adaptively, have shown advantages in occluded person ReID. Existing methods mainly adopted transformer as a feature extractor and enhanced local features from the output of the transformer encoder. However, during the processing of self-attention blocks, disturbing features from occlusions may be diffused into all the tokens, making it difficult to enhance local features effectively. On the other hand, the different heads in self-attention remain isolated during image encoding. Therefore, we consider applying feature enhancement strategies in the channel dimensions instead of the spatial dimensions. First, we divide the heads into groups to enhance diversity and strengthen the robustness of some patterns in occlusion scenarios. Then during training we iteratively suppress the most salient patterns, forcing the model to mine more salient patterns. Finally, we assign adaptive weights for different head groups to compute a robust distance matrix. Our method enhances the model’s ability to extract discriminative and diverse head features and achieves the state-of-the-art performance on occluded person ReID benchmarks, e.g., Rank-1 of 73.2% on Occluded-DukeMTMC.
{"title":"Enhance Heads in Vision Transformer for Occluded Person Re-Identification","authors":"Shoudong Han;Ziwen Zhang;Xinpeng Yuan;Delie Ming","doi":"10.1109/JSEN.2024.3523475","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3523475","url":null,"abstract":"Occlusion scenarios pose a great challenge to person re-identification (ReID) task because various occlusions may weaken the discriminative features and introduce interference. Recently, transformer-based networks, which can aggregate features of all the image patches to construct global features adaptively, have shown advantages in occluded person ReID. Existing methods mainly adopted transformer as a feature extractor and enhanced local features from the output of the transformer encoder. However, during the processing of self-attention blocks, disturbing features from occlusions may be diffused into all the tokens, making it difficult to enhance local features effectively. On the other hand, the different heads in self-attention remain isolated during image encoding. Therefore, we consider applying feature enhancement strategies in the channel dimensions instead of the spatial dimensions. First, we divide the heads into groups to enhance diversity and strengthen the robustness of some patterns in occlusion scenarios. Then during training we iteratively suppress the most salient patterns, forcing the model to mine more salient patterns. Finally, we assign adaptive weights for different head groups to compute a robust distance matrix. Our method enhances the model’s ability to extract discriminative and diverse head features and achieves the state-of-the-art performance on occluded person ReID benchmarks, e.g., Rank-1 of 73.2% on Occluded-DukeMTMC.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"6894-6904"},"PeriodicalIF":4.3,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446244","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}
Ground penetrating radar (GPR) forward and inversion methods are key techniques for studying radar imaging mechanisms and investigating subsurface scenes. Efficiently interpreting radar wave data will facilitate the development of subsurface structure detection applications, especially in the intricate plant root distribution. Existing forward and inversion models are constrained by the highly computational and time-consuming forward process, making it difficult to be applied to complex real-world subsurface scenarios. Inspired by the spatio-temporal properties during radar wave imaging, a spatial and temporal fusion cycle U-shaped model named GPR-CUNet was proposed. The model is more adapted to the transformation between permittivity distribution and GPR B-Scan data in complex environment. First, to extract the spatial and temporal features from the permittivity distribution and radar data, a spatio-temporal feature fusion module (STFM) based on CNN and BiLSTM was designed. Then, for the translation between the permittivity distribution and the radar wave data, two identical U-shaped networks with the STFM were constructed. Finally, guided by predictive consistency and cyclic consistency, a hybrid loss function based on multiscale structural similarity (MS-SSIM) and L1 norm was configured to boost the performance of both the forward and inversion networks. The numerical simulation experiments revealed that the proposed model imparted exceptional performance and efficiency in the prediction of radar wave features and reconstruction of permittivity distribution under complex scenarios. In preburial experiments and field root testing, our inversion model can effectively recover the subsurface root and soil horizons distribution. Accurate permittivity distribution of subsurface scene can provide a theoretical basis for imaging and 3-D reconstruction of the physical media distribution in plant root zones.
{"title":"GPR-CUNet: Spatio-Temporal Feature Fusion-Based GPR Forward and Inversion Cycle Network for Root Scene Survey","authors":"Xiaowei Zhang;Xuan Zhao;Shuang Li;Shenghua Lv;Chen Lin;Jian Wen","doi":"10.1109/JSEN.2024.3522888","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3522888","url":null,"abstract":"Ground penetrating radar (GPR) forward and inversion methods are key techniques for studying radar imaging mechanisms and investigating subsurface scenes. Efficiently interpreting radar wave data will facilitate the development of subsurface structure detection applications, especially in the intricate plant root distribution. Existing forward and inversion models are constrained by the highly computational and time-consuming forward process, making it difficult to be applied to complex real-world subsurface scenarios. Inspired by the spatio-temporal properties during radar wave imaging, a spatial and temporal fusion cycle U-shaped model named GPR-CUNet was proposed. The model is more adapted to the transformation between permittivity distribution and GPR B-Scan data in complex environment. First, to extract the spatial and temporal features from the permittivity distribution and radar data, a spatio-temporal feature fusion module (STFM) based on CNN and BiLSTM was designed. Then, for the translation between the permittivity distribution and the radar wave data, two identical U-shaped networks with the STFM were constructed. Finally, guided by predictive consistency and cyclic consistency, a hybrid loss function based on multiscale structural similarity (MS-SSIM) and L1 norm was configured to boost the performance of both the forward and inversion networks. The numerical simulation experiments revealed that the proposed model imparted exceptional performance and efficiency in the prediction of radar wave features and reconstruction of permittivity distribution under complex scenarios. In preburial experiments and field root testing, our inversion model can effectively recover the subsurface root and soil horizons distribution. Accurate permittivity distribution of subsurface scene can provide a theoretical basis for imaging and 3-D reconstruction of the physical media distribution in plant root zones.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"7569-7583"},"PeriodicalIF":4.3,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438354","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 : 2025-01-03DOI: 10.1109/JSEN.2024.3523035
Kapil Gupta;Varun Bajaj;Irshad Ahmad Ansari
Myocardial infarction (MI) stands as one of the most critical cardiac complications, occurring when blood flow to the cardiovascular system is partially or completely blocked. Electrocardiography (ECG) is an invaluable tool for detecting diverse cardiac irregularities. Manual investigation of MI-induced ECG changes is tedious, laborious, and time-consuming. Nowadays, deep learning-based algorithms are widely investigated to detect various cardiac abnormalities and enhance the performance of medical diagnostic systems. Therefore, this work presents a lightweight deep learning framework (CardioNet) for MI detection using ECG signals. To construct time-frequency (T-F) spectrograms, filtered ECG sensor data are subjected to the short-time Fourier transform (STFT), movable Gaussian window-based S-transform (ST), and smoothed pseudo-Wigner-Ville distribution (SPWVD) methods. To develop an automated MI detection system, obtained spectrograms are fed to benchmark Squeeze-Net, Alex-Net, and a newly developed, lightweight deep learning model. The developed CardioNet with ST-based T-F images has obtained an average classification accuracy of 99.82%, a specificity of 99.57%, and a sensitivity of 99.97%. The proposed system, in combination with a cloud-based algorithm, is suitable for designing wearable to detect several cardiac diseases using other biological signals from the cardiovascular system.
心肌梗塞（MI）是最严重的心脏并发症之一，当心血管系统的血流部分或完全受阻时就会发生。心电图（ECG）是检测各种心脏异常的重要工具。人工调查心肌梗死引起的心电图变化既繁琐、费力又耗时。如今，基于深度学习的算法被广泛用于检测各种心脏异常，并提高医疗诊断系统的性能。因此，本研究提出了一种轻量级深度学习框架（CardioNet），用于利用心电信号检测心肌梗死。为了构建时频（T-F）频谱图，对滤波后的心电图传感器数据采用了短时傅立叶变换（STFT）、基于可移动高斯窗的S变换（ST）和平滑伪维格纳-维尔分布（SPWVD）方法。为了开发 MI 自动检测系统，获得的频谱图被输入到基准 Squeeze-Net、Alex-Net 和新开发的轻量级深度学习模型中。利用基于 ST 的 T-F 图像开发的 CardioNet 获得了 99.82% 的平均分类准确率、99.57% 的特异性和 99.97% 的灵敏度。所提出的系统与基于云的算法相结合，适用于设计可穿戴设备，利用心血管系统的其他生物信号检测多种心脏疾病。
{"title":"CardioNet: A Lightweight Deep Learning Framework for Screening of Myocardial Infarction Using ECG Sensor Data","authors":"Kapil Gupta;Varun Bajaj;Irshad Ahmad Ansari","doi":"10.1109/JSEN.2024.3523035","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3523035","url":null,"abstract":"Myocardial infarction (MI) stands as one of the most critical cardiac complications, occurring when blood flow to the cardiovascular system is partially or completely blocked. Electrocardiography (ECG) is an invaluable tool for detecting diverse cardiac irregularities. Manual investigation of MI-induced ECG changes is tedious, laborious, and time-consuming. Nowadays, deep learning-based algorithms are widely investigated to detect various cardiac abnormalities and enhance the performance of medical diagnostic systems. Therefore, this work presents a lightweight deep learning framework (CardioNet) for MI detection using ECG signals. To construct time-frequency (T-F) spectrograms, filtered ECG sensor data are subjected to the short-time Fourier transform (STFT), movable Gaussian window-based S-transform (ST), and smoothed pseudo-Wigner-Ville distribution (SPWVD) methods. To develop an automated MI detection system, obtained spectrograms are fed to benchmark Squeeze-Net, Alex-Net, and a newly developed, lightweight deep learning model. The developed CardioNet with ST-based T-F images has obtained an average classification accuracy of 99.82%, a specificity of 99.57%, and a sensitivity of 99.97%. The proposed system, in combination with a cloud-based algorithm, is suitable for designing wearable to detect several cardiac diseases using other biological signals from the cardiovascular system.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"6794-6800"},"PeriodicalIF":4.3,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446187","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}
Atmospheric fine particulate matter (PM2.5) poses significant risks to both environmental and human health, highlighting the need for regional estimations and spatiotemporal analyses. While most studies have focused on large-scale areas, such as global or national levels, fewer studies addressed PM2.5 at the urban level. This study analyzed PM2.5 monitoring data from ground stations in Wuhan, collected between July 2018 and July 2023, integrating 1 km aerosol optical depth (AOD) products, Sentinel-5 NO2 column concentration data, nighttime light remote sensing, and ERA5 reanalysis meteorological data. Key innovations included selecting NO2 column concentration data, as NOx primarily exists as NO2, and using novel Sentinel-5P measurements rarely explored in related research. Three PM2.5 estimation models were developed: multiple linear regression (MLR), extreme gradient boosting (XGBoost), and random forest (RF). Evaluation results showed that all models achieved Pearson’s correlation coefficients (r) above 0.8, with the segmented RF-XGBoost model performing best, reaching an average relative error of 10.38%. Using this optimal model, monthly spatiotemporal maps of PM2.5 concentrations in Wuhan were generated. Key findings include 1) seasonal PM2.5 levels in Wuhan were lower in summer and higher in winter; 2) significant regional disparities in PM2.5 levels were observed, with persistently high pollution in areas such as Qing Shan; and 3) significant changes in PM2.5 levels before and after the COVID-19 pandemic, characterized by an overall decrease in concentrations from 2019 to 2020, followed by gradual increases in certain districts post-lockdown. This study provides valuable insights for urban-level PM2.5 estimation, supporting effective pollution control strategies.
{"title":"Spatiotemporal Estimation and Analysis of PM2.5 Concentrations in Wuhan Utilizing Multisource Remote Sensing Data and NOx as Inputs for Machine Learning Models","authors":"Jinwen Song;Xinyan Hong;Kai Yu;Baoyin He;Shenshen Wu;Ke Hu;Junrui Zhou;Dehao Zhan;Qi Feng;Yadong Zhou;Tao Li;Fan Yang","doi":"10.1109/JSEN.2024.3523046","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3523046","url":null,"abstract":"Atmospheric fine particulate matter (PM2.5) poses significant risks to both environmental and human health, highlighting the need for regional estimations and spatiotemporal analyses. While most studies have focused on large-scale areas, such as global or national levels, fewer studies addressed PM2.5 at the urban level. This study analyzed PM2.5 monitoring data from ground stations in Wuhan, collected between July 2018 and July 2023, integrating 1 km aerosol optical depth (AOD) products, Sentinel-5 NO2 column concentration data, nighttime light remote sensing, and ERA5 reanalysis meteorological data. Key innovations included selecting NO2 column concentration data, as NOx primarily exists as NO2, and using novel Sentinel-5P measurements rarely explored in related research. Three PM2.5 estimation models were developed: multiple linear regression (MLR), extreme gradient boosting (XGBoost), and random forest (RF). Evaluation results showed that all models achieved Pearson’s correlation coefficients (r) above 0.8, with the segmented RF-XGBoost model performing best, reaching an average relative error of 10.38%. Using this optimal model, monthly spatiotemporal maps of PM2.5 concentrations in Wuhan were generated. Key findings include 1) seasonal PM2.5 levels in Wuhan were lower in summer and higher in winter; 2) significant regional disparities in PM2.5 levels were observed, with persistently high pollution in areas such as Qing Shan; and 3) significant changes in PM2.5 levels before and after the COVID-19 pandemic, characterized by an overall decrease in concentrations from 2019 to 2020, followed by gradual increases in certain districts post-lockdown. This study provides valuable insights for urban-level PM2.5 estimation, supporting effective pollution control strategies.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"6812-6824"},"PeriodicalIF":4.3,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446282","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 : 2025-01-03DOI: 10.1109/JSEN.2024.3523176
Zhan Gao;Weixiong Jiang;Jun Wu;Tianjiao Dai
Remaining useful life (RUL) prediction plays a critical role in mechanical systems. RNN-based methods have achieved unprecedented success. However, these methods neglect spatial dependencies among sensors and suffer from long-term dependency learning. To break through these limitations, a novel multiscale spatiotemporal attention network (MSAN) is proposed for predicting the RUL of aircraft engines. In the MSAN, a multiscale discrete wavelet transformation (MDWT) is first constructed to obtain a multiscale subseries set. Then, an adaptive spatiotemporal feature extraction module is proposed to mine both long-term and spatial dependencies and form holistic spatiotemporal features by a collaborative spatiotemporal learning module (CSLM). Finally, a versatile fusion module is developed to integrate holistic spatiotemporal features for RUL prediction. The MSAN is validated on C-MAPSS datasets, and the experimental results demonstrate that the MSAN can better perform prediction tasks than existing state-of-the-art (SOTA) methods.
{"title":"Multiscale Spatiotemporal Attention Network for Remaining Useful Life Prediction of Mechanical Systems","authors":"Zhan Gao;Weixiong Jiang;Jun Wu;Tianjiao Dai","doi":"10.1109/JSEN.2024.3523176","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3523176","url":null,"abstract":"Remaining useful life (RUL) prediction plays a critical role in mechanical systems. RNN-based methods have achieved unprecedented success. However, these methods neglect spatial dependencies among sensors and suffer from long-term dependency learning. To break through these limitations, a novel multiscale spatiotemporal attention network (MSAN) is proposed for predicting the RUL of aircraft engines. In the MSAN, a multiscale discrete wavelet transformation (MDWT) is first constructed to obtain a multiscale subseries set. Then, an adaptive spatiotemporal feature extraction module is proposed to mine both long-term and spatial dependencies and form holistic spatiotemporal features by a collaborative spatiotemporal learning module (CSLM). Finally, a versatile fusion module is developed to integrate holistic spatiotemporal features for RUL prediction. The MSAN is validated on C-MAPSS datasets, and the experimental results demonstrate that the MSAN can better perform prediction tasks than existing state-of-the-art (SOTA) methods.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 4","pages":"6825-6835"},"PeriodicalIF":4.3,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446222","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：