Deriving a unique cryptographic key from biometric measurements is a challenging task due to the existing noise gap between the biometric measurements and error correction coding. Additionally, privacy and security concerns arise as biometric measurements are inherently linked to the user. Bio-cryptosystems represent a key branch of solutions aimed at addressing these issues. However, many existing bio-cryptosystems rely on handcrafted feature extractors and error correction codes (ECC), often leading to performance degradation. To address these challenges and improve the reliability of biometric measurements, we propose a novel biometric cryptosystem (BC) named WiFaKey, for generating cryptographic keys from face in unconstrained settings. Specifically, WiFaKey first introduces an adaptive random masking-driven feature transformation pipeline, AdaMTrans. AdaMTrans effectively quantizes and binarizes real-valued features and incorporates an adaptive random masking scheme to align the bit error rate (BER) with error correction requirements, thereby mitigating the noise gap. Besides, WiFaKey incorporates a supervised learning-based neural decoding scheme called neural-MS decoder, which delivers a more robust error correction performance with less iteration than nonlearning decoders, thereby alleviating the performance degradation. We evaluated WiFaKey using widely adopted face feature extractors on six large unconstrained and two constrained datasets. On the labeled faces in the wild database (LFW) dataset, WiFaKey achieved an average genuine match rate (GMR) of 85.45% and 85.20% at a 0% false match rate (FMR) for MagFace and AdaFace features, respectively. Our comprehensive comparative analysis shows a significant performance improvement of WiFaKey. The source code of our work is available at github.com/xingbod/WiFaKey.
{"title":"WiFaKey: Generating Cryptographic Keys From Face in the Wild","authors":"Xingbo Dong;Hui Zhang;Yen Lung Lai;Zhe Jin;Junduan Huang;Wenxiong Kang;Andrew Beng Jin Teoh","doi":"10.1109/TIM.2024.3485436","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485436","url":null,"abstract":"Deriving a unique cryptographic key from biometric measurements is a challenging task due to the existing noise gap between the biometric measurements and error correction coding. Additionally, privacy and security concerns arise as biometric measurements are inherently linked to the user. Bio-cryptosystems represent a key branch of solutions aimed at addressing these issues. However, many existing bio-cryptosystems rely on handcrafted feature extractors and error correction codes (ECC), often leading to performance degradation. To address these challenges and improve the reliability of biometric measurements, we propose a novel biometric cryptosystem (BC) named WiFaKey, for generating cryptographic keys from face in unconstrained settings. Specifically, WiFaKey first introduces an adaptive random masking-driven feature transformation pipeline, AdaMTrans. AdaMTrans effectively quantizes and binarizes real-valued features and incorporates an adaptive random masking scheme to align the bit error rate (BER) with error correction requirements, thereby mitigating the noise gap. Besides, WiFaKey incorporates a supervised learning-based neural decoding scheme called neural-MS decoder, which delivers a more robust error correction performance with less iteration than nonlearning decoders, thereby alleviating the performance degradation. We evaluated WiFaKey using widely adopted face feature extractors on six large unconstrained and two constrained datasets. On the labeled faces in the wild database (LFW) dataset, WiFaKey achieved an average genuine match rate (GMR) of 85.45% and 85.20% at a 0% false match rate (FMR) for MagFace and AdaFace features, respectively. Our comprehensive comparative analysis shows a significant performance improvement of WiFaKey. The source code of our work is available at github.com/xingbod/WiFaKey.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-16"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As an indicator of grain safety, grain temperature data assumes great importance in the analysis of grain storage conditions and the decision-making of preventive measures such as ventilation and cooling. However, obtaining a thorough picture of grain temperature distribution via grain IoT with sensors deployed in the granary remains a challenge, given numerous data gaps across various areas due to insufficient coverage of the sensor network that fails to encompass the entire granary. Interpolation of grain temperature data, in this regard, is able to fill in the “unsensored” areas that are vacant in the records of data. Yet little literature is found in the frontier scholarship of grain temperature interpolation. To fill this noticeable niche, this study develops a novel data fusion interpolation model named convolutional neural network-attention-multilayer perceptron neural network (CAMNN) featuring an integration of convolutional neural network (CNN), attention mechanism, and multilayer perceptron (MLP). CNN is used to capture local spatial features of the temperature data, the attention mechanism enables the location of key and sensitive temperature areas, and MLP is incorporated for deep feature fusion. Performances of the proposed model are evaluated in a bin granary located in Shaanxi, China, and further validated in a larger bin granary of different storage types situated in Ningxia, China. Comparative assessments are conducted with five machine learning and deep learning (DL) models. Results indicate that CAMNN outperforms the other models, with a mean absolute error (MAE) of 0.5251 and a mean square error (mse) of 1.0881, demonstrating robust cross-context applicability across bin granaries varying in terms of sizes, storage types, and climatic zones.
{"title":"On Grain Security by Temperature Interpolation: A Deep Learning Method for Comprehensive Data Fusion in Smart Granaries","authors":"Zhongke Qu;Ke Yang;Yue Li;Xuemei Jiang;Yang Zhang;Yanyan Zhao;Wenfei Wu;Yuan Gao;Zhaolin Gu;Zhibin Zhao","doi":"10.1109/TIM.2024.3485435","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485435","url":null,"abstract":"As an indicator of grain safety, grain temperature data assumes great importance in the analysis of grain storage conditions and the decision-making of preventive measures such as ventilation and cooling. However, obtaining a thorough picture of grain temperature distribution via grain IoT with sensors deployed in the granary remains a challenge, given numerous data gaps across various areas due to insufficient coverage of the sensor network that fails to encompass the entire granary. Interpolation of grain temperature data, in this regard, is able to fill in the “unsensored” areas that are vacant in the records of data. Yet little literature is found in the frontier scholarship of grain temperature interpolation. To fill this noticeable niche, this study develops a novel data fusion interpolation model named convolutional neural network-attention-multilayer perceptron neural network (CAMNN) featuring an integration of convolutional neural network (CNN), attention mechanism, and multilayer perceptron (MLP). CNN is used to capture local spatial features of the temperature data, the attention mechanism enables the location of key and sensitive temperature areas, and MLP is incorporated for deep feature fusion. Performances of the proposed model are evaluated in a bin granary located in Shaanxi, China, and further validated in a larger bin granary of different storage types situated in Ningxia, China. Comparative assessments are conducted with five machine learning and deep learning (DL) models. Results indicate that CAMNN outperforms the other models, with a mean absolute error (MAE) of 0.5251 and a mean square error (mse) of 1.0881, demonstrating robust cross-context applicability across bin granaries varying in terms of sizes, storage types, and climatic zones.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-20"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article presents the method to evaluate the fast neutron energy spectrum using the single-crystal chemical vapor deposition (CVD) diamond detector to be applicable on the radiation monitoring in advanced scientific/engineering systems usually characterized with mixed and high-dose radiation field. The pulse shape discrimination (PSD) based on the shape and the width of a pulse was applied to extract events, in which fast neutron hits at the specific depth of the single-crystal diamond. Unfolding of the measured spectrum for extracted pulses could deduce the neutron energy spectrum. Experiments using monoenergetic neutron sources demonstrated the reliable capability of this method to evaluate the neutron energy spectrum quantitatively.
{"title":"Application of a Single-Crystal CVD Diamond Detector for Fast Neutron Measurement in High Dose and Mixed Radiation Fields","authors":"Makoto I. Kobayashi;Sachiko Yoshihashi;Kunihiro Ogawa;Mitsutaka Isobe;Tsukasa Aso;Masanori Hara;Siriyaporn Sangaroon;Sachie Kusaka;Shingo Tamaki;Isao Murata;Sho Toyama;Misako Miwa;Shigeo Matsuyama;Masaki Osakabe","doi":"10.1109/TIM.2024.3481590","DOIUrl":"https://doi.org/10.1109/TIM.2024.3481590","url":null,"abstract":"This article presents the method to evaluate the fast neutron energy spectrum using the single-crystal chemical vapor deposition (CVD) diamond detector to be applicable on the radiation monitoring in advanced scientific/engineering systems usually characterized with mixed and high-dose radiation field. The pulse shape discrimination (PSD) based on the shape and the width of a pulse was applied to extract events, in which fast neutron hits at the specific depth of the single-crystal diamond. Unfolding of the measured spectrum for extracted pulses could deduce the neutron energy spectrum. Experiments using monoenergetic neutron sources demonstrated the reliable capability of this method to evaluate the neutron energy spectrum quantitatively.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-8"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-23DOI: 10.1109/TIM.2024.3485460
ZhenZhou Wang
The visual sensing system is one of the most important parts of the welding robots to realize intelligent and autonomous welding. The active visual sensing methods have been widely adopted in robotic welding because of their higher accuracies compared to the passive visual sensing methods. In this article, a comprehensive review of the active visual sensing methods for robotic welding is given. According to their uses, the state-of-the-art active visual sensing methods are divided into four categories: seam tracking, weld bead defect detection, 3-D weld pool geometry measurement, and welding path planning. First, the principles of these active visual sensing methods are reviewed. Then, a tutorial on the 3-D calibration methods for the active visual sensing systems used in intelligent welding robots is given to fill the gaps in the related fields. At last, the reviewed active visual sensing methods are compared and the prospects are given based on their advantages and disadvantages.
{"title":"The Active Visual Sensing Methods for Robotic Welding: Review, Tutorial, and Prospect","authors":"ZhenZhou Wang","doi":"10.1109/TIM.2024.3485460","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485460","url":null,"abstract":"The visual sensing system is one of the most important parts of the welding robots to realize intelligent and autonomous welding. The active visual sensing methods have been widely adopted in robotic welding because of their higher accuracies compared to the passive visual sensing methods. In this article, a comprehensive review of the active visual sensing methods for robotic welding is given. According to their uses, the state-of-the-art active visual sensing methods are divided into four categories: seam tracking, weld bead defect detection, 3-D weld pool geometry measurement, and welding path planning. First, the principles of these active visual sensing methods are reviewed. Then, a tutorial on the 3-D calibration methods for the active visual sensing systems used in intelligent welding robots is given to fill the gaps in the related fields. At last, the reviewed active visual sensing methods are compared and the prospects are given based on their advantages and disadvantages.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-19"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-23DOI: 10.1109/TIM.2024.3485439
Huabin Wang;Dongxu Shang;Zhe Jin;Fei Liu
Alzheimer’s disease (AD) is a degenerative disorder that encompasses multiple stages during its onset. There are certain shared characteristics among patients at various stages of AD, which results in the presence of incorrect edges in the graph structure constructed using graph convolutional network (GCN) for AD diagnosis. Due to the presence of incorrect edges, a singular graph structure faces challenges in accurately capturing the relationships between nodes. To tackle such a problem, this article proposes a screening strategy that constructs a large number of graphs, and selects an optimal graph combination. For each graph, the model adaptively aggregates lesion area features of similar nodes. Such a graph-selecting strategy alleviates the impact of incorrect edges and yields better performance. First, a multiscale composition module is designed to find the potential relationship between nodes, and the graph structure at different scales is constructed by extracting the significant pathogenic features from the node features. Second, a multihop node aggregation (MHNA) algorithm is proposed to find the correlation between multihop nodes in the same category, and highly correlated multihop nodes are found by traversing the features of different hop nodes. Third, an optimal multigraph combination screening strategy is proposed to select the optimal multihop graph combinations under the optimal multiscale combinations, and further adaptive fusion by using the multigraph attention mechanism. This enables the whole model to capture the distinctive features of AD while enhancing aggregation among similar nodes. The proposed model achieves an average accuracy of 90.21% and 94.10% on the NACC and Tadpole datasets, respectively, surpassing state-of-the-art results.
阿尔茨海默病（AD）是一种退行性疾病，发病过程包含多个阶段。处于不同阶段的阿尔茨海默病患者具有某些共同特征，这导致在使用图卷积网络（GCN）构建的用于诊断阿尔茨海默病的图结构中存在不正确的边。由于存在错误的边，奇异图结构在准确捕捉节点之间的关系方面面临挑战。为解决这一问题，本文提出了一种筛选策略，即构建大量图，并选择最佳图组合。对于每个图，该模型会自适应地汇总相似节点的病变区域特征。这种图选择策略可减轻错误边缘的影响，并产生更好的性能。首先，设计了一个多尺度组成模块，以发现节点之间的潜在关系，并通过从节点特征中提取重要的致病特征来构建不同尺度的图结构。其次，提出了多跳节点聚合（MHNA）算法，通过遍历不同跳节点的特征，找到同类多跳节点之间的相关性，从而找到高度相关的多跳节点。第三，提出最优多图组合筛选策略，在最优多尺度组合下选择最优多跳图组合，并利用多图关注机制进一步自适应融合。这使得整个模型能够捕捉到 AD 的显著特征，同时加强相似节点之间的聚合。所提出的模型在 NACC 和 Tadpole 数据集上的平均准确率分别达到了 90.21% 和 94.10%，超过了最先进的结果。
{"title":"A Multigraph Combination Screening Strategy Enabled Graph Convolutional Network for Alzheimer’s Disease Diagnosis","authors":"Huabin Wang;Dongxu Shang;Zhe Jin;Fei Liu","doi":"10.1109/TIM.2024.3485439","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485439","url":null,"abstract":"Alzheimer’s disease (AD) is a degenerative disorder that encompasses multiple stages during its onset. There are certain shared characteristics among patients at various stages of AD, which results in the presence of incorrect edges in the graph structure constructed using graph convolutional network (GCN) for AD diagnosis. Due to the presence of incorrect edges, a singular graph structure faces challenges in accurately capturing the relationships between nodes. To tackle such a problem, this article proposes a screening strategy that constructs a large number of graphs, and selects an optimal graph combination. For each graph, the model adaptively aggregates lesion area features of similar nodes. Such a graph-selecting strategy alleviates the impact of incorrect edges and yields better performance. First, a multiscale composition module is designed to find the potential relationship between nodes, and the graph structure at different scales is constructed by extracting the significant pathogenic features from the node features. Second, a multihop node aggregation (MHNA) algorithm is proposed to find the correlation between multihop nodes in the same category, and highly correlated multihop nodes are found by traversing the features of different hop nodes. Third, an optimal multigraph combination screening strategy is proposed to select the optimal multihop graph combinations under the optimal multiscale combinations, and further adaptive fusion by using the multigraph attention mechanism. This enables the whole model to capture the distinctive features of AD while enhancing aggregation among similar nodes. The proposed model achieves an average accuracy of 90.21% and 94.10% on the NACC and Tadpole datasets, respectively, surpassing state-of-the-art results.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-19"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-23DOI: 10.1109/TIM.2024.3485428
Xiao Zhu;Waqar Ahmed;Kamila Schmidt;Raíssa Barroso;Stephen J. Fowler;Christopher F. Blanford
Gas chromatography (GC) is a standard method to quantify volatile organic compounds (VOCs). However, this technique has high capital costs and is not suitable for real-time monitoring. Commercial metal oxide (MOX) sensors, on the other hand, are compact, cost-effective, and capable of providing real-time data to inform process control. This work used $alpha $ -pinene in dry argon as a model system to compare the VOC detection performance of Bosch Sensortec’s BME680 sensor against the same VOC analyzed by thermal desorption-GC–mass spectrometry (TD-GC-MS) after adsorption onto a polymeric sorbent. Electronic sensor measurements were conducted in temperature- and atmosphere-controlled environments to minimize confounding effects on the resistance response. The BME680 electronic sensors showed limits of detection (LODs) ranging from 20 to 39 parts per billion (ppb), with a linear range above 40 ppb. The GC-MS in multiple reaction monitoring (MRM) mode exhibited an LOD at ( $0.61~pm ~0.33$ ) ppb and a linear range from 1 to 100 ppb, equivalent to an adsorption volume of 2- $mu $ L VOC gas samples at concentrations of 1–100 ppb of $alpha $ -pinene in the gas control system. The overlapping calibration region ranges for these two methods spanned from 40 to 100 ppb. There was >30% sensor-to-sensor variability in the response from the MOX sensing components that were reduced to 5%–7% using a two-point calibration method.
{"title":"Validation of an Electronic VOC Sensor Against Gas Chromatography–Mass Spectrometry","authors":"Xiao Zhu;Waqar Ahmed;Kamila Schmidt;Raíssa Barroso;Stephen J. Fowler;Christopher F. Blanford","doi":"10.1109/TIM.2024.3485428","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485428","url":null,"abstract":"Gas chromatography (GC) is a standard method to quantify volatile organic compounds (VOCs). However, this technique has high capital costs and is not suitable for real-time monitoring. Commercial metal oxide (MOX) sensors, on the other hand, are compact, cost-effective, and capable of providing real-time data to inform process control. This work used \u0000<inline-formula> <tex-math>$alpha $ </tex-math></inline-formula>\u0000-pinene in dry argon as a model system to compare the VOC detection performance of Bosch Sensortec’s BME680 sensor against the same VOC analyzed by thermal desorption-GC–mass spectrometry (TD-GC-MS) after adsorption onto a polymeric sorbent. Electronic sensor measurements were conducted in temperature- and atmosphere-controlled environments to minimize confounding effects on the resistance response. The BME680 electronic sensors showed limits of detection (LODs) ranging from 20 to 39 parts per billion (ppb), with a linear range above 40 ppb. The GC-MS in multiple reaction monitoring (MRM) mode exhibited an LOD at (\u0000<inline-formula> <tex-math>$0.61~pm ~0.33$ </tex-math></inline-formula>\u0000) ppb and a linear range from 1 to 100 ppb, equivalent to an adsorption volume of 2-\u0000<inline-formula> <tex-math>$mu $ </tex-math></inline-formula>\u0000L VOC gas samples at concentrations of 1–100 ppb of \u0000<inline-formula> <tex-math>$alpha $ </tex-math></inline-formula>\u0000-pinene in the gas control system. The overlapping calibration region ranges for these two methods spanned from 40 to 100 ppb. There was >30% sensor-to-sensor variability in the response from the MOX sensing components that were reduced to 5%–7% using a two-point calibration method.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-8"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Transceivers are critical components of phased array radar (PAR) systems, and accurate fault diagnosis is essential for ensuring their reliability. However, many transceiver faults exhibit similar characteristics, making them difficult to identify. To address this challenge, a two-stage fault diagnosis method employing both rough and fine classifiers is proposed for PAR transceivers. In the first stage, a weighted support vector machine serves as the rough classifier to effectively separate easily distinguishable faults. For more complex faults that remain ambiguous, Fisher’s discriminating ratio is used to identify the most significant monitoring variables, refining the analysis further. In the second stage, a sparse momentum deep belief network (DBN) is developed as the fine classifier to accurately identify these challenging faults. The configuration parameters for both classifiers are optimized using a modified equilibrium optimizer to maximize performance. The proposed method is validated using a real-world dataset of PAR transceivers, with test results demonstrating superior accuracy compared to several existing intelligent diagnostic methods.
收发器是相控阵雷达（PAR）系统的关键部件，准确的故障诊断对确保其可靠性至关重要。然而，许多收发器故障具有相似的特征，因此难以识别。为了应对这一挑战，我们提出了一种针对 PAR 收发器的两阶段故障诊断方法，同时采用粗分类器和精分类器。在第一阶段，加权支持向量机作为粗略分类器，可有效区分易于区分的故障。对于仍不明确的较复杂故障，则使用费雪判别率来识别最重要的监测变量，进一步细化分析。在第二阶段，开发了稀疏动量深度信念网络（DBN）作为精细分类器，以准确识别这些具有挑战性的故障。两个分类器的配置参数都使用改进的平衡优化器进行优化，以最大限度地提高性能。使用 PAR 收发器的真实数据集对所提出的方法进行了验证，测试结果表明，与现有的几种智能诊断方法相比，该方法具有更高的准确性。
{"title":"A Two-Stage Fault Diagnosis Method With Rough and Fine Classifiers for Phased Array Radar Transceivers","authors":"Chuang Chen;Jiantao Shi;Lihang Feng;Hui Yi;Cunsong Wang;Hongtian Chen","doi":"10.1109/TIM.2024.3485396","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485396","url":null,"abstract":"Transceivers are critical components of phased array radar (PAR) systems, and accurate fault diagnosis is essential for ensuring their reliability. However, many transceiver faults exhibit similar characteristics, making them difficult to identify. To address this challenge, a two-stage fault diagnosis method employing both rough and fine classifiers is proposed for PAR transceivers. In the first stage, a weighted support vector machine serves as the rough classifier to effectively separate easily distinguishable faults. For more complex faults that remain ambiguous, Fisher’s discriminating ratio is used to identify the most significant monitoring variables, refining the analysis further. In the second stage, a sparse momentum deep belief network (DBN) is developed as the fine classifier to accurately identify these challenging faults. The configuration parameters for both classifiers are optimized using a modified equilibrium optimizer to maximize performance. The proposed method is validated using a real-world dataset of PAR transceivers, with test results demonstrating superior accuracy compared to several existing intelligent diagnostic methods.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-14"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-23DOI: 10.1109/TIM.2024.3485457
Yonghua Li;Chenghuai Mo;Jiaxing Li;Pengfei Yang;Jing Wang;Hongyi Yu;Sheng Hu;Puming Zhang;Xun Liu
The temperature rise effect caused by a time-varying magnetic field in an MRI scanner on active implantable medical devices (AIMDs) is related to the safety of patients. A reasonable experimental design is an important step to objectively evaluate the temperature rise of the equipment. To clarify the influence of key parameters of the temperature rise experiment on the results, this work theoretically modeled the physical mechanism of the temperature increase and studied the temperature increase of the device by experiments under different initial system temperatures, gel thicknesses, and magnetic field waveforms. The results show that the initial temperature has no effect on the temperature increase of the device. A thicker gel thickness corresponds to a smaller temperature increase. Under identical effective magnetic field switching rates, the sine wave magnetic field has a significantly stronger temperature rise effect than the triangular wave magnetic field. In addition, the point where the device has the largest temperature increase is located near the battery. This result indicates that the influence of these factors on temperature increase must be thoroughly considered during all phases of the device’s design, development, testing, and evaluation.
{"title":"Temperature Rise Mechanism of Pacemaker Induced by a Time-Varying Gradient Magnetic Field","authors":"Yonghua Li;Chenghuai Mo;Jiaxing Li;Pengfei Yang;Jing Wang;Hongyi Yu;Sheng Hu;Puming Zhang;Xun Liu","doi":"10.1109/TIM.2024.3485457","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485457","url":null,"abstract":"The temperature rise effect caused by a time-varying magnetic field in an MRI scanner on active implantable medical devices (AIMDs) is related to the safety of patients. A reasonable experimental design is an important step to objectively evaluate the temperature rise of the equipment. To clarify the influence of key parameters of the temperature rise experiment on the results, this work theoretically modeled the physical mechanism of the temperature increase and studied the temperature increase of the device by experiments under different initial system temperatures, gel thicknesses, and magnetic field waveforms. The results show that the initial temperature has no effect on the temperature increase of the device. A thicker gel thickness corresponds to a smaller temperature increase. Under identical effective magnetic field switching rates, the sine wave magnetic field has a significantly stronger temperature rise effect than the triangular wave magnetic field. In addition, the point where the device has the largest temperature increase is located near the battery. This result indicates that the influence of these factors on temperature increase must be thoroughly considered during all phases of the device’s design, development, testing, and evaluation.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-9"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10731952","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the widespread application of the virtual reality (VR) technique, omnidirectional image (OI) has attracted remarkable attention both from academia and industry. In contrast to a natural 2-D image, an OI contains $360^{circ } times 180^{circ }$ panoramic content, which presents great challenges for no-reference quality assessment. In this article, we propose a saliency-guided no-reference OI quality assessment (OIQA) method based on scene content understanding. Inspired by the fact that humans use hierarchical representations to grade images, we extract multiscale features from each projected viewport. Then, we integrate the texture removal and background detection techniques to obtain the corresponding saliency map of each viewport, which is subsequently utilized to guide the multiscale feature fusion from the low-level feature to the high-level one. Furthermore, motivated by the human way of understanding content, we leverage a self-attention-based Transformer to build nonlocal mutual dependencies to perceive the variations of distortion and scene in each viewport. Moreover, we also propose a content perception hypernetwork to adaptively return weights and biases for quality regressor, which is conducive to understanding the scene content and learning the perception rule for the quality assessment procedure. Comprehensive experiments validate that the proposed method can achieve competitive performances on two available databases. The code is publicly available at https://github.com/ldyorchid/SCP-OIQA .
{"title":"Saliency-Guided No-Reference Omnidirectional Image Quality Assessment via Scene Content Perceiving","authors":"Youzhi Zhang;Lifei Wan;Deyang Liu;Xiaofei Zhou;Ping An;Caifeng Shan","doi":"10.1109/TIM.2024.3485447","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485447","url":null,"abstract":"Due to the widespread application of the virtual reality (VR) technique, omnidirectional image (OI) has attracted remarkable attention both from academia and industry. In contrast to a natural 2-D image, an OI contains \u0000<inline-formula> <tex-math>$360^{circ } times 180^{circ }$ </tex-math></inline-formula>\u0000 panoramic content, which presents great challenges for no-reference quality assessment. In this article, we propose a saliency-guided no-reference OI quality assessment (OIQA) method based on scene content understanding. Inspired by the fact that humans use hierarchical representations to grade images, we extract multiscale features from each projected viewport. Then, we integrate the texture removal and background detection techniques to obtain the corresponding saliency map of each viewport, which is subsequently utilized to guide the multiscale feature fusion from the low-level feature to the high-level one. Furthermore, motivated by the human way of understanding content, we leverage a self-attention-based Transformer to build nonlocal mutual dependencies to perceive the variations of distortion and scene in each viewport. Moreover, we also propose a content perception hypernetwork to adaptively return weights and biases for quality regressor, which is conducive to understanding the scene content and learning the perception rule for the quality assessment procedure. Comprehensive experiments validate that the proposed method can achieve competitive performances on two available databases. The code is publicly available at \u0000<uri>https://github.com/ldyorchid/SCP-OIQA</uri>\u0000.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-15"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Device-free passive indoor human tracking based on radio frequency (RF) signals has prompted extensive research in academia and industry. Most existing approaches track a single target due to the coarse-grained spatial resolution. Multiperson tracking methods face challenges in complex and dynamic scenes, leading to a sharp decline in accuracy and an exponential increase in computation. In this article, we employ the impulse radio ultrawideband (IR-UWB), known for its high spatial resolution and range accuracy, to break down these limitations. We design, implement, and evaluate UWTrack, a clustering-assisted device-free tracking system that can achieve the trajectories of multiple persons in real time with two key components. First, a multiperson detection scheme with the adaptive motion filter and the range compensation is devised, which significantly improves the ranging accuracy and reduces false detections. Second, we propose a clustering-based multiperson tracking method to remove noise points and decline extra updating operations in the Gaussian mixture probability hypothesis density (GM-PHD) filter. It makes UWTrack enhance the real-time tracking performance and decrease the computational cost. We conduct experiments to evaluate UWTrack under various scenarios and conditions. The results reveal that UWTrack can achieve 35.3 cm average tracking accuracy and 90.25% detection accuracy in real time, outperforming the existing solutions by more than 36%.
{"title":"UWTrack: Clustering-Assisted Multiperson Passive Indoor Tracking via IR-UWB","authors":"Kuiyuan Zhang;Shouwan Gao;Junpeng Lv;Tao Lin;Pengpeng Chen","doi":"10.1109/TIM.2024.3485432","DOIUrl":"https://doi.org/10.1109/TIM.2024.3485432","url":null,"abstract":"Device-free passive indoor human tracking based on radio frequency (RF) signals has prompted extensive research in academia and industry. Most existing approaches track a single target due to the coarse-grained spatial resolution. Multiperson tracking methods face challenges in complex and dynamic scenes, leading to a sharp decline in accuracy and an exponential increase in computation. In this article, we employ the impulse radio ultrawideband (IR-UWB), known for its high spatial resolution and range accuracy, to break down these limitations. We design, implement, and evaluate UWTrack, a clustering-assisted device-free tracking system that can achieve the trajectories of multiple persons in real time with two key components. First, a multiperson detection scheme with the adaptive motion filter and the range compensation is devised, which significantly improves the ranging accuracy and reduces false detections. Second, we propose a clustering-based multiperson tracking method to remove noise points and decline extra updating operations in the Gaussian mixture probability hypothesis density (GM-PHD) filter. It makes UWTrack enhance the real-time tracking performance and decrease the computational cost. We conduct experiments to evaluate UWTrack under various scenarios and conditions. The results reveal that UWTrack can achieve 35.3 cm average tracking accuracy and 90.25% detection accuracy in real time, outperforming the existing solutions by more than 36%.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"73 ","pages":"1-14"},"PeriodicalIF":5.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","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：