Pub Date : 2025-10-06DOI: 10.1109/JSEN.2025.3615981
Shijian Dong;Tianyu Yu;Lixin Han;Jianguo Dong
To accurately predict the output of complex systems with input noise, a deep Informer network is innovatively designed, which combines signal decoupled denoising and interpretable functions. ELasticNet is employed for fitting evaluation and principal component feature selection. The dynamic variational mode decomposition (VMD) technique is established to decompose the input sequence. The high-frequency signal with a certain weight is combined with the low-frequency signal to realize decoupling reconstruction and weaken noise. The sliding window strategy is constructed to regularly decompose and update the newly obtained data online, so as to overcome the information leakage problem. Informer is applied to reasonably divide and reconstruct the principal component feature sequence. Encoder and decoder are used to realize feature capture under the embedding framework. In the encoder layer, the correlation of sequence signals is extracted and activated by multihead ProbSparse attention and wavelet activation function, respectively. The feedforward neural network (FNN) is utilized to map the extracted features by combining with the intermediate output of decoder. The combined results are analyzed globally using multihead attention. In the decoder layer, the masked attention and 1-D convolution are combined to decode features, and the fully connected layer is utilized to obtain the prediction output. The integrated gradient (IG) is applied to analyze the global and local interpretability of the prediction results to reveal the differential preferences of the proposed models in capturing key features. Finally, the accuracy and applicability of the proposed network are verified in complex industrial systems by comparing with the existing networks.
{"title":"Informer Network Fusing Interpretability and Dynamic Frequency Denoising Without Information Leakage for Predicting Complex Systems","authors":"Shijian Dong;Tianyu Yu;Lixin Han;Jianguo Dong","doi":"10.1109/JSEN.2025.3615981","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3615981","url":null,"abstract":"To accurately predict the output of complex systems with input noise, a deep Informer network is innovatively designed, which combines signal decoupled denoising and interpretable functions. ELasticNet is employed for fitting evaluation and principal component feature selection. The dynamic variational mode decomposition (VMD) technique is established to decompose the input sequence. The high-frequency signal with a certain weight is combined with the low-frequency signal to realize decoupling reconstruction and weaken noise. The sliding window strategy is constructed to regularly decompose and update the newly obtained data online, so as to overcome the information leakage problem. Informer is applied to reasonably divide and reconstruct the principal component feature sequence. Encoder and decoder are used to realize feature capture under the embedding framework. In the encoder layer, the correlation of sequence signals is extracted and activated by multihead ProbSparse attention and wavelet activation function, respectively. The feedforward neural network (FNN) is utilized to map the extracted features by combining with the intermediate output of decoder. The combined results are analyzed globally using multihead attention. In the decoder layer, the masked attention and 1-D convolution are combined to decode features, and the fully connected layer is utilized to obtain the prediction output. The integrated gradient (IG) is applied to analyze the global and local interpretability of the prediction results to reveal the differential preferences of the proposed models in capturing key features. Finally, the accuracy and applicability of the proposed network are verified in complex industrial systems by comparing with the existing networks.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 22","pages":"42372-42388"},"PeriodicalIF":4.3,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145500458","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 : 2025-10-06DOI: 10.1109/JSEN.2025.3615736
Yan-Lin He;Ze-Hao Bai;Yuan Xu;Qun-Xiong Zhu;Longchuan Li
The accurate detection of key quality variables plays a crucial role in process optimization and operational decision-making. As a result, real-time prediction of these variables is essential for effective monitoring and control in industrial processes. However, as sequence length and complexity increase, achieving accurate real-time predictions becomes more challenging. To address these challenges, this article proposes a novel time series prediction framework—patch decomposition enhanced temporal convolutional network with transformer (PETC-TNet), which combines a patch-based enhanced temporal convolutional network (TCN) with a Transformer architecture. PETC-TNet introduces a time-window block strategy that decomposes long sequences into manageable patches, preserving critical details. A channel attention mechanism is integrated into the TCN, forming the temporal convolutional channel attention network (TCCAN), which enhances feature extraction and improves the modeling of spatiotemporal relationships. The outputs from TCCAN are then processed by a Transformer module to effectively capture and attend to information across different historical time windows, overcoming the limitations of traditional Transformers with long sequences. Experiments on industrial datasets show that PETC-TNet surpasses Transformer-based and other state-of-the-art approaches in prediction accuracy, achieving notably lower mean absolute error (MAE). Additionally, sensitivity analysis reveals that PETC-TNet maintains reasonable sensitivity to sequence length and patch size, providing valuable insights for industrial soft sensor modeling.
{"title":"Patch-Decomposition-Enhanced TCN With Transformer for Soft Sensor Modeling","authors":"Yan-Lin He;Ze-Hao Bai;Yuan Xu;Qun-Xiong Zhu;Longchuan Li","doi":"10.1109/JSEN.2025.3615736","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3615736","url":null,"abstract":"The accurate detection of key quality variables plays a crucial role in process optimization and operational decision-making. As a result, real-time prediction of these variables is essential for effective monitoring and control in industrial processes. However, as sequence length and complexity increase, achieving accurate real-time predictions becomes more challenging. To address these challenges, this article proposes a novel time series prediction framework—patch decomposition enhanced temporal convolutional network with transformer (PETC-TNet), which combines a patch-based enhanced temporal convolutional network (TCN) with a Transformer architecture. PETC-TNet introduces a time-window block strategy that decomposes long sequences into manageable patches, preserving critical details. A channel attention mechanism is integrated into the TCN, forming the temporal convolutional channel attention network (TCCAN), which enhances feature extraction and improves the modeling of spatiotemporal relationships. The outputs from TCCAN are then processed by a Transformer module to effectively capture and attend to information across different historical time windows, overcoming the limitations of traditional Transformers with long sequences. Experiments on industrial datasets show that PETC-TNet surpasses Transformer-based and other state-of-the-art approaches in prediction accuracy, achieving notably lower mean absolute error (MAE). Additionally, sensitivity analysis reveals that PETC-TNet maintains reasonable sensitivity to sequence length and patch size, providing valuable insights for industrial soft sensor modeling.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 22","pages":"42364-42371"},"PeriodicalIF":4.3,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145500473","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 : 2025-10-06DOI: 10.1109/JSEN.2025.3613742
Ruiqin Zhao;Jinxia Li;Ting Shi;Haiyan Wang
Underwater acoustic sensor networks (UASNs) play a critical role in underwater communication and mission execution. However, their open nature and the dynamics of underwater acoustic channels (UACs) make them highly susceptible to spoofing attacks, posing severe security threats. Physical layer authentication (PLA) offers a promising defense by exploiting the unique characteristics of UACs, which are difficult to replicate. Nevertheless, most existing PLA schemes rely on static or statistical features that degrade significantly under time-varying ocean environments. To address this challenge, we propose a robust PLA (RPLA) scheme based on differential features designed for dynamic underwater channels. RPLA adopts a differential feature extraction method that compares each channel impulse response (CIR) with historical CIRs from the same link to quantify temporal variations. Five multidimensional differential features are extracted to capture fine-grained link variability and highlight distinctions between legitimate and adversarial links. These features are used to construct labeled training samples, which are then fed into an authentication model to enable robust and adaptive classification under time-varying underwater conditions. Extensive evaluations using both simulated and sea trial CIR datasets demonstrate that RPLA achieves high authentication accuracy and robust performance, significantly improving resistance to spoofing attacks. This work presents a practical and effective approach to enhancing physical layer security in dynamic underwater communication environments.
{"title":"Differential Feature-Based Physical Layer Authentication for Underwater Acoustic Sensor Networks","authors":"Ruiqin Zhao;Jinxia Li;Ting Shi;Haiyan Wang","doi":"10.1109/JSEN.2025.3613742","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3613742","url":null,"abstract":"Underwater acoustic sensor networks (UASNs) play a critical role in underwater communication and mission execution. However, their open nature and the dynamics of underwater acoustic channels (UACs) make them highly susceptible to spoofing attacks, posing severe security threats. Physical layer authentication (PLA) offers a promising defense by exploiting the unique characteristics of UACs, which are difficult to replicate. Nevertheless, most existing PLA schemes rely on static or statistical features that degrade significantly under time-varying ocean environments. To address this challenge, we propose a robust PLA (RPLA) scheme based on differential features designed for dynamic underwater channels. RPLA adopts a differential feature extraction method that compares each channel impulse response (CIR) with historical CIRs from the same link to quantify temporal variations. Five multidimensional differential features are extracted to capture fine-grained link variability and highlight distinctions between legitimate and adversarial links. These features are used to construct labeled training samples, which are then fed into an authentication model to enable robust and adaptive classification under time-varying underwater conditions. Extensive evaluations using both simulated and sea trial CIR datasets demonstrate that RPLA achieves high authentication accuracy and robust performance, significantly improving resistance to spoofing attacks. This work presents a practical and effective approach to enhancing physical layer security in dynamic underwater communication environments.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 21","pages":"40834-40848"},"PeriodicalIF":4.3,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455804","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 : 2025-10-02DOI: 10.1109/JSEN.2025.3614813
Jowa Yangchin;Ningrinla Marchang
This article proposes the enhanced utility and reverse auction (EURA) framework as an incentive mechanism for mobile crowdsensing. EURA integrates reverse auction principles with utility optimization, forming an innovative region-based strategy that enhances data sensing efficiency and coverage maximization. Through an adaptive bidding model, EURA ensures fair and strategic participant selection, maintaining optimal resource allocation across large-scale sensing networks. EURA optimizes participation by assigning efficiencies based on users’ regions, fostering localized engagement and fair competition across diverse sensing environments. This article introduces a greedy incentive mechanism called EURA with greedy auction incentive (EGAIN) that dynamically adjusts bid evaluations based on data quality and regional significance, optimizing both competition fairness and efficiency. Additionally, the coverage-aware auction strategy mitigates redundancy while fostering an equitable distribution of sensing responsibilities. A variant model is also proposed called EURA with reputation auction incentive (ERAIN), incorporating reputation-based bid evaluations to further refine selection criteria and strengthen incentive alignment. Performance evaluations demonstrate EURA’s superiority in maximizing utility by 20%–50%, boosting participation by 30%–50% compared to RADP-VPC, Random, and RADP_EWMA while effectively minimizing bid exploitation and enabling cost efficient regional sensing, establishing its clear advantage over these existing mechanisms.
{"title":"Region-Based Incentive Mechanisms for Utility Maximization in Mobile Crowd Sensing","authors":"Jowa Yangchin;Ningrinla Marchang","doi":"10.1109/JSEN.2025.3614813","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3614813","url":null,"abstract":"This article proposes the enhanced utility and reverse auction (EURA) framework as an incentive mechanism for mobile crowdsensing. EURA integrates reverse auction principles with utility optimization, forming an innovative region-based strategy that enhances data sensing efficiency and coverage maximization. Through an adaptive bidding model, EURA ensures fair and strategic participant selection, maintaining optimal resource allocation across large-scale sensing networks. EURA optimizes participation by assigning efficiencies based on users’ regions, fostering localized engagement and fair competition across diverse sensing environments. This article introduces a greedy incentive mechanism called EURA with greedy auction incentive (EGAIN) that dynamically adjusts bid evaluations based on data quality and regional significance, optimizing both competition fairness and efficiency. Additionally, the coverage-aware auction strategy mitigates redundancy while fostering an equitable distribution of sensing responsibilities. A variant model is also proposed called EURA with reputation auction incentive (ERAIN), incorporating reputation-based bid evaluations to further refine selection criteria and strengthen incentive alignment. Performance evaluations demonstrate EURA’s superiority in maximizing utility by 20%–50%, boosting participation by 30%–50% compared to RADP-VPC, Random, and RADP_EWMA while effectively minimizing bid exploitation and enabling cost efficient regional sensing, establishing its clear advantage over these existing mechanisms.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 21","pages":"40861-40868"},"PeriodicalIF":4.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145405238","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}
Non-contact blood pressure (BP) monitoring offers a comfortable and uninterrupted means of BP assessment, free from the constraints of physical contact. A core challenge in radar-based BP monitoring is the extraction of weak BP-related information from radar signals, which significantly affects both the accuracy and real-time performance of BP prediction models. To address this challenge, we focus on waveform features and temporal continuity, proposing a Temporal-Spatial Feature Fusion Network (TSFN) framework for radar-based BP prediction. The TSFN architecture integrates three components: Residual Networks (ResNet) for the extraction of detailed waveform features, gated recurrent units (GRUs) for capturing continuous temporal dependencies, and multiple head attention (MHA) to focus on critical information. To enhance the model’s robustness, a Pseudo–Huber loss function was employed to refine the optimization process, providing a smoother gradient transition and improved stability. Evaluations demonstrated impressive accuracies, with mean errors (MEs) of 0.24 ± 6.78 mmHg for systolic BP (SBP) and 0.25 ± 5.13 mmHg for diastolic BP (DBP). These outcomes meet the standards set by the British Hypertension Society (BHS) for grade “A” benchmarks for SBP and DBP measurements. Notably, the TSFN model avoids the need for complex feature engineering, demonstrating its effectiveness in monitoring BP fluctuations across diverse physiological states at 2 s intervals. This feature highlights its potential applicability in real-time monitoring systems. Furthermore, using our proposed TSFN framework, we have validated various combinations of temporal and spatial feature extraction networks. Our findings promise a significant advancement for continuous, non-contact BP monitoring with radar technology.
{"title":"A Temporal–Spatial Feature Fusion Network for Accurate Non-Contact Blood Pressure Measurement via Radar","authors":"Pengfei Wang;Hongqiu Zhang;Minghao Yang;Jianqi Wang;Cong Wang;Hongbo Jia","doi":"10.1109/JSEN.2025.3614579","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3614579","url":null,"abstract":"Non-contact blood pressure (BP) monitoring offers a comfortable and uninterrupted means of BP assessment, free from the constraints of physical contact. A core challenge in radar-based BP monitoring is the extraction of weak BP-related information from radar signals, which significantly affects both the accuracy and real-time performance of BP prediction models. To address this challenge, we focus on waveform features and temporal continuity, proposing a Temporal-Spatial Feature Fusion Network (TSFN) framework for radar-based BP prediction. The TSFN architecture integrates three components: Residual Networks (ResNet) for the extraction of detailed waveform features, gated recurrent units (GRUs) for capturing continuous temporal dependencies, and multiple head attention (MHA) to focus on critical information. To enhance the model’s robustness, a Pseudo–Huber loss function was employed to refine the optimization process, providing a smoother gradient transition and improved stability. Evaluations demonstrated impressive accuracies, with mean errors (MEs) of 0.24 ± 6.78 mmHg for systolic BP (SBP) and 0.25 ± 5.13 mmHg for diastolic BP (DBP). These outcomes meet the standards set by the British Hypertension Society (BHS) for grade “A” benchmarks for SBP and DBP measurements. Notably, the TSFN model avoids the need for complex feature engineering, demonstrating its effectiveness in monitoring BP fluctuations across diverse physiological states at 2 s intervals. This feature highlights its potential applicability in real-time monitoring systems. Furthermore, using our proposed TSFN framework, we have validated various combinations of temporal and spatial feature extraction networks. Our findings promise a significant advancement for continuous, non-contact BP monitoring with radar technology.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 21","pages":"40748-40762"},"PeriodicalIF":4.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455803","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 : 2025-10-02DOI: 10.1109/JSEN.2025.3614730
Ayhan Yazgan;Ufuk Koçbıyık
Abstract-This article focuses on the wireless monitoring of rubber lifter-bar wear, which has been used for years in mills to grind ore under harsh environmental conditions. Due to the abrasive nature of the process, worn lifter-bars must be replaced after a certain period to prevent damage to the mill body, which is extremely costly. Since predicting this wear in advance is challenging, replacements often occur at incorrect times, leading to financial losses in the mining industry. In addition, lifter-bars that are not fully worn are frequently discarded, resulting in unnecessary waste. In this study, two partially conductive resistive sensor probes (RSPs) were designed and embedded into the lifter-bar. The resistance between the RSP terminals becomes part of a proposed modified relaxation oscillator. Due to the applied electric field and the presence of carbon black within the lifter-bar, an electric current related to the degree of wear flows between the RSP terminals, causing the oscillator’s frequency to vary accordingly. A microprocessor-based electronic circuit was developed to convert this frequency into digital wear data. The sensor board contains a transceiver operating at 2.4 GHz with a receiver sensitivity better than -120 dBm. The sensor circuit and antenna are located in a safe area of the lifter-bar, away from the wear zone, for wireless wear monitoring. The proposed sensor was installed on a commercial lifter-bar in an operational grinding mill located in Bingöl, Türkiye. To verify its reliability, battery power planning was conducted based on the proposed data packet structure, and wear data were monitored over a 100 -day period. Despite the thick metallic structure of the mill and the presence of hundreds of rotating metal balls inside, the wireless sensor successfully transmitted signals at -104 dBm with a $2.8-mathrm{dB}$ signal-to-noise ratio (SNR) outside the mill, achieving a $6 %$ wear resolution. Simulations and experimental results showed strong agreement with the theoretical model.
{"title":"A Novel Wireless Wear Monitoring Sensor for Grinding Mill Lifter-Bars","authors":"Ayhan Yazgan;Ufuk Koçbıyık","doi":"10.1109/JSEN.2025.3614730","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3614730","url":null,"abstract":"Abstract-This article focuses on the wireless monitoring of rubber lifter-bar wear, which has been used for years in mills to grind ore under harsh environmental conditions. Due to the abrasive nature of the process, worn lifter-bars must be replaced after a certain period to prevent damage to the mill body, which is extremely costly. Since predicting this wear in advance is challenging, replacements often occur at incorrect times, leading to financial losses in the mining industry. In addition, lifter-bars that are not fully worn are frequently discarded, resulting in unnecessary waste. In this study, two partially conductive resistive sensor probes (RSPs) were designed and embedded into the lifter-bar. The resistance between the RSP terminals becomes part of a proposed modified relaxation oscillator. Due to the applied electric field and the presence of carbon black within the lifter-bar, an electric current related to the degree of wear flows between the RSP terminals, causing the oscillator’s frequency to vary accordingly. A microprocessor-based electronic circuit was developed to convert this frequency into digital wear data. The sensor board contains a transceiver operating at 2.4 GHz with a receiver sensitivity better than -120 dBm. The sensor circuit and antenna are located in a safe area of the lifter-bar, away from the wear zone, for wireless wear monitoring. The proposed sensor was installed on a commercial lifter-bar in an operational grinding mill located in Bingöl, Türkiye. To verify its reliability, battery power planning was conducted based on the proposed data packet structure, and wear data were monitored over a 100 -day period. Despite the thick metallic structure of the mill and the presence of hundreds of rotating metal balls inside, the wireless sensor successfully transmitted signals at -104 dBm with a <inline-formula> <tex-math>$2.8-mathrm{dB}$ </tex-math></inline-formula> signal-to-noise ratio (SNR) outside the mill, achieving a <inline-formula> <tex-math>$6 %$ </tex-math></inline-formula> wear resolution. Simulations and experimental results showed strong agreement with the theoretical model.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 21","pages":"40738-40747"},"PeriodicalIF":4.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455742","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 rotary axis is the basis of rotational motion. At present, error compensation is the main method to improve the motion accuracy of the rotary axis. The key to error compensation lies in the fast and accurate measurement of the geometric errors of rotary axis. The simultaneous measurement of themultidegree-of-freedom geometric errors and the establishment of the error compensation model are the main means to achieve fast and accurate measurement. Existing methods have problems such as complex error decoupling, the need for servo rotation system, and incomplete error compensation models. To address these issues, we proposed a new method for measuring the four-degree-offreedom geometric errors of the rotary axis based on a circular grating (CG). The significant advantage is its ability to perform full-circle, simultaneous, and continuous measurement without requiring a servo rotation system. Afterward, an error compensation model for the measurement system was established based on the theory of homogeneous coordinate transformation, and the effects of drift, installation, and crosstalk errors on the results were analyzed in detail. During this process, we utilized a fourth-order transformation matrix and developed the first homogeneous coordinate transformation matrix applicable to CGs. The model was used to compensate for the experimental results. The results showed that the radial error motions and tilt error motions are reduced by 87% at most after compensation, and repeatability values of the tilt error motions are reduced by 20% at most. The experimental results verified the effectiveness of the method and the model.
{"title":"Method and Compensation Model for Measuring Geometric Errors of Rotary Axis Based on Circular Grating","authors":"Jiakun Li;Shuai Han;Bintao Zhao;Qixin He;Kaifeng Hu;Yibin Qian;Qibo Feng","doi":"10.1109/JSEN.2025.3613795","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3613795","url":null,"abstract":"The rotary axis is the basis of rotational motion. At present, error compensation is the main method to improve the motion accuracy of the rotary axis. The key to error compensation lies in the fast and accurate measurement of the geometric errors of rotary axis. The simultaneous measurement of themultidegree-of-freedom geometric errors and the establishment of the error compensation model are the main means to achieve fast and accurate measurement. Existing methods have problems such as complex error decoupling, the need for servo rotation system, and incomplete error compensation models. To address these issues, we proposed a new method for measuring the four-degree-offreedom geometric errors of the rotary axis based on a circular grating (CG). The significant advantage is its ability to perform full-circle, simultaneous, and continuous measurement without requiring a servo rotation system. Afterward, an error compensation model for the measurement system was established based on the theory of homogeneous coordinate transformation, and the effects of drift, installation, and crosstalk errors on the results were analyzed in detail. During this process, we utilized a fourth-order transformation matrix and developed the first homogeneous coordinate transformation matrix applicable to CGs. The model was used to compensate for the experimental results. The results showed that the radial error motions and tilt error motions are reduced by 87% at most after compensation, and repeatability values of the tilt error motions are reduced by 20% at most. The experimental results verified the effectiveness of the method and the model.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 21","pages":"40727-40737"},"PeriodicalIF":4.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455945","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 : 2025-10-01Epub Date: 2025-08-28DOI: 10.1109/jsen.2025.3602006
Letian Ai, Saikat Sengupta, Yue Chen
In image-guided interventions, fiducial markers are widely used for medical instrument tracking by attaching them to designated positions. However, due to the difficulty of precise marker placement, obtaining an accurate marker-to-object transformation remains technically challenging, particularly with customized markers or those with non-standard geometries. To accurately identify the transformation, this study introduces a novel calibration method achieved by sequentially touching a fixed tip with landmarks on the object. An inverse sample consensus filter was proposed to remove potential measurement outliers and improve the robustness of the calibration result. Validation through simulations and experiments under two tracking modalities demonstrated superior translational accuracy and improved robustness compared to conventional methods. Specifically, the experiment conducted under electromagnetic tracking system demonstrated a translational error of 0.61 ± 0.11 mm and a rotational error of 0.97 ± 0.18°. The experiment using magnetic resonance imaging system demonstrated a translational error of 0.60 mm and a rotational error of 2.81°. A use case with an intracerebral hemorrhage evacuation robot further verified the feasibility of integrating the calibration method into the image-guided workflow. The proposed method achieved sub-millimeter calibration accuracy across different scenarios, demonstrating its effectiveness and strong potential for diverse research and clinical applications.
{"title":"Marker-to-Object Calibration Using Landmark Touch.","authors":"Letian Ai, Saikat Sengupta, Yue Chen","doi":"10.1109/jsen.2025.3602006","DOIUrl":"10.1109/jsen.2025.3602006","url":null,"abstract":"<p><p>In image-guided interventions, fiducial markers are widely used for medical instrument tracking by attaching them to designated positions. However, due to the difficulty of precise marker placement, obtaining an accurate marker-to-object transformation remains technically challenging, particularly with customized markers or those with non-standard geometries. To accurately identify the transformation, this study introduces a novel calibration method achieved by sequentially touching a fixed tip with landmarks on the object. An inverse sample consensus filter was proposed to remove potential measurement outliers and improve the robustness of the calibration result. Validation through simulations and experiments under two tracking modalities demonstrated superior translational accuracy and improved robustness compared to conventional methods. Specifically, the experiment conducted under electromagnetic tracking system demonstrated a translational error of 0.61 ± 0.11 mm and a rotational error of 0.97 ± 0.18°. The experiment using magnetic resonance imaging system demonstrated a translational error of 0.60 mm and a rotational error of 2.81°. A use case with an intracerebral hemorrhage evacuation robot further verified the feasibility of integrating the calibration method into the image-guided workflow. The proposed method achieved sub-millimeter calibration accuracy across different scenarios, demonstrating its effectiveness and strong potential for diverse research and clinical applications.</p>","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 19","pages":"36773-36784"},"PeriodicalIF":4.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12539640/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145342540","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 : 2025-10-01DOI: 10.1109/JSEN.2025.3613846
Yanhui Xi;Wenxin Zhu;Zhen Ding;Lanlan Liu
In autonomous driving and robotic navigation, the fusion of multimodal data from LiDAR and cameras relies on accurate extrinsic calibration. However, the calibration accuracy may drop when there is an external disturbance, such as sensor vibrations, temperature fluctuations, and aging. To address this problem, this article presents a novel LiDAR–camera joint calibration network based on cross-modal attention fusion (CMAF) and cross-domain feature extraction (CDFE). The CMAF module is constructed based on region-level matching and pixel-level interaction to improve the cross-modal feature alignment and fusion. To address the semantic inconsistency between encoder and decoder features, the CDFE is designed for a U-shaped architecture with multimodal skip connections to capture large-scale contextual correlations through the transformation from the spatial domain to the frequency domain, and it can maintain semantic consistency through the fusion of global features and original features (residual information) based on the dual-path architecture. Experiments on the KITTI odometry dataset and KITTI-360 dataset show that our network not only significantly outperforms mainstream methods and demonstrates strong generalization capabilities but also achieves high computational efficiency.
{"title":"A Novel LiDAR–Camera Joint Calibration Network Based on Cross-Modal Feature Fusion","authors":"Yanhui Xi;Wenxin Zhu;Zhen Ding;Lanlan Liu","doi":"10.1109/JSEN.2025.3613846","DOIUrl":"https://doi.org/10.1109/JSEN.2025.3613846","url":null,"abstract":"In autonomous driving and robotic navigation, the fusion of multimodal data from LiDAR and cameras relies on accurate extrinsic calibration. However, the calibration accuracy may drop when there is an external disturbance, such as sensor vibrations, temperature fluctuations, and aging. To address this problem, this article presents a novel LiDAR–camera joint calibration network based on cross-modal attention fusion (CMAF) and cross-domain feature extraction (CDFE). The CMAF module is constructed based on region-level matching and pixel-level interaction to improve the cross-modal feature alignment and fusion. To address the semantic inconsistency between encoder and decoder features, the CDFE is designed for a U-shaped architecture with multimodal skip connections to capture large-scale contextual correlations through the transformation from the spatial domain to the frequency domain, and it can maintain semantic consistency through the fusion of global features and original features (residual information) based on the dual-path architecture. Experiments on the KITTI odometry dataset and KITTI-360 dataset show that our network not only significantly outperforms mainstream methods and demonstrates strong generalization capabilities but also achieves high computational efficiency.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 21","pages":"40849-40860"},"PeriodicalIF":4.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145405229","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：