{"title":"A Noninvasive Framework for Heart Function Assessment by Multitask Learning","authors":"Haimiao Mo;Juan Liang;Bing Li;Zhijian Hu;Meng Yi;Hongjia Wu;Qian Rong;Zeyuan Xu","doi":"10.1109/TIM.2025.3553885","DOIUrl":"https://doi.org/10.1109/TIM.2025.3553885","url":null,"abstract":"Accurate assessment of cardiac function is vital for preventing and managing cardiovascular diseases (CVDs). Recent advancements in machine learning, especially convolutional neural networks (CNNs) and multitask learning (MTL), have improved the precision of echocardiogram evaluations. However, existing methods often overlook the intrinsic relationships among ejection fraction (EF), end-diastolic volume (EDV), and end-systolic volume (ESV), which are essential for accurate assessments. We propose a noninvasive framework for heart function assessment (FHFA) using MTL that utilizes a 3-D CNN to extract key spatiotemporal features from echocardiogram videos. By employing an MTL strategy and weight distribution mechanism, this framework enhances the accuracy of EF predictions and provides a comprehensive assessment of cardiac structure and function. This approach ensures that the model effectively integrates auxiliary task information while focusing on the primary task, resulting in a more precise analysis of cardiac function. The experimental results on the Echonet-Dynamic dataset demonstrate that our method achieves an average absolute error of 3.89, a root-mean-square error (RMSE) of 5.13, and an <inline-formula> <tex-math>$R^{2}$ </tex-math></inline-formula> value of 0.82, outperforming existing methods. Future work will focus on automatic weight optimization, model compression, and improving computational efficiency for broader clinical applications.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769485","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}
Bo Qi;Kehan Zhu;Chunyi Wang;Meng Huang;Shupeng Yang;Chengrong Li
{"title":"An Oil Flow Velocity In Situ Sensor for Power Transformers Based on Laser Doppler Effect","authors":"Bo Qi;Kehan Zhu;Chunyi Wang;Meng Huang;Shupeng Yang;Chengrong Li","doi":"10.1109/TIM.2025.3551565","DOIUrl":"https://doi.org/10.1109/TIM.2025.3551565","url":null,"abstract":"The assessment of the power transformers health status has garnered significant attention. The oil flow velocity serves as a critical parameter for assessing the severity of internal faults in oil-immersed power transformers, and its effective monitoring can accurately reflect the operational state of power transformers. The operational principle of the existing transformer heavy gas protection involves measuring the oil flow velocity during transformer faults through a mechanical device positioned at a specific pipeline location. However, this approach presents several challenges, including prolonged response times, a narrow monitoring range, and low measurement accuracy. To address these challenges, a fast-response, wide-range, high-accuracy, and long-lifespan in situ oil flow velocity sensor was designed and developed, drawing inspiration from the existing sensing technologies based on the laser Doppler effect and tailored to the operational environment of transformers. Test results for the key parameters of the sensor demonstrated that a measurement range of 0–3 m/s was achieved, with a maximum measurement error of 3.6%. Furthermore, the sensor is capable of operating for over 15 years in the complex operational environment of power transformers. Finally, application tests were conducted on a real scale 110-kV transformer, yielding a maximum measurement error of only 3%, with the flow velocity being accurately measurable under various conditions. The developed sensor offers a novel technical approach for the digital sensing of transformer oil velocity.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-8"},"PeriodicalIF":5.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748750","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}
{"title":"A Novel Accuracy-Constrained Scheme for Efficient Trend Extraction of Industrial Time-Series Data","authors":"Ju Liu;Jiayi Zhao;Hao Ye;Dexian Huang;Chao Shang","doi":"10.1109/TIM.2025.3554295","DOIUrl":"https://doi.org/10.1109/TIM.2025.3554295","url":null,"abstract":"Data trend extraction provides a useful means to qualitatively capture the underlying variations of time-series data. A class of algorithms is built upon segmentation and piecewise polynomial fitting, where the model complexity is primarily controlled by the number of data segments. However, it is not trivial to specify when tackling datasets of different sizes, and expensive computations are required in current global optimization algorithms. To address these issues, we propose a novel data trend extraction and segmentation method based on accuracy-constrained polynomial fitting. Two normalized indices are coined to define constraints on the accuracy of piecewise polynomial fitting, which allows for an interpretable and clear tuning guideline to regulate model complexities of segmentation when facing data trajectories of different lengths. By exploiting the structure of the constrained fitting problem, a breadth-first search (BFS) algorithm is established, with two branch pruning (BP) strategies designed to remarkably improve the solution efficiency. In particular, we prove that the proposed solution algorithm has a desirable <inline-formula> <tex-math>$mathcal {O}(n^{2})$ </tex-math></inline-formula> complexity that does not grow with the number of segments and is much lower than that of generic global optimization algorithms. Comprehensive case studies show that compared with conventional methods, our approach enjoys better empirical performance, easier tuning of parameters, and lower computational cost.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769484","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}
Peng Tang;Guodong Sa;Junkai Ge;Zhenyu Liu;Jianrong Tan
{"title":"Projection Pattern Precorrection Method Based on Projection Error Decoupling in Fringe Projection Profilometry","authors":"Peng Tang;Guodong Sa;Junkai Ge;Zhenyu Liu;Jianrong Tan","doi":"10.1109/TIM.2025.3553566","DOIUrl":"https://doi.org/10.1109/TIM.2025.3553566","url":null,"abstract":"The quality of sinusoidal fringe projection is one of the most critical factors affecting the accuracy of fringe projection profilometry (FPP). Existing projection error correction methods, however, fail to address the simultaneous occurrence and mutual influence of geometric distortion and grayscale inconsistency in the actual projected pattern. In order to tackle this issue, this article proposes a projection pattern precorrection method based on projection error decoupling. By using multiangle expanded Gray code (MEGC), this method decouples the projection error correction process into two independent correction processes. Specifically, for the projection distortion error, a per-pixel distortion error calibration method is introduced. This method improves the accuracy of phase coordinate calculation by designing an encoding method for multiangle floating-point coordinates and a decoding method for weighted fusion of multi coordinate values. It compensates for the distortion error pixel by pixel using a nonparametric form. A subregional nonlinear error calibration method is, furthermore, proposed to enhance the sinusoidal quality of the projected fringes and ensure grayscale consistency. Finally, the precorrected pattern is generated based on the two error calibration results which ensures distortion-free and brightness-accurate fringe pattern. Experimental results with various 3-D objects demonstrated that our proposed method, achieves higher and more stable measurement accuracy (average 0.0327 mm versus 0.0184 mm), compared with traditional precorrection methods that address projection errors separately.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-16"},"PeriodicalIF":5.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769490","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}
Kaiwen Dong;Yu Zhou;Kévin Riou;Xiao Yun;Yanjing Sun;Kévin Subrin;Patrick Le Callet
{"title":"Spatial–Temporal–Geometric Graph Convolutional Network for 3-D Human Pose Estimation From Multiview Video","authors":"Kaiwen Dong;Yu Zhou;Kévin Riou;Xiao Yun;Yanjing Sun;Kévin Subrin;Patrick Le Callet","doi":"10.1109/TIM.2025.3551025","DOIUrl":"https://doi.org/10.1109/TIM.2025.3551025","url":null,"abstract":"The multiview 3-D human pose estimation (HPE) effectively addresses challenges, such as depth ambiguity and occlusion faced by monocular methods through the complementing of geometric information from multiple views. However, existing multiview methods often necessitate well-calibrated camera parameters or rely on complex parametric models. These requirements can result in inaccuracies when camera placement is perturbed and can negatively impact the deployability. This article proposes a lightweight approach that synergistically models geometric information with spatial-temporal information without relying on camera parameters, named spatial-temporal–geometric graph convolutional network (STG-GCN). We leverage the inherent connections in multiview sequences of 2-D poses, representing them as a spatial-temporal–geometric graph (STG-Graph), which allows for the simultaneous encoding of spatial-temporal–geometric relations across various joints, consecutive frames, and multiple views. Using a unified graph to model all features, this approach reduces the parameter explosion in existing methods, caused by separate modules extracting spatial, temporal, and view axis features. Building upon the STG-Graph, an adaptive confidence-aware graph convolution (ACA-GraphConv) is proposed to mitigate the impact of unreliable 2-D poses predicted by 2-D pose estimators. This is achieved by leveraging corresponding confidence scores to adjust the graph convolution accordingly. Experimental results on two public datasets demonstrate that our STG-GCN achieves performance comparable to state-of-the-art approaches while significantly reducing parameter volume. Ablation studies also illustrate the effectiveness of our ACA-GraphConv in both monocular and multiview scenarios.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-13"},"PeriodicalIF":5.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726388","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}
{"title":"Contactless Wideband Current Measurement Based on Tunneling Magnetoresistance Sensor Array for Rectangular Busbar Systems","authors":"Qi Zhu;Guangchao Geng;Quanyuan Jiang","doi":"10.1109/TIM.2025.3551027","DOIUrl":"https://doi.org/10.1109/TIM.2025.3551027","url":null,"abstract":"Current measurements based on magnetic field sensor arrays have attracted a lot of attention due to their convenience in installation and maintenance. However, conventional current transducers of rectangular busbars are primarily designed for the dc and 50-Hz currents. Numerous industrial applications in power systems require novel technologies of ac current transducers with broader frequency ranges. Some research has achieved accurate measurement for high-frequency ac currents but often relies heavily on the known relative positions of the busbars and sensors. Thus, this article proposes a wideband current measurement method without prior knowledge of precise busbar and sensor positions, which consists of two steps. The first step is using the sensed magnetic field at the fundamental frequency to localize busbar positions, which assist in revealing the regularity of magnetic field variation with frequency. The second step is to reconstruct the currents at harmonic frequencies using the sensed magnetic field at different frequencies and busbar positions. The proposed method is demonstrated for the experiments involving different arrangements of busbar systems, and the performance of the designed wideband current measuring device is verified through experiments.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726411","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}
{"title":"Fault-Tolerant Placement of Phasor Measurement Units and Communication Infrastructure in SDN-Enabled Wide-Area Monitoring Systems","authors":"Huibin Jia;Weiran Hou;Siqi Wan;Xuguang Wang;Hongyin Xiang","doi":"10.1109/TIM.2025.3551007","DOIUrl":"https://doi.org/10.1109/TIM.2025.3551007","url":null,"abstract":"Software-defined networking (SDN) separates the control plane from the data plane, features flexible configuration and dynamic programmability, and can enhance the survivability of networks during faults. SDN has been widely applied in wide-area monitoring systems (WAMSs) to enhance their fault defense capabilities. This study investigated the fault-tolerant placement problem of phasor measurement units (PMUs) and communication infrastructure of SDN-enabled WAMSs. First, a hidden Markov model was established to describe the recovery process of observable states of power nodes when the failures of power lines and communication networks occur. Based on the hidden Markov model, the availability of synchrophasors of the power node was calculated. Second, a mathematical model for the simultaneously optimal placement of the PMUs and SDN infrastructure was formulated to minimize the construction cost of the WAMS. The mathematical model was calculated using a particle swarm optimization (PSO) algorithm. Finally, simulation experiments were performed on an IEEE 30-bus system and an IEEE 118-bus system to verify the effectiveness of the proposed method. Experimental results indicate that the proposed method can effectively improve the accuracy of the state estimation, which enhances the ability of WAMSs to mitigate failure risks.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-11"},"PeriodicalIF":5.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706758","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}
{"title":"A State-Matching-Based Method for Identifying Intrusive Object Data and Evaluating Collision Features Using Robotic E-Skin Proximity Perception","authors":"Guangming Xue;Guodong Chen;Lining Sun;Huicong Liu","doi":"10.1109/TIM.2025.3551000","DOIUrl":"https://doi.org/10.1109/TIM.2025.3551000","url":null,"abstract":"Proximity perception is a crucial foundation for robotic collision safety control, and e-skin proximity offers unique advantages in this field. However, traditional e-skin proximity data struggle to effectively distinguish between intrusive object data and the data from the robot itself and the surrounding environment, making it accurately evaluate collision features of intrusive objects. This article proposes a state-matching-based method for identifying intrusive object data and evaluating collision features using e-skin proximity. By establishing a nonintrusive feature model, the process extracts the nonintrusive feature data corresponding to the current robot state through state matching and compares it with the current e-skin proximity data. This allows for the effective identification of intrusive object data and the accurate and rapid evaluation of collision features, such as approach distance (AD) and approach orientation (AO). In the static experiments, the proposed method significantly improves the accuracy of evaluating AD and AO. In the dynamic experiments, the method proposed in this article demonstrated a high degree of alignment between the evaluated values and the actual values for AD and AO. Furthermore, this article analyzes the impact of the sampling state differentiation (SD) threshold during the construction of the nonintrusive feature (NIF) model on the subsequent evaluation of the robot’s dynamic AD. It demonstrates that a lower threshold for sampling SD threshold will effectively enhance the stability of the robot’s dynamic feature evaluation. Through experiments on safe collision control of robots along predetermined trajectory, it is proven that the method proposed in this article can achieve safe collision speed control for robots in human-robot interaction (HRI) scenarios, where the robot operates at a speed of 0.5 m/s.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-12"},"PeriodicalIF":5.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706701","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}
{"title":"Estimating Remaining Useful Life of Aircraft Engine System via a Novel Graph Tensor Fusion Network Based on Knowledge of Physical Structure and Thermodynamics","authors":"Ze-Zhou Liu;Tao Sun;Xi-Ming Sun;Wen-Yue Cui","doi":"10.1109/TIM.2025.3550613","DOIUrl":"https://doi.org/10.1109/TIM.2025.3550613","url":null,"abstract":"Accurate estimation of the remaining useful life (RUL) of aircraft engines is critical for aircraft health management and maintenance planning. To address such an issue, this article proposes a spatiotemporal graph attention tensor network (STGATN) based on knowledge of physical structure and thermodynamics. First, by utilizing engine sensor time-series data, we generate and construct an airflow state graph with thermodynamic knowledge and a structure state graph with structural layout knowledge. Then, by introducing a graph attention mechanism to extract spatial features of the two types of state graphs separately, and by proposing a tensor fusion module to embed and integrate the two groups of first-order feature vectors into a high-order tensor data. Furthermore, by designing the convLSTM layer to acquire temporal information of high-order tensor for accurate RUL prediction. Finally, experiments are conducted on the commercial modular aero-propulsion system simulation (CMPASS) dataset and the real engine test dataset. The comparative results show that our approach outperforms existing state-of-the-art methods.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-14"},"PeriodicalIF":5.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735291","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}
{"title":"Tensor Low-Rank Approximation via Plug-and-Play Priors for Anomaly Detection in Remote Sensing Images","authors":"Jingjing Liu;Manlong Feng;Xianchao Xiu;Xiaoyang Zeng;Jianhua Zhang","doi":"10.1109/TIM.2025.3553235","DOIUrl":"https://doi.org/10.1109/TIM.2025.3553235","url":null,"abstract":"Optical remote sensing images (RSIs) have received widespread attention in fields such as agricultural monitoring, mineral exploration, and military defense. However, the detection performance will be seriously degraded when interfered with by noise. To overcome this issue, we first present a novel method called tensor low-rank approximation (TLRA), which leverages the weighted tensor nuclear norm (WTNN) to exploit the spectral overall structure, introduces a new tensor sparse <inline-formula> <tex-math>$ell _{F,0}$ </tex-math></inline-formula> term to characterize the local anomalies, and embeds an auxiliary <inline-formula> <tex-math>$ell _{F}$ </tex-math></inline-formula> term to reduce the impact of Gaussian noise. Compared to existing tensor low-rank methods, the proposed TLRA has shown improvements in feature recognition performance and robustness. Moreover, by integrating pretrained neural networks instead of the WTNN, we further construct a plug-and-play (PnP) deep prior variant, dubbed PnP-TLRA, which can automatically learn nonlocal self-similarity. In addition, we have devised a consolidated optimization strategy utilizing the alternating direction method of multipliers (ADMM). The numerical experiments verify the advantages of the proposed methods over benchmark detectors and also show that PnP-TLRA has a better performance compared to TLRA with respect to effectiveness, efficiency, separability, and convergence. The code of the proposed methods will be published at <uri>https://github.com/EMXlight</uri>.","PeriodicalId":13341,"journal":{"name":"IEEE Transactions on Instrumentation and Measurement","volume":"74 ","pages":"1-14"},"PeriodicalIF":5.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748949","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}