Pub Date : 2024-09-25DOI: 10.1109/TSIPN.2024.3467916
Dong Liang;Shimin Wang;Engang Tian
Multiple rigid bodies can model various practical industrial systems. However, periodic sampled-data communication can have a load over the network subject to limited bandwidth. The research on the leader-follower attitude consensus issue for a group of rigid-body dynamics is conducted in this technical paper. The plant of each follower is subject to unknown external disturbances. To reduce the burden of the communication network, an edge-triggered nonlinear distributed observer with dynamic triggering mechanisms is presented. The proposed observer has the ability to evaluate the leader system's state regardless of implementing the continuous-time exchange of the neighborhood information. The proposed edge-based triggering mechanism is asynchronous while eliminating the Zeno phenomenon. Based on the nonlinear observer, a distributed control protocol together with an adaptive law is put forward in order to realize the leader-follower attitude consensus while attenuating the unknown external disturbances. In the end, an illustrative example of a collection of spacecraft systems is provided to verify the feasibility of our methods.
{"title":"Edge-Triggered Leader–Follower Consensus of Multiple Spacecraft Systems With Unknown Disturbances","authors":"Dong Liang;Shimin Wang;Engang Tian","doi":"10.1109/TSIPN.2024.3467916","DOIUrl":"https://doi.org/10.1109/TSIPN.2024.3467916","url":null,"abstract":"Multiple rigid bodies can model various practical industrial systems. However, periodic sampled-data communication can have a load over the network subject to limited bandwidth. The research on the leader-follower attitude consensus issue for a group of rigid-body dynamics is conducted in this technical paper. The plant of each follower is subject to unknown external disturbances. To reduce the burden of the communication network, an edge-triggered nonlinear distributed observer with dynamic triggering mechanisms is presented. The proposed observer has the ability to evaluate the leader system's state regardless of implementing the continuous-time exchange of the neighborhood information. The proposed edge-based triggering mechanism is asynchronous while eliminating the Zeno phenomenon. Based on the nonlinear observer, a distributed control protocol together with an adaptive law is put forward in order to realize the leader-follower attitude consensus while attenuating the unknown external disturbances. In the end, an illustrative example of a collection of spacecraft systems is provided to verify the feasibility of our methods.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"740-751"},"PeriodicalIF":3.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-20DOI: 10.1109/TSIPN.2024.3464350
Marco Carpentiero;Vincenzo Matta;Ali H. Sayed
In this work we derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints , a regression problem. Agents employ the recently proposed ACTC (adapt-compress-then-combine) diffusion strategy, where the signals exchanged locally by neighboring agents are encoded with randomized differential compression operators. We provide a detailed characterization of the mean-square estimation error, which is shown to comprise a term related to the error that agents would achieve without communication constraints, plus a term arising from compression. The analysis reveals quantitative relationships between the compression loss and fundamental attributes of the distributed regression problem, in particular, the stochastic approximation error caused by the gradient noise and the network topology (through the Perron eigenvector). We show that knowledge of such relationships is critical to allocate optimally the communication resources across the agents, taking into account their individual attributes, such as the quality of their data or their degree of centrality in the network topology. We devise an optimized allocation strategy where the parameters necessary for the optimization can be learned online by the agents. Illustrative examples show that a significant performance improvement, as compared to a blind (i.e., uniform) resource allocation, can be achieved by optimizing the allocation by means of the provided mean-square-error formulas.
{"title":"Compressed Regression Over Adaptive Networks","authors":"Marco Carpentiero;Vincenzo Matta;Ali H. Sayed","doi":"10.1109/TSIPN.2024.3464350","DOIUrl":"https://doi.org/10.1109/TSIPN.2024.3464350","url":null,"abstract":"In this work we derive the performance achievable by a network of distributed agents that solve, \u0000<italic>adaptively</i>\u0000 and in the presence of \u0000<italic>communication constraints</i>\u0000, a regression problem. Agents employ the recently proposed ACTC (adapt-compress-then-combine) diffusion strategy, where the signals exchanged locally by neighboring agents are encoded with \u0000<italic>randomized differential compression</i>\u0000 operators. We provide a detailed characterization of the mean-square estimation error, which is shown to comprise a term related to the error that agents would achieve without communication constraints, plus a term arising from compression. The analysis reveals quantitative relationships between the compression loss and fundamental attributes of the distributed regression problem, in particular, the stochastic approximation error caused by the gradient noise and the network topology (through the Perron eigenvector). We show that knowledge of such relationships is critical to allocate optimally the communication resources across the agents, taking into account their individual attributes, such as the quality of their data or their degree of centrality in the network topology. We devise an optimized allocation strategy where the parameters necessary for the optimization can be learned \u0000<italic>online</i>\u0000 by the agents. Illustrative examples show that a significant performance improvement, as compared to a blind (i.e., uniform) resource allocation, can be achieved by optimizing the allocation by means of the provided mean-square-error formulas.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"851-867"},"PeriodicalIF":3.0,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10685148","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-18DOI: 10.1109/TSIPN.2024.3463408
Siyu Chen;Fengyang Zhao;Haijun Jiang;Zhiyong Yu
The present study addresses the preset-time multi-objective optimization problem subject to external disturbances on directed topologies. Firstly, a novel preset-time robust algorithm is designed by employing two types of time-regulator functions, the linear weighted sum method, global information of cost functions, and integral sliding mode control with robustness. This algorithm is tailored for solving multi-objective optimization problems on strongly connected networks. Additionally, two distributed preset-time estimators are proposed and incorporated into the design of the optimization algorithm, effectively eliminating the dependence on global information. Distinct from existing optimization outcomes, the algorithms developed in this study exhibit superior performance in terms of network structure (digraph), convergence time (preset-time), and robustness. Finally, the correctness and effectiveness of the designed optimization algorithms are corroborated by a bilateral negotiation model.
{"title":"Preset-Time Robust Multi-Objective Optimization Over Directed Networks Based On Multi-Agent Framework","authors":"Siyu Chen;Fengyang Zhao;Haijun Jiang;Zhiyong Yu","doi":"10.1109/TSIPN.2024.3463408","DOIUrl":"10.1109/TSIPN.2024.3463408","url":null,"abstract":"The present study addresses the preset-time multi-objective optimization problem subject to external disturbances on directed topologies. Firstly, a novel preset-time robust algorithm is designed by employing two types of time-regulator functions, the linear weighted sum method, global information of cost functions, and integral sliding mode control with robustness. This algorithm is tailored for solving multi-objective optimization problems on strongly connected networks. Additionally, two distributed preset-time estimators are proposed and incorporated into the design of the optimization algorithm, effectively eliminating the dependence on global information. Distinct from existing optimization outcomes, the algorithms developed in this study exhibit superior performance in terms of network structure (digraph), convergence time (preset-time), and robustness. Finally, the correctness and effectiveness of the designed optimization algorithms are corroborated by a bilateral negotiation model.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"706-714"},"PeriodicalIF":3.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142266491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-13DOI: 10.1109/TSIPN.2024.3458789
Yang Liu;Guochen Pang;Jianlong Qiu;Xiangyong Chen;Jinde Cao
This paper investigates the problem of fault-tolerant control for output regulation in multi-agent systems with actuator multiplicative faults. Initially, a prescribed-time observer is established for the followers to estimate the states of the leader. By incorporating a time-varying scaling function, the convergence time is predetermined, ensuring that the observer error converges to zero independently of the system parameters and initial conditions. Subsequently, a distributed adaptive fault-tolerant controller is designed based on the states of the observer and the relative information among the neighboring agents. It is verified that the designed controller can effectively compensate for actuator faults and address the cooperative output regulation fault-tolerant control problem. Finally, the effectiveness of the adaptive fault-tolerant controller is demonstrated through a simulation example.
{"title":"Fault-Tolerant Control for Output Regulation in Multi-Agent Systems Based on Prescribed-Time Observers","authors":"Yang Liu;Guochen Pang;Jianlong Qiu;Xiangyong Chen;Jinde Cao","doi":"10.1109/TSIPN.2024.3458789","DOIUrl":"10.1109/TSIPN.2024.3458789","url":null,"abstract":"This paper investigates the problem of fault-tolerant control for output regulation in multi-agent systems with actuator multiplicative faults. Initially, a prescribed-time observer is established for the followers to estimate the states of the leader. By incorporating a time-varying scaling function, the convergence time is predetermined, ensuring that the observer error converges to zero independently of the system parameters and initial conditions. Subsequently, a distributed adaptive fault-tolerant controller is designed based on the states of the observer and the relative information among the neighboring agents. It is verified that the designed controller can effectively compensate for actuator faults and address the cooperative output regulation fault-tolerant control problem. Finally, the effectiveness of the adaptive fault-tolerant controller is demonstrated through a simulation example.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"729-739"},"PeriodicalIF":3.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142266492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-11DOI: 10.1109/TSIPN.2024.3458791
Xiaoyue Zhang;Jingfei He;Xiaotong Liu
Restricted by various factors, the data collected by sensor nodes in some Internet of Things (IoT) can only provide spatio-temporal low-resolution multi-attribute information of the monitored area. Estimating environmental data in sensorless deployment locations to achieve spatio-temporal high-resolution multi-attribute data sensing has become an urgent problem. Existing IoT data reconstruction methods either suffer from performance degradation due to continuous data loss or ignore the correlation among multi-attribute data. To overcome these two shortcomings, a multi-attribute data reconstruction method utilizing a high-order spatial delay-embedding transform is proposed in this work. Strict low-rank property can be achieved in the proposed method without additional constraints, avoiding overcomplicating the model by combining too many constraints. The tensor ring decomposition is used to approximate the rank of the formulated data and to efficiently solve the tensor completion model via the alternating least squares algorithm. Experimental results on IoT data demonstrate that the proposed method outperforms the state-of-the-art low-rank-based methods on multi-attribute data reconstruction.
{"title":"Tensor Completion Using High-Order Spatial Delay Embedding for IoT Multi-Attribute Data Reconstruction","authors":"Xiaoyue Zhang;Jingfei He;Xiaotong Liu","doi":"10.1109/TSIPN.2024.3458791","DOIUrl":"10.1109/TSIPN.2024.3458791","url":null,"abstract":"Restricted by various factors, the data collected by sensor nodes in some Internet of Things (IoT) can only provide spatio-temporal low-resolution multi-attribute information of the monitored area. Estimating environmental data in sensorless deployment locations to achieve spatio-temporal high-resolution multi-attribute data sensing has become an urgent problem. Existing IoT data reconstruction methods either suffer from performance degradation due to continuous data loss or ignore the correlation among multi-attribute data. To overcome these two shortcomings, a multi-attribute data reconstruction method utilizing a high-order spatial delay-embedding transform is proposed in this work. Strict low-rank property can be achieved in the proposed method without additional constraints, avoiding overcomplicating the model by combining too many constraints. The tensor ring decomposition is used to approximate the rank of the formulated data and to efficiently solve the tensor completion model via the alternating least squares algorithm. Experimental results on IoT data demonstrate that the proposed method outperforms the state-of-the-art low-rank-based methods on multi-attribute data reconstruction.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"715-728"},"PeriodicalIF":3.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142223946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-30DOI: 10.1109/TSIPN.2024.3444484
Zehan Zhu;Ye Tian;Yan Huang;Jinming Xu;Shibo He
We propose a Robust Fully-Asynchronous Stochastic Gradient Tracking method (R-FAST) for distributed machine learning problems over a network of nodes, where each node performs local computation and communication at its own pace without any form of synchronization. Different from existing asynchronous distributed algorithms, R-FAST can eliminate the impact of data heterogeneity across nodes on convergence performance and allow for packet losses by employing a robust gradient tracking strategy that relies on properly designed auxiliary variables for tracking and buffering the overall gradient vector. Moreover, the proposed method utilizes two spanning-tree graphs for communication so long as both share at least one common root, enabling flexible designs in communication topologies. We show that R-FAST converges in expectation to a neighborhood of the optimum with a geometric rate for smooth and strongly convex objectives; and to a stationary point with a sublinear rate for general non-convex problems. Extensive experiments demonstrate that R-FAST runs 1.5-2 times faster than synchronous benchmark algorithms, such as Ring-AllReduce and D-PSGD, while still achieving comparable accuracy, and outperforms the existing well-known asynchronous algorithms, such as AD-PSGD and OSGP, especially in the presence of stragglers.
{"title":"R-FAST: Robust Fully-Asynchronous Stochastic Gradient Tracking Over General Topology","authors":"Zehan Zhu;Ye Tian;Yan Huang;Jinming Xu;Shibo He","doi":"10.1109/TSIPN.2024.3444484","DOIUrl":"https://doi.org/10.1109/TSIPN.2024.3444484","url":null,"abstract":"We propose a Robust Fully-Asynchronous Stochastic Gradient Tracking method (R-FAST) for distributed machine learning problems over a network of nodes, where each node performs local computation and communication at its own pace without any form of synchronization. Different from existing asynchronous distributed algorithms, R-FAST can eliminate the impact of data heterogeneity across nodes on convergence performance and allow for packet losses by employing a robust gradient tracking strategy that relies on properly designed auxiliary variables for tracking and buffering the overall gradient vector. Moreover, the proposed method utilizes two spanning-tree graphs for communication so long as both share at least one common root, enabling flexible designs in communication topologies. We show that R-FAST converges in expectation to a neighborhood of the optimum with a geometric rate for smooth and strongly convex objectives; and to a stationary point with a sublinear rate for general non-convex problems. Extensive experiments demonstrate that R-FAST runs 1.5-2 times faster than synchronous benchmark algorithms, such as Ring-AllReduce and D-PSGD, while still achieving comparable accuracy, and outperforms the existing well-known asynchronous algorithms, such as AD-PSGD and OSGP, especially in the presence of stragglers.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"665-678"},"PeriodicalIF":3.0,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142173995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1109/TSIPN.2024.3451979
Zhaoming Sheng;Qian Ma
This paper studies the distributed Nash equilibrium seeking problem for players subject to unknown nonlinear dynamics and input delay. By designing a distributed estimator for each player to estimate other players' decisions and embedding an auxiliary variable to compensate for the influence of unknown nonlinearities, the distributed Nash equilibrium seeking algorithms are obtained for first-, second-, and high-order nonlinear players, respectively. With the help of the Lyapunov stability theory and Lyapunov-Krasovskii functional approach, the maximum allowable input delay is determined and the global asymptotic convergence of players' decisions to the Nash equilibrium is proved. Finally, simulation examples are provided to demonstrate the effectiveness of the proposed methods.
{"title":"Distributed Nash Equilibrium Seeking for Nonlinear Players With Input Delay","authors":"Zhaoming Sheng;Qian Ma","doi":"10.1109/TSIPN.2024.3451979","DOIUrl":"https://doi.org/10.1109/TSIPN.2024.3451979","url":null,"abstract":"This paper studies the distributed Nash equilibrium seeking problem for players subject to unknown nonlinear dynamics and input delay. By designing a distributed estimator for each player to estimate other players' decisions and embedding an auxiliary variable to compensate for the influence of unknown nonlinearities, the distributed Nash equilibrium seeking algorithms are obtained for first-, second-, and high-order nonlinear players, respectively. With the help of the Lyapunov stability theory and Lyapunov-Krasovskii functional approach, the maximum allowable input delay is determined and the global asymptotic convergence of players' decisions to the Nash equilibrium is proved. Finally, simulation examples are provided to demonstrate the effectiveness of the proposed methods.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"679-689"},"PeriodicalIF":3.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1109/TSIPN.2024.3451992
Maximilian H. V. Tillmann;Masahiro Yukawa
This paper presents a mathematically rigorous framework of remarkably-robust signal recovery over networks. The proposed framework is based on the minimax concave (MC) loss, which is a weakly convex function so that it attains i) remarkable outlier-robustness and ii) guarantee of convergence to a solution of the posed problem. We present a novel problem formulation which involves an auxiliary vector so that the formulation accommodates statistical properties of signal, noise, and outliers. We show the conditions to guarantee convexity of the local and global objectives. Via reformulation, the distributed triangularly preconditioned primal-dual algorithm is applied to the posed problem. The numerical examples show that our proposed formulation exhibits remarkable robustness under devastating outliers as well as outperforming the existing methods. Comparisons between the local and global convexity conditions are also presented.
{"title":"Stable Outlier-Robust Signal Recovery Over Networks: A Convex Analytic Approach Using Minimax Concave Loss","authors":"Maximilian H. V. Tillmann;Masahiro Yukawa","doi":"10.1109/TSIPN.2024.3451992","DOIUrl":"10.1109/TSIPN.2024.3451992","url":null,"abstract":"This paper presents a mathematically rigorous framework of remarkably-robust signal recovery over networks. The proposed framework is based on the \u0000<italic>minimax concave (MC)</i>\u0000 loss, which is a weakly convex function so that it attains i) remarkable outlier-robustness and ii) guarantee of convergence to a solution of the posed problem. We present a novel problem formulation which involves an auxiliary vector so that the formulation accommodates statistical properties of signal, noise, and outliers. We show the conditions to guarantee convexity of the local and global objectives. Via reformulation, the distributed triangularly preconditioned primal-dual algorithm is applied to the posed problem. The numerical examples show that our proposed formulation exhibits remarkable robustness under devastating outliers as well as outperforming the existing methods. Comparisons between the local and global convexity conditions are also presented.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"690-705"},"PeriodicalIF":3.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142182551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-08DOI: 10.1109/TSIPN.2024.3440644
Lei Shi;Shaojie Yao;Nianwen Ning;Yi Zhou
Accurate localization of underwater wireless sensor networks (UWSNs) are essential for their seamless integration and operational efficacy in marine environments, yet it poses a considerable technical challenge due to the distinctive limitations of underwater communications. This paper addresses the intricate 3-D localization problem for UWSNs by proposing an innovative method based on barycentric coordinates and relative distance measurements. In order to adapt to the influence of underwater communication constraints, a barycentric coordinate-based distributed iterative localization method combining with the processing of underwater background noise is proposed. It is proved theoretically that the proposed method can almost guarantee the convergence to the exact location of each underwater sensor node. Finally, the effectiveness of the proposed localization method is verified by numerical simulations. The proposed localization scheme requires only small number of anchor nodes, thus facilitating the development of broader and more cost-effective underwater localization systems.
{"title":"Barycentric Coordinate-Based Distributed Localization Over 3-D Underwater Wireless Sensor Networks","authors":"Lei Shi;Shaojie Yao;Nianwen Ning;Yi Zhou","doi":"10.1109/TSIPN.2024.3440644","DOIUrl":"10.1109/TSIPN.2024.3440644","url":null,"abstract":"Accurate localization of underwater wireless sensor networks (UWSNs) are essential for their seamless integration and operational efficacy in marine environments, yet it poses a considerable technical challenge due to the distinctive limitations of underwater communications. This paper addresses the intricate 3-D localization problem for UWSNs by proposing an innovative method based on barycentric coordinates and relative distance measurements. In order to adapt to the influence of underwater communication constraints, a barycentric coordinate-based distributed iterative localization method combining with the processing of underwater background noise is proposed. It is proved theoretically that the proposed method can almost guarantee the convergence to the exact location of each underwater sensor node. Finally, the effectiveness of the proposed localization method is verified by numerical simulations. The proposed localization scheme requires only small number of anchor nodes, thus facilitating the development of broader and more cost-effective underwater localization systems.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"640-649"},"PeriodicalIF":3.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141945156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-18DOI: 10.1109/TSIPN.2024.3430474
Junzhong Ji;Feipeng Wang;Lu Han;Jinduo Liu
Current studies have shown that the classification of human brain functional networks (BFN) is a reliable way to diagnose and predict brain diseases. However, a great challenge for current traditional machine learning methods and deep learning methods is their poor performance or lack of interpretability. To alleviate this problem, we propose a novel causal learning and knowledge fusion mechanism for brain functional network classification, named CLKF. The proposed mechanism first extracts causal relationships among brain regions from functional magnetic resonance imaging (fMRI) data using partial correlation and conditional mutual information, and obtains the relationships between BFN and labels by Gaussian kernel density estimation. Then, it fuses these two types of relationships as knowledge to aid in the classification of brain functional networks. The experimental results on the simulated resting-state fMRI dataset show that the proposed mechanism can effectively learn the causal relationships among brain regions. The results on the real resting-state fMRI dataset demonstrate that our mechanism can not only improve the classification performance of both traditional machine learning and deep learning methods but also provide an interpretation of the results obtained by deep learning methods. These findings suggest that the proposed mechanism has good potential in practical medical applications.
{"title":"Causal Learning and Knowledge Fusion Mechanism for Brain Functional Network Classification","authors":"Junzhong Ji;Feipeng Wang;Lu Han;Jinduo Liu","doi":"10.1109/TSIPN.2024.3430474","DOIUrl":"10.1109/TSIPN.2024.3430474","url":null,"abstract":"Current studies have shown that the classification of human brain functional networks (BFN) is a reliable way to diagnose and predict brain diseases. However, a great challenge for current traditional machine learning methods and deep learning methods is their poor performance or lack of interpretability. To alleviate this problem, we propose a novel causal learning and knowledge fusion mechanism for brain functional network classification, named CLKF. The proposed mechanism first extracts causal relationships among brain regions from functional magnetic resonance imaging (fMRI) data using partial correlation and conditional mutual information, and obtains the relationships between BFN and labels by Gaussian kernel density estimation. Then, it fuses these two types of relationships as knowledge to aid in the classification of brain functional networks. The experimental results on the simulated resting-state fMRI dataset show that the proposed mechanism can effectively learn the causal relationships among brain regions. The results on the real resting-state fMRI dataset demonstrate that our mechanism can not only improve the classification performance of both traditional machine learning and deep learning methods but also provide an interpretation of the results obtained by deep learning methods. These findings suggest that the proposed mechanism has good potential in practical medical applications.","PeriodicalId":56268,"journal":{"name":"IEEE Transactions on Signal and Information Processing over Networks","volume":"10 ","pages":"650-664"},"PeriodicalIF":3.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：