Pub Date : 2024-12-20DOI: 10.1109/TSP.2024.3354364
{"title":"IEEE Signal Processing Society Information","authors":"","doi":"10.1109/TSP.2024.3354364","DOIUrl":"https://doi.org/10.1109/TSP.2024.3354364","url":null,"abstract":"","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"72 ","pages":"C2-C2"},"PeriodicalIF":4.6,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10811671","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1109/TSP.2024.3499092
{"title":"List of Reviewers","authors":"","doi":"10.1109/TSP.2024.3499092","DOIUrl":"10.1109/TSP.2024.3499092","url":null,"abstract":"","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"72 ","pages":"5725-5732"},"PeriodicalIF":4.6,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10807693","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-17DOI: 10.1109/TSP.2024.3519442
Danyan Lin;Gang Wang;K. C. Ho;Lei Huang
This paper addresses the multi-object localization problem by using a hybrid of differential time delay (DTD) and angle-of-arrival (AOA) measurements collected by a single receiver in an unsynchronized multistatic localization system, where two kinds of transmitters, intentional transmitters at known positions and unintentional transmitters at unknown positions, are used for the illumination of the objects. By integrating the DTD and AOA measurements, we first derive a new set of transformed observation models relating to the object positions, and then investigate the three cases of intentional transmitters only, a mix of intentional and unintentional transmitters, and unintentional transmitters only. Localization for the first case is addressed by a linear weighted least squares (LWLS) estimator and the other two are solved by applying semidefinite relaxation followed with an LWLS estimator. Furthermore, we conduct a thorough theoretical analysis. It shows that incorporating unintentional transmitters at unknown positions is beneficial to improve the localization performance, and increasing the number of objects will also improve the positioning accuracy when unintentional transmitters are used. Additionally, a theoretical bias analysis is conducted, based on which a bias-subtracted solution is given. Both theoretical mean square error analysis and simulations validate well the good performance of the proposed methods.
{"title":"Hybrid DTD-AOA Multi-Object Localization in 3-D by Single Receiver Without Synchronization and Some Transmitter Positions: Solutions and Analysis","authors":"Danyan Lin;Gang Wang;K. C. Ho;Lei Huang","doi":"10.1109/TSP.2024.3519442","DOIUrl":"10.1109/TSP.2024.3519442","url":null,"abstract":"This paper addresses the multi-object localization problem by using a hybrid of differential time delay (DTD) and angle-of-arrival (AOA) measurements collected by a single receiver in an unsynchronized multistatic localization system, where two kinds of transmitters, intentional transmitters at known positions and unintentional transmitters at unknown positions, are used for the illumination of the objects. By integrating the DTD and AOA measurements, we first derive a new set of transformed observation models relating to the object positions, and then investigate the three cases of intentional transmitters only, a mix of intentional and unintentional transmitters, and unintentional transmitters only. Localization for the first case is addressed by a linear weighted least squares (LWLS) estimator and the other two are solved by applying semidefinite relaxation followed with an LWLS estimator. Furthermore, we conduct a thorough theoretical analysis. It shows that incorporating unintentional transmitters at unknown positions is beneficial to improve the localization performance, and increasing the number of objects will also improve the positioning accuracy when unintentional transmitters are used. Additionally, a theoretical bias analysis is conducted, based on which a bias-subtracted solution is given. Both theoretical mean square error analysis and simulations validate well the good performance of the proposed methods.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"305-323"},"PeriodicalIF":4.6,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142840864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-16DOI: 10.1109/TSP.2024.3518695
Itai Nuri;Nir Shlezinger
A leading family of algorithms for state estimation in dynamic systems with multiple sub-states is based on particle filters (PFs). PFs often struggle when operating under complex or approximated modelling (necessitating many particles) with low latency requirements (limiting the number of particles), as is typically the case in multi target tracking (MTT). In this work, we introduce a deep neural network (DNN) augmentation for PFs termed learning flock (LF) . LF learns to correct a particles-weights set, which we coin flock , based on the relationships between all sub-particles in the set itself, while disregarding the set acquisition procedure. Our proposed LF, which can be readily incorporated into different PFs flow, is designed to facilitate rapid operation by maintaining accuracy with a reduced number of particles. We introduce a dedicated training algorithm, allowing both supervised and unsupervised training, and yielding a module that supports a varying number of sub-states and particles without necessitating re-training. We experimentally show the improvements in performance, robustness, and latency of LF augmentation for radar multi-target tracking, as well its ability to mitigate the effect of a mismatched observation modelling. We also compare and illustrate the advantages of LF over a state-of-the-art DNN-aided PF, and demonstrate that LF enhances both classic PFs as well as DNN-based filters.
{"title":"Learning Flock: Enhancing Sets of Particles for Multi Substate Particle Filtering With Neural Augmentation","authors":"Itai Nuri;Nir Shlezinger","doi":"10.1109/TSP.2024.3518695","DOIUrl":"10.1109/TSP.2024.3518695","url":null,"abstract":"A leading family of algorithms for state estimation in dynamic systems with multiple sub-states is based on particle filters (PFs). PFs often struggle when operating under complex or approximated modelling (necessitating many particles) with low latency requirements (limiting the number of particles), as is typically the case in multi target tracking (MTT). In this work, we introduce a deep neural network (DNN) augmentation for PFs termed \u0000<italic>learning flock (LF)</i>\u0000. LF learns to correct a particles-weights set, which we coin \u0000<italic>flock</i>\u0000, based on the relationships between all sub-particles in the set itself, while disregarding the set acquisition procedure. Our proposed LF, which can be readily incorporated into different PFs flow, is designed to facilitate rapid operation by maintaining accuracy with a reduced number of particles. We introduce a dedicated training algorithm, allowing both supervised and unsupervised training, and yielding a module that supports a varying number of sub-states and particles without necessitating re-training. We experimentally show the improvements in performance, robustness, and latency of LF augmentation for radar multi-target tracking, as well its ability to mitigate the effect of a mismatched observation modelling. We also compare and illustrate the advantages of LF over a state-of-the-art DNN-aided PF, and demonstrate that LF enhances both classic PFs as well as DNN-based filters.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"99-112"},"PeriodicalIF":4.6,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142832369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-13DOI: 10.1109/TSP.2024.3517158
Oscar G. Ibarra-Manzano;José A. Andrade-Lucio;Miguel A. Vazquez Olguin;Yuriy S. Shmaliy
The sampling interval generated by a local clock (biological, physical, or digital) is known to have a certain amount of errors (deterministic or random) called timing jitter. The latter can vary in nature and magnitude depending on how accurately the time scale is formed and the dynamic process is sampled. In state estimation, timing jitter can cause extra errors that cannot always be ignored. In this paper, we modify the Kalman filter for discrete processes with random timing jitter and call it jitter Kalman filter (JKF). The JKF is developed both intuitively and in the first-order approximation. It is shown that to cope with timing jitter, the system noise covariance acquires an additional term, which is proportional to the fractional jitter standard deviation and the process rate. Based on extensive numerical simulations of polynomial and harmonic models, it is shown that unlimited increase in the process rate leads to the fact that the error caused by jitter also grow without limit. Thus, jitter is dangerous for fast processes, but can be neglected in slow processes. Experimental testing has confirmed the high efficiency of JKF.
{"title":"Kalman Filter for Discrete Processes With Timing Jitter","authors":"Oscar G. Ibarra-Manzano;José A. Andrade-Lucio;Miguel A. Vazquez Olguin;Yuriy S. Shmaliy","doi":"10.1109/TSP.2024.3517158","DOIUrl":"10.1109/TSP.2024.3517158","url":null,"abstract":"The sampling interval generated by a local clock (biological, physical, or digital) is known to have a certain amount of errors (deterministic or random) called timing jitter. The latter can vary in nature and magnitude depending on how accurately the time scale is formed and the dynamic process is sampled. In state estimation, timing jitter can cause extra errors that cannot always be ignored. In this paper, we modify the Kalman filter for discrete processes with random timing jitter and call it jitter Kalman filter (JKF). The JKF is developed both intuitively and in the first-order approximation. It is shown that to cope with timing jitter, the system noise covariance acquires an additional term, which is proportional to the fractional jitter standard deviation and the process rate. Based on extensive numerical simulations of polynomial and harmonic models, it is shown that unlimited increase in the process rate leads to the fact that the error caused by jitter also grow without limit. Thus, jitter is dangerous for fast processes, but can be neglected in slow processes. Experimental testing has confirmed the high efficiency of JKF.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"219-229"},"PeriodicalIF":4.6,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142820905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-13DOI: 10.1109/TSP.2024.3517323
Ben Gabrielson;Hanlu Yang;Trung Vu;Vince Calhoun;Tülay Adali
Joint blind source separation (JBSS) involves the factorization of multiple matrices, i.e. “datasets”, into “sources” that are statistically dependent across datasets and independent within datasets. Despite this usefulness for analyzing multiple datasets, JBSS methods suffer from considerable computational costs and are typically intractable for hundreds or thousands of datasets. To address this issue, we present a methodology for how a subset of the datasets can be used to perform efficient JBSS over the full set. We motivate two such methods: a numerical extension of independent vector analysis (IVA) with the multivariate Gaussian model (IVA-G), and a recently proposed analytic method resembling generalized joint diagonalization (GJD). We derive nonidentifiability conditions for both methods, and then demonstrate how one can significantly improve these methods’ generalizability by an efficient representative subset selection method. This involves selecting a coreset (a weighted subset) that minimizes a measure of discrepancy between the statistics of the coreset and the full set. Using simulated and real functional magnetic resonance imaging (fMRI) data, we demonstrate significant scalability and source separation advantages of our “coreIVA-G” method vs. other JBSS methods.
{"title":"Large-Scale Independent Vector Analysis (IVA-G) via Coresets","authors":"Ben Gabrielson;Hanlu Yang;Trung Vu;Vince Calhoun;Tülay Adali","doi":"10.1109/TSP.2024.3517323","DOIUrl":"10.1109/TSP.2024.3517323","url":null,"abstract":"Joint blind source separation (JBSS) involves the factorization of multiple matrices, i.e. “datasets”, into “sources” that are statistically dependent across datasets and independent within datasets. Despite this usefulness for analyzing multiple datasets, JBSS methods suffer from considerable computational costs and are typically intractable for hundreds or thousands of datasets. To address this issue, we present a methodology for how a subset of the datasets can be used to perform efficient JBSS over the full set. We motivate two such methods: a numerical extension of independent vector analysis (IVA) with the multivariate Gaussian model (IVA-G), and a recently proposed analytic method resembling generalized joint diagonalization (GJD). We derive nonidentifiability conditions for both methods, and then demonstrate how one can significantly improve these methods’ generalizability by an efficient representative subset selection method. This involves selecting a \u0000<italic>coreset</i>\u0000 (a weighted subset) that minimizes a measure of discrepancy between the statistics of the coreset and the full set. Using simulated and real functional magnetic resonance imaging (fMRI) data, we demonstrate significant scalability and source separation advantages of our “coreIVA-G” method vs. other JBSS methods.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"230-244"},"PeriodicalIF":4.6,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142820906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-13DOI: 10.1109/TSP.2024.3516709
Mingxin Chen;Ming-Min Zhao;An Liu;Min Li;Qingjiang Shi
In this paper, we consider a cooperative sensing framework in the context of future multi-functional network with both communication and sensing ability, where one base station (BS) serves as a sensing transmitter and several nearby BSs serve as sensing receivers. Each receiver receives the sensing signal reflected by the target and communicates with the fusion center (FC) through a wireless multiple access channel (MAC) for cooperative target localization. To improve the localization performance, we present a hybrid information-signal domain cooperative sensing (HISDCS) design, where each sensing receiver transmits both the estimated time delay/effective reflecting coefficient and the received sensing signal sampled around the estimated time delay to the FC. Then, we propose to minimize the number of channel uses by utilizing an efficient Karhunen-Loéve transformation (KLT) encoding scheme for signal quantization and proper node selection, under the Cramér-Rao lower bound (CRLB) constraint and the capacity limits of MAC. A novel matrix-inequality constrained successive convex approximation (MCSCA) algorithm is proposed to optimize the wireless backhaul resource allocation, together with a greedy strategy for node selection. Despite the high non-convexness of the considered problem, we prove that the proposed MCSCA algorithm is able to converge to the set of Karush-Kuhn-Tucker (KKT) solutions of a relaxed problem obtained by relaxing the discrete variables. Besides, a low-complexity quantization bit reallocation algorithm is designed, which does not perform explicit node selection, and is able to harvest most of the performance gain brought by HISDCS. Finally, numerical simulations are presented to show that the proposed HISDCS design is able to significantly outperform the baseline schemes.
{"title":"Joint Node Selection and Resource Allocation Optimization for Cooperative Sensing With a Shared Wireless Backhaul","authors":"Mingxin Chen;Ming-Min Zhao;An Liu;Min Li;Qingjiang Shi","doi":"10.1109/TSP.2024.3516709","DOIUrl":"10.1109/TSP.2024.3516709","url":null,"abstract":"In this paper, we consider a cooperative sensing framework in the context of future multi-functional network with both communication and sensing ability, where one base station (BS) serves as a sensing transmitter and several nearby BSs serve as sensing receivers. Each receiver receives the sensing signal reflected by the target and communicates with the fusion center (FC) through a wireless multiple access channel (MAC) for cooperative target localization. To improve the localization performance, we present a hybrid information-signal domain cooperative sensing (HISDCS) design, where each sensing receiver transmits both the estimated time delay/effective reflecting coefficient and the received sensing signal sampled around the estimated time delay to the FC. Then, we propose to minimize the number of channel uses by utilizing an efficient Karhunen-Loéve transformation (KLT) encoding scheme for signal quantization and proper node selection, under the Cramér-Rao lower bound (CRLB) constraint and the capacity limits of MAC. A novel matrix-inequality constrained successive convex approximation (MCSCA) algorithm is proposed to optimize the wireless backhaul resource allocation, together with a greedy strategy for node selection. Despite the high non-convexness of the considered problem, we prove that the proposed MCSCA algorithm is able to converge to the set of Karush-Kuhn-Tucker (KKT) solutions of a relaxed problem obtained by relaxing the discrete variables. Besides, a low-complexity quantization bit reallocation algorithm is designed, which does not perform explicit node selection, and is able to harvest most of the performance gain brought by HISDCS. Finally, numerical simulations are presented to show that the proposed HISDCS design is able to significantly outperform the baseline schemes.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"67-82"},"PeriodicalIF":4.6,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142820907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-12DOI: 10.1109/TSP.2024.3516502
Xingyu Zhou;Le Liang;Jing Zhang;Chao-Kai Wen;Shi Jin
The discrete nature of transmitted symbols poses challenges for achieving optimal detection in multiple-input multiple-output (MIMO) systems associated with a large number of antennas. Recently, the combination of two powerful machine learning methods, Markov chain Monte Carlo (MCMC) sampling and gradient descent, has emerged as a highly efficient solution to address this issue. However, existing gradient-based MCMC detectors are heuristically designed and thus are theoretically untenable. To bridge this gap, we introduce a novel sampling algorithm tailored for discrete spaces. This algorithm leverages gradients from the underlying continuous spaces for acceleration while maintaining the validity of probabilistic sampling. We prove the convergence of this method and also analyze its convergence rate using both MCMC theory and empirical diagnostics. On this basis, we develop a MIMO detector that precisely samples from the target discrete distribution and generates posterior Bayesian estimates using these samples, whose performance is thereby theoretically guaranteed. Furthermore, our proposed detector is highly parallelizable and scalable to large MIMO dimensions, positioning it as a compelling candidate for next-generation wireless networks. Simulation results show that our detector achieves near-optimal performance, significantly outperforms state-of-the-art baselines, and showcases resilience to various system setups.
{"title":"Near-Optimal MIMO Detection Using Gradient-Based MCMC in Discrete Spaces","authors":"Xingyu Zhou;Le Liang;Jing Zhang;Chao-Kai Wen;Shi Jin","doi":"10.1109/TSP.2024.3516502","DOIUrl":"10.1109/TSP.2024.3516502","url":null,"abstract":"The discrete nature of transmitted symbols poses challenges for achieving optimal detection in multiple-input multiple-output (MIMO) systems associated with a large number of antennas. Recently, the combination of two powerful machine learning methods, Markov chain Monte Carlo (MCMC) sampling and gradient descent, has emerged as a highly efficient solution to address this issue. However, existing gradient-based MCMC detectors are heuristically designed and thus are theoretically untenable. To bridge this gap, we introduce a novel sampling algorithm tailored for discrete spaces. This algorithm leverages gradients from the underlying continuous spaces for acceleration while maintaining the validity of probabilistic sampling. We prove the convergence of this method and also analyze its convergence rate using both MCMC theory and empirical diagnostics. On this basis, we develop a MIMO detector that precisely samples from the target discrete distribution and generates posterior Bayesian estimates using these samples, whose performance is thereby theoretically guaranteed. Furthermore, our proposed detector is highly parallelizable and scalable to large MIMO dimensions, positioning it as a compelling candidate for next-generation wireless networks. Simulation results show that our detector achieves near-optimal performance, significantly outperforms state-of-the-art baselines, and showcases resilience to various system setups.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"584-600"},"PeriodicalIF":4.6,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142815710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-12DOI: 10.1109/TSP.2024.3511452
Haoyuan Cai;Sulaiman A. Alghunaim;Ali H. Sayed
The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of $mathcal{O}(varepsilon^{-2})$ to achieve an $varepsilon$ -stationary solution, we introduce and analyze a new formulation termed Diffusion Stochastic Same-Sample Optimistic Gradient (DSS-OG). We prove its convergence and resolve the large batch issue by establishing a tighter upper bound, under the more general setting of nonconvex Polyak-Lojasiewicz (PL) risk functions. We also extend the applicability of the proposed method to the distributed scenario, where agents communicate with their neighbors via a left-stochastic protocol. To implement DSS-OG, we can query the stochastic gradient oracles in parallel with some extra memory overhead, resulting in a complexity comparable to its conventional counterpart. To demonstrate the efficacy of the proposed algorithm, we conduct tests by training generative adversarial networks.
{"title":"Diffusion Stochastic Optimization for Min-Max Problems","authors":"Haoyuan Cai;Sulaiman A. Alghunaim;Ali H. Sayed","doi":"10.1109/TSP.2024.3511452","DOIUrl":"10.1109/TSP.2024.3511452","url":null,"abstract":"The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of \u0000<inline-formula><tex-math>$mathcal{O}(varepsilon^{-2})$</tex-math></inline-formula>\u0000 to achieve an \u0000<inline-formula><tex-math>$varepsilon$</tex-math></inline-formula>\u0000-stationary solution, we introduce and analyze a new formulation termed Diffusion Stochastic Same-Sample Optimistic Gradient (DSS-OG). We prove its convergence and resolve the large batch issue by establishing a tighter upper bound, under the more general setting of nonconvex Polyak-Lojasiewicz (PL) risk functions. We also extend the applicability of the proposed method to the distributed scenario, where agents communicate with their neighbors via a left-stochastic protocol. To implement DSS-OG, we can query the stochastic gradient oracles in parallel with some extra memory overhead, resulting in a complexity comparable to its conventional counterpart. To demonstrate the efficacy of the proposed algorithm, we conduct tests by training generative adversarial networks.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"259-274"},"PeriodicalIF":4.6,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142815498","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}
Communication base stations can achieve high-precision tracking and accurate classification for multiple extended targets in the context of integrated communication and sensing by transmitting wideband signal. However, the time resources of the base stations are often limited. In the time-division operation mode, part of the time resources must be reserved to guarantee communication performance, while the rest of the resources must be properly allocated for better multi-target sensing performance. To deal with this, we develop a sensing task-oriented resource allocation (RA) scheme for wideband sensors. We first derive the Cramér–Rao lower bound for the estimation errors of position and shape parameters of the extended targets, and analyze their inside relations w.r.t. the resource vectors. Based on this, we construct the evaluation metric of tracking and classification performance, and subsequently build a non-smooth mathematical resource optimization model to maximize the target capacity within predetermined tracking and classification requirements. To solve this RA model, we then design an efficient two-step solution technique that incorporates dual transformation and discrete search. Finally, simulation results demonstrate that the proposed RA scheme can greatly increase the number of the well sensed targets within a limited sensing resource budget.
{"title":"Wideband Sensor Resource Allocation for Extended Target Tracking and Classification","authors":"Hao Jiao;Junkun Yan;Wenqiang Pu;Yijun Chen;Hongwei Liu;Maria Sabrina Greco","doi":"10.1109/TSP.2024.3512615","DOIUrl":"10.1109/TSP.2024.3512615","url":null,"abstract":"Communication base stations can achieve high-precision tracking and accurate classification for multiple extended targets in the context of integrated communication and sensing by transmitting wideband signal. However, the time resources of the base stations are often limited. In the time-division operation mode, part of the time resources must be reserved to guarantee communication performance, while the rest of the resources must be properly allocated for better multi-target sensing performance. To deal with this, we develop a sensing task-oriented resource allocation (RA) scheme for wideband sensors. We first derive the Cramér–Rao lower bound for the estimation errors of position and shape parameters of the extended targets, and analyze their inside relations w.r.t. the resource vectors. Based on this, we construct the evaluation metric of tracking and classification performance, and subsequently build a non-smooth mathematical resource optimization model to maximize the target capacity within predetermined tracking and classification requirements. To solve this RA model, we then design an efficient two-step solution technique that incorporates dual transformation and discrete search. Finally, simulation results demonstrate that the proposed RA scheme can greatly increase the number of the well sensed targets within a limited sensing resource budget.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"55-66"},"PeriodicalIF":4.6,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142815712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：