Amar Kasibovic, Benedikt Fesl, Michael Baur, Wolfgang Utschick
Pilot contamination (PC) is a well-known problem that affects massive multiple-input multiple-output (MIMO) systems. When frequency and pilots are reused between different cells, PC constitutes one of the main bottlenecks of the system's performance. In this paper, we propose a method based on the variational autoencoder (VAE), capable of reducing the impact of PC-related interference during channel estimation (CE). We obtain the first and second-order statistics of the conditionally Gaussian (CG) channels for both the user equipments (UEs) in a cell of interest and those in interfering cells, and we then use these moments to compute conditional linear minimum mean square error estimates. We show that the proposed estimator is capable of exploiting the interferers' additional statistical knowledge, outperforming other classical approaches. Moreover, we highlight how the achievable performance is tied to the chosen setup, making the setup selection crucial in the study of multi-cell CE.
先导污染（PC）是影响大规模多输入多输出（MIMO）系统的一个众所周知的问题。当频率和先导在不同小区之间使用时，PC 是系统性能的主要瓶颈之一。本文提出了一种基于变量自动编码器（VAE）的方法，能够在信道估计（CE）过程中减少 PC 相关干扰的影响。我们获得了相关小区用户设备（UE）和干扰小区用户设备（UE）的条件高斯（CG）信道的一阶和二阶统计量，然后利用这些矩来计算条件线性最小均方误差估计值。我们的研究表明，所提出的估计器能够利用干扰者的额外统计知识，其性能优于其他经典方法。此外，我们还强调了可实现的性能与所选设置的关系，从而使设置选择在多小区 CE 研究中变得至关重要。
{"title":"Addressing Pilot Contamination in Channel Estimation with Variational Autoencoders","authors":"Amar Kasibovic, Benedikt Fesl, Michael Baur, Wolfgang Utschick","doi":"arxiv-2409.07071","DOIUrl":"https://doi.org/arxiv-2409.07071","url":null,"abstract":"Pilot contamination (PC) is a well-known problem that affects massive\u0000multiple-input multiple-output (MIMO) systems. When frequency and pilots are\u0000reused between different cells, PC constitutes one of the main bottlenecks of\u0000the system's performance. In this paper, we propose a method based on the\u0000variational autoencoder (VAE), capable of reducing the impact of PC-related\u0000interference during channel estimation (CE). We obtain the first and\u0000second-order statistics of the conditionally Gaussian (CG) channels for both\u0000the user equipments (UEs) in a cell of interest and those in interfering cells,\u0000and we then use these moments to compute conditional linear minimum mean square\u0000error estimates. We show that the proposed estimator is capable of exploiting\u0000the interferers' additional statistical knowledge, outperforming other\u0000classical approaches. Moreover, we highlight how the achievable performance is\u0000tied to the chosen setup, making the setup selection crucial in the study of\u0000multi-cell CE.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Harris K. Armeniakos, Petros S. Bithas, Konstantinos Maliatsos, Athanasios G. Kanatas
This letter studies the joint energy and signal-to-interference-plus-noise (SINR)-based coverage probability in Unmanned Aerial Vehicle (UAV)-assisted radio frequency (RF)-powered Internet of Things (IoT) networks. The UAVs are spatially distributed in an aerial corridor that is modeled as a one-dimensional (1D) binomial point process (BPP). By accurately capturing the line-of-sight (LoS) probability of a UAV through large-scale fading i) an exact form expression for the energy coverage probability is derived, and ii) a tight approximation for the overall coverage performance is obtained. Among several key findings, numerical results reveal the optimal number of deployed UAV-BSs that maximizes the joint coverage probability, as well as the optimal length of the UAV corridors when designing such UAV-assisted IoT networks.
{"title":"Joint Energy and SINR Coverage Probability in UAV Corridor-assisted RF-powered IoT Networks","authors":"Harris K. Armeniakos, Petros S. Bithas, Konstantinos Maliatsos, Athanasios G. Kanatas","doi":"arxiv-2409.07333","DOIUrl":"https://doi.org/arxiv-2409.07333","url":null,"abstract":"This letter studies the joint energy and signal-to-interference-plus-noise\u0000(SINR)-based coverage probability in Unmanned Aerial Vehicle (UAV)-assisted\u0000radio frequency (RF)-powered Internet of Things (IoT) networks. The UAVs are\u0000spatially distributed in an aerial corridor that is modeled as a\u0000one-dimensional (1D) binomial point process (BPP). By accurately capturing the\u0000line-of-sight (LoS) probability of a UAV through large-scale fading i) an exact\u0000form expression for the energy coverage probability is derived, and ii) a tight\u0000approximation for the overall coverage performance is obtained. Among several\u0000key findings, numerical results reveal the optimal number of deployed UAV-BSs\u0000that maximizes the joint coverage probability, as well as the optimal length of\u0000the UAV corridors when designing such UAV-assisted IoT networks.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"116 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Corentin Piozin, Lisa Bouarroudj, Jean-Yves Audran, Brice Lavrard, Catherine Simon, Florian Waszak, Selim Eskiizmirliler
Decoding multiple movements from the same limb using electroencephalographic (EEG) activity is a key challenge with applications for controlling prostheses in upper-limb amputees. This study investigates the classification of four hand movements to control a modified Myobock prosthesis via EEG signals. We report results from three EEG recording sessions involving four amputees and twenty able-bodied subjects performing four grasp movements under three conditions: Motor Execution (ME), Motor Imagery (MI), and Motor Observation (MO). EEG preprocessing was followed by feature extraction using Common Spatial Patterns (CSP), Wavelet Decomposition (WD), and Riemannian Geometry. Various classification algorithms were applied to decode EEG signals, and a metric assessed pattern separability. We evaluated system performance across different electrode combinations and compared it to the original setup. Our results show that distinguishing movement from no movement achieved 100% accuracy, while classification between movements reached 70-90%. No significant differences were found between recording conditions in classification performance. Able-bodied participants outperformed amputees, but there were no significant differences in Motor Imagery. Performance did not improve across the sessions, and there was considerable variability in EEG pattern distinction. Reducing the number of electrodes by half led to only a 2% average accuracy drop. These results provide insights into developing wearable brain-machine interfaces, particularly for electrode optimization and training in grasp movement classification.
{"title":"Variability in Grasp Type Distinction for Myoelectric Prosthesis Control Using a Non-Invasive Brain-Machine Interface","authors":"Corentin Piozin, Lisa Bouarroudj, Jean-Yves Audran, Brice Lavrard, Catherine Simon, Florian Waszak, Selim Eskiizmirliler","doi":"arxiv-2409.07207","DOIUrl":"https://doi.org/arxiv-2409.07207","url":null,"abstract":"Decoding multiple movements from the same limb using electroencephalographic\u0000(EEG) activity is a key challenge with applications for controlling prostheses\u0000in upper-limb amputees. This study investigates the classification of four hand\u0000movements to control a modified Myobock prosthesis via EEG signals. We report\u0000results from three EEG recording sessions involving four amputees and twenty\u0000able-bodied subjects performing four grasp movements under three conditions:\u0000Motor Execution (ME), Motor Imagery (MI), and Motor Observation (MO). EEG\u0000preprocessing was followed by feature extraction using Common Spatial Patterns\u0000(CSP), Wavelet Decomposition (WD), and Riemannian Geometry. Various\u0000classification algorithms were applied to decode EEG signals, and a metric\u0000assessed pattern separability. We evaluated system performance across different\u0000electrode combinations and compared it to the original setup. Our results show\u0000that distinguishing movement from no movement achieved 100% accuracy, while\u0000classification between movements reached 70-90%. No significant differences\u0000were found between recording conditions in classification performance.\u0000Able-bodied participants outperformed amputees, but there were no significant\u0000differences in Motor Imagery. Performance did not improve across the sessions,\u0000and there was considerable variability in EEG pattern distinction. Reducing the\u0000number of electrodes by half led to only a 2% average accuracy drop. These\u0000results provide insights into developing wearable brain-machine interfaces,\u0000particularly for electrode optimization and training in grasp movement\u0000classification.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"106 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Övgü Özdemir, M. Tuğberk İşyapar, Pınar Karagöz, Klaus Werner Schmidt, Demet Demir, N. Alpay Karagöz
Modern vehicles are equipped with Electronic Control Units (ECU) that are used for controlling important vehicle functions including safety-critical operations. ECUs exchange information via in-vehicle communication buses, of which the Controller Area Network (CAN bus) is by far the most widespread representative. Problems that may occur in the vehicle's physical parts or malicious attacks may cause anomalies in the CAN traffic, impairing the correct vehicle operation. Therefore, the detection of such anomalies is vital for vehicle safety. This paper reviews the research on anomaly detection for in-vehicle networks, more specifically for the CAN bus. Our main focus is the evaluation of methods used for CAN bus anomaly detection together with the datasets used in such analysis. To provide the reader with a more comprehensive understanding of the subject, we first give a brief review of related studies on time series-based anomaly detection. Then, we conduct an extensive survey of recent deep learning-based techniques as well as conventional techniques for CAN bus anomaly detection. Our comprehensive analysis delves into anomaly detection algorithms employed in in-vehicle networks, specifically focusing on their learning paradigms, inherent strengths, and weaknesses, as well as their efficacy when applied to CAN bus datasets. Lastly, we highlight challenges and open research problems in CAN bus anomaly detection.
现代汽车配备有电子控制单元（ECU），用于控制重要的汽车功能，包括安全关键操作。ECU 通过车载通信总线交换信息，其中控制器区域网络（CAN 总线）是迄今为止最广泛的代表。车辆物理部件可能出现的问题或恶意攻击可能会导致 CAN 流量异常，从而影响车辆的正确运行。因此，检测此类异常对车辆安全至关重要。本文回顾了车载网络异常检测方面的研究，特别是 CAN 总线异常检测方面的研究。我们的主要重点是评估 CAN 总线异常检测方法以及用于此类分析的数据集。为了让读者更全面地了解这一主题，我们首先简要回顾了基于时间序列的异常检测方面的相关研究。然后，我们对近期基于深度学习的技术以及用于 CAN 总线异常检测的传统技术进行了广泛调查。我们的综合分析深入探讨了车载网络中采用的异常检测算法，特别关注了这些算法的学习范式、内在优缺点以及应用于 CAN 总线数据集时的有效性。最后，我们强调了 CAN 总线异常检测面临的挑战和有待解决的研究问题。
{"title":"A Survey of Anomaly Detection in In-Vehicle Networks","authors":"Övgü Özdemir, M. Tuğberk İşyapar, Pınar Karagöz, Klaus Werner Schmidt, Demet Demir, N. Alpay Karagöz","doi":"arxiv-2409.07505","DOIUrl":"https://doi.org/arxiv-2409.07505","url":null,"abstract":"Modern vehicles are equipped with Electronic Control Units (ECU) that are\u0000used for controlling important vehicle functions including safety-critical\u0000operations. ECUs exchange information via in-vehicle communication buses, of\u0000which the Controller Area Network (CAN bus) is by far the most widespread\u0000representative. Problems that may occur in the vehicle's physical parts or\u0000malicious attacks may cause anomalies in the CAN traffic, impairing the correct\u0000vehicle operation. Therefore, the detection of such anomalies is vital for\u0000vehicle safety. This paper reviews the research on anomaly detection for\u0000in-vehicle networks, more specifically for the CAN bus. Our main focus is the\u0000evaluation of methods used for CAN bus anomaly detection together with the\u0000datasets used in such analysis. To provide the reader with a more comprehensive\u0000understanding of the subject, we first give a brief review of related studies\u0000on time series-based anomaly detection. Then, we conduct an extensive survey of\u0000recent deep learning-based techniques as well as conventional techniques for\u0000CAN bus anomaly detection. Our comprehensive analysis delves into anomaly\u0000detection algorithms employed in in-vehicle networks, specifically focusing on\u0000their learning paradigms, inherent strengths, and weaknesses, as well as their\u0000efficacy when applied to CAN bus datasets. Lastly, we highlight challenges and\u0000open research problems in CAN bus anomaly detection.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"46 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
EEG-based emotion recognition holds significant potential in the field of brain-computer interfaces. A key challenge lies in extracting discriminative spatiotemporal features from electroencephalogram (EEG) signals. Existing studies often rely on domain-specific time-frequency features and analyze temporal dependencies and spatial characteristics separately, neglecting the interaction between local-global relationships and spatiotemporal dynamics. To address this, we propose a novel network called Multi-Scale Inverted Mamba (MS-iMamba), which consists of Multi-Scale Temporal Blocks (MSTB) and Temporal-Spatial Fusion Blocks (TSFB). Specifically, MSTBs are designed to capture both local details and global temporal dependencies across different scale subsequences. The TSFBs, implemented with an inverted Mamba structure, focus on the interaction between dynamic temporal dependencies and spatial characteristics. The primary advantage of MS-iMamba lies in its ability to leverage reconstructed multi-scale EEG sequences, exploiting the interaction between temporal and spatial features without the need for domain-specific time-frequency feature extraction. Experimental results on the DEAP, DREAMER, and SEED datasets demonstrate that MS-iMamba achieves classification accuracies of 94.86%, 94.94%, and 91.36%, respectively, using only four-channel EEG signals, outperforming state-of-the-art methods.
{"title":"Multi-scale spatiotemporal representation learning for EEG-based emotion recognition","authors":"Xin Zhou, Xiaojing Peng","doi":"arxiv-2409.07589","DOIUrl":"https://doi.org/arxiv-2409.07589","url":null,"abstract":"EEG-based emotion recognition holds significant potential in the field of\u0000brain-computer interfaces. A key challenge lies in extracting discriminative\u0000spatiotemporal features from electroencephalogram (EEG) signals. Existing\u0000studies often rely on domain-specific time-frequency features and analyze\u0000temporal dependencies and spatial characteristics separately, neglecting the\u0000interaction between local-global relationships and spatiotemporal dynamics. To\u0000address this, we propose a novel network called Multi-Scale Inverted Mamba\u0000(MS-iMamba), which consists of Multi-Scale Temporal Blocks (MSTB) and\u0000Temporal-Spatial Fusion Blocks (TSFB). Specifically, MSTBs are designed to\u0000capture both local details and global temporal dependencies across different\u0000scale subsequences. The TSFBs, implemented with an inverted Mamba structure,\u0000focus on the interaction between dynamic temporal dependencies and spatial\u0000characteristics. The primary advantage of MS-iMamba lies in its ability to\u0000leverage reconstructed multi-scale EEG sequences, exploiting the interaction\u0000between temporal and spatial features without the need for domain-specific\u0000time-frequency feature extraction. Experimental results on the DEAP, DREAMER,\u0000and SEED datasets demonstrate that MS-iMamba achieves classification accuracies\u0000of 94.86%, 94.94%, and 91.36%, respectively, using only four-channel EEG\u0000signals, outperforming state-of-the-art methods.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
High-speed train (HST) has garnered significant attention from both academia and industry due to the rapid development of railways worldwide. Millimeter wave (mmWave) communication, known for its large bandwidth is an effective way to address performance bottlenecks in cellular network based HST wireless communication systems. However, mmWave signals suffer from significant path loss when traversing carriage, posing substantial challenges to cellular networks. To address this issue, reconfigurable intelligent surfaces (RIS) have gained considerable interest for its ability to enhance cell coverage by reflecting signals toward receiver. Ensuring communication reliability, a core performance indicators of ultra-reliable and low-latency communications (URLLC) in fifth-generation systems, is crucial for providing steady and reliable data transmissions along railways, particularly for delivering safety and control messages and monitoring HST signaling information. In this paper, we investigate a refracting RIS-assisted multi-user multiple-input single-output URLLC system in mmWave HST communications. We propose a sum rate maximization problem, subject to base station beamforming constraint, as well as refracting RIS discrete phase shifts and reliability constraints. To solve this optimization problem, we design a joint optimization algorithm based on alternating optimization method. This involves decoupling the original optimization problem into active beamforming design and packet error probability optimization subproblem, and discrete phase shift design subproblems. These subproblems are addressed exploiting Lagrangian dual method and the local search method, respectively. Simulation results demonstrate the fast convergence of the proposed algorithm and highlight the benefits of refracting RIS adoption for sum rate improvement in mmWave HST networks.
{"title":"Refracting Reconfigurable Intelligent Surface Assisted URLLC for Millimeter Wave High-Speed Train Communication Coverage Enhancement","authors":"Changzhu Liu, Ruisi He, Yong Niu, Shiwen Mao, Bo Ai, Ruifeng Chen","doi":"arxiv-2409.06946","DOIUrl":"https://doi.org/arxiv-2409.06946","url":null,"abstract":"High-speed train (HST) has garnered significant attention from both academia\u0000and industry due to the rapid development of railways worldwide. Millimeter\u0000wave (mmWave) communication, known for its large bandwidth is an effective way\u0000to address performance bottlenecks in cellular network based HST wireless\u0000communication systems. However, mmWave signals suffer from significant path\u0000loss when traversing carriage, posing substantial challenges to cellular\u0000networks. To address this issue, reconfigurable intelligent surfaces (RIS) have\u0000gained considerable interest for its ability to enhance cell coverage by\u0000reflecting signals toward receiver. Ensuring communication reliability, a core\u0000performance indicators of ultra-reliable and low-latency communications (URLLC)\u0000in fifth-generation systems, is crucial for providing steady and reliable data\u0000transmissions along railways, particularly for delivering safety and control\u0000messages and monitoring HST signaling information. In this paper, we\u0000investigate a refracting RIS-assisted multi-user multiple-input single-output\u0000URLLC system in mmWave HST communications. We propose a sum rate maximization\u0000problem, subject to base station beamforming constraint, as well as refracting\u0000RIS discrete phase shifts and reliability constraints. To solve this\u0000optimization problem, we design a joint optimization algorithm based on\u0000alternating optimization method. This involves decoupling the original\u0000optimization problem into active beamforming design and packet error\u0000probability optimization subproblem, and discrete phase shift design\u0000subproblems. These subproblems are addressed exploiting Lagrangian dual method\u0000and the local search method, respectively. Simulation results demonstrate the\u0000fast convergence of the proposed algorithm and highlight the benefits of\u0000refracting RIS adoption for sum rate improvement in mmWave HST networks.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artifact removal in electroencephalography (EEG) is a longstanding challenge that significantly impacts neuroscientific analysis and brain-computer interface (BCI) performance. Tackling this problem demands advanced algorithms, extensive noisy-clean training data, and thorough evaluation strategies. This study presents the Artifact Removal Transformer (ART), an innovative EEG denoising model employing transformer architecture to adeptly capture the transient millisecond-scale dynamics characteristic of EEG signals. Our approach offers a holistic, end-to-end denoising solution for diverse artifact types in multichannel EEG data. We enhanced the generation of noisy-clean EEG data pairs using an independent component analysis, thus fortifying the training scenarios critical for effective supervised learning. We performed comprehensive validations using a wide range of open datasets from various BCI applications, employing metrics like mean squared error and signal-to-noise ratio, as well as sophisticated techniques such as source localization and EEG component classification. Our evaluations confirm that ART surpasses other deep-learning-based artifact removal methods, setting a new benchmark in EEG signal processing. This advancement not only boosts the accuracy and reliability of artifact removal but also promises to catalyze further innovations in the field, facilitating the study of brain dynamics in naturalistic environments.
{"title":"ART: Artifact Removal Transformer for Reconstructing Noise-Free Multichannel Electroencephalographic Signals","authors":"Chun-Hsiang Chuang, Kong-Yi Chang, Chih-Sheng Huang, Anne-Mei Bessas","doi":"arxiv-2409.07326","DOIUrl":"https://doi.org/arxiv-2409.07326","url":null,"abstract":"Artifact removal in electroencephalography (EEG) is a longstanding challenge\u0000that significantly impacts neuroscientific analysis and brain-computer\u0000interface (BCI) performance. Tackling this problem demands advanced algorithms,\u0000extensive noisy-clean training data, and thorough evaluation strategies. This\u0000study presents the Artifact Removal Transformer (ART), an innovative EEG\u0000denoising model employing transformer architecture to adeptly capture the\u0000transient millisecond-scale dynamics characteristic of EEG signals. Our\u0000approach offers a holistic, end-to-end denoising solution for diverse artifact\u0000types in multichannel EEG data. We enhanced the generation of noisy-clean EEG\u0000data pairs using an independent component analysis, thus fortifying the\u0000training scenarios critical for effective supervised learning. We performed\u0000comprehensive validations using a wide range of open datasets from various BCI\u0000applications, employing metrics like mean squared error and signal-to-noise\u0000ratio, as well as sophisticated techniques such as source localization and EEG\u0000component classification. Our evaluations confirm that ART surpasses other\u0000deep-learning-based artifact removal methods, setting a new benchmark in EEG\u0000signal processing. This advancement not only boosts the accuracy and\u0000reliability of artifact removal but also promises to catalyze further\u0000innovations in the field, facilitating the study of brain dynamics in\u0000naturalistic environments.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"75 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Considering the problem of nonlinear and non-gaussian filtering of the graph signal, in this paper, a robust square root unscented Kalman filter based on graph signal processing is proposed. The algorithm uses a graph topology to generate measurements and an unscented transformation is used to obtain the priori state estimates. In addition, in order to enhance the numerical stability of the unscented Kalman filter, the algorithm combines the double square root decomposition method to update the covariance matrix in the graph frequency domain. Furthermore, to handle the non-Gaussian noise problem in the state estimation process, an error augmentation model is constructed in the graph frequency domain by unifying the measurement error and state error, which utilizes the Laplace matrix of the graph to effectively reduce the cumulative error at each vertex. Then the general robust cost function is adopted as the optimal criterion to deal with the error, which has more parameter options so that effectively suppresses the problems of random outliers and abnormal measurement values in the state estimation process. Finally, the convergence of the error of the proposed algorithm is firstly verified theoretically, and then the robustness of the proposed algorithm is verified by experimental simulation.
{"title":"Robust Square Root Unscented Kalman filter of graph signals","authors":"Jinhui Hu, Haiquan Zhao, Yi Peng","doi":"arxiv-2409.06981","DOIUrl":"https://doi.org/arxiv-2409.06981","url":null,"abstract":"Considering the problem of nonlinear and non-gaussian filtering of the graph\u0000signal, in this paper, a robust square root unscented Kalman filter based on\u0000graph signal processing is proposed. The algorithm uses a graph topology to\u0000generate measurements and an unscented transformation is used to obtain the\u0000priori state estimates. In addition, in order to enhance the numerical\u0000stability of the unscented Kalman filter, the algorithm combines the double\u0000square root decomposition method to update the covariance matrix in the graph\u0000frequency domain. Furthermore, to handle the non-Gaussian noise problem in the\u0000state estimation process, an error augmentation model is constructed in the\u0000graph frequency domain by unifying the measurement error and state error, which\u0000utilizes the Laplace matrix of the graph to effectively reduce the cumulative\u0000error at each vertex. Then the general robust cost function is adopted as the\u0000optimal criterion to deal with the error, which has more parameter options so\u0000that effectively suppresses the problems of random outliers and abnormal\u0000measurement values in the state estimation process. Finally, the convergence of\u0000the error of the proposed algorithm is firstly verified theoretically, and then\u0000the robustness of the proposed algorithm is verified by experimental\u0000simulation.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose: To develop and evaluate a new pulse sequence for highly accelerated distortion-free diffusion MRI (dMRI) by inserting an additional echo without prolonging TR, when generalized slice dithered enhanced resolution (gSlider) radiofrequency encoding is used for volumetric acquisition. Methods: A phase-reversed interleaved multi-echo acquisition (PRIME) was developed for rapid, high-resolution, and distortion-free dMRI, which includes two echoes where the first echo is for target diffusion-weighted imaging (DWI) acquisition with high-resolution and the second echo is acquired with either 1) lower-resolution for high-fidelity field map estimation, or 2) matching resolution to enable efficient diffusion relaxometry acquisitions. The sequence was evaluated on in vivo data acquired from healthy volunteers on clinical and Connectome 2.0 scanners. Results: In vivo experiments demonstrated that 1) high in-plane acceleration (Rin-plane of 5-fold with 2D partial Fourier) was achieved using the high-fidelity field maps estimated from the second echo, which was made at a lower resolution/acceleration to increase its SNR while matching the effective echo spacing of the first readout, 2) high-resolution diffusion relaxometry parameters were estimated from dual-echo PRIME data using a white matter model of multi-TE spherical mean technique (MTE-SMT), and 3) high-fidelity mesoscale DWI at 550 um isotropic resolution could be obtained in vivo by capitalizing on the high-performance gradients of the Connectome 2.0 scanner. Conclusion: The proposed PRIME sequence enabled highly accelerated, high-resolution, and distortion-free dMRI using an additional echo without prolonging scan time when gSlider encoding is utilized.
目的：开发并评估一种新的脉冲序列，当使用广义切片抖动增强分辨率（gSlider）射频编码进行容积采集时，通过插入额外的回波，在不延长 TR 的情况下实现高度加速的无失真弥散 MRI（dMRI）。方法：相位反转交错多回波采集（PRIME）是为快速、高分辨率和无失真 dMRI 而开发的，它包括两个回波，其中第一个回波用于高分辨率的目标扩散加权成像（DWI）采集，第二个回波用于 1) 低分辨率的高保真场图估算，或 2) 匹配分辨率的高效扩散弛豫测量采集。该序列在临床和Connectome 2.0扫描仪上获取的健康志愿者的体内数据上进行了评估。结果显示活体实验表明：1）使用从第二次回波中估算出的高保真场图实现了高面内加速（二维部分傅立叶的 5 倍面内加速），第二次回波以较低的分辨率/加速度进行，以提高信噪比，同时与第一次读出的有效回波间距相匹配、2）利用多回波球面平均技术（MTE-SMT）的白质模型，从双回波 PRIME 数据中估算出高分辨率的扩散弛豫参数；3）利用 Connectome 2.0 扫描仪的高性能梯度，在体内获得 550 um 各向同性分辨率的高保真中尺度 DWI。0 扫描仪。结论：当使用 gSlider 编码时，所提出的 PRIME 序列可在不延长扫描时间的情况下使用额外的回波实现高度加速、高分辨率和无失真 dMRI。
{"title":"PRIME: Phase Reversed Interleaved Multi-Echo acquisition enables highly accelerated distortion-free diffusion MRI","authors":"Yohan Jun, Qiang Liu, Ting Gong, Jaejin Cho, Shohei Fujita, Xingwang Yong, Susie Y Huang, Lipeng Ning, Anastasia Yendiki, Yogesh Rathi, Berkin Bilgic","doi":"arxiv-2409.07375","DOIUrl":"https://doi.org/arxiv-2409.07375","url":null,"abstract":"Purpose: To develop and evaluate a new pulse sequence for highly accelerated\u0000distortion-free diffusion MRI (dMRI) by inserting an additional echo without\u0000prolonging TR, when generalized slice dithered enhanced resolution (gSlider)\u0000radiofrequency encoding is used for volumetric acquisition. Methods: A\u0000phase-reversed interleaved multi-echo acquisition (PRIME) was developed for\u0000rapid, high-resolution, and distortion-free dMRI, which includes two echoes\u0000where the first echo is for target diffusion-weighted imaging (DWI) acquisition\u0000with high-resolution and the second echo is acquired with either 1)\u0000lower-resolution for high-fidelity field map estimation, or 2) matching\u0000resolution to enable efficient diffusion relaxometry acquisitions. The sequence\u0000was evaluated on in vivo data acquired from healthy volunteers on clinical and\u0000Connectome 2.0 scanners. Results: In vivo experiments demonstrated that 1) high\u0000in-plane acceleration (Rin-plane of 5-fold with 2D partial Fourier) was\u0000achieved using the high-fidelity field maps estimated from the second echo,\u0000which was made at a lower resolution/acceleration to increase its SNR while\u0000matching the effective echo spacing of the first readout, 2) high-resolution\u0000diffusion relaxometry parameters were estimated from dual-echo PRIME data using\u0000a white matter model of multi-TE spherical mean technique (MTE-SMT), and 3)\u0000high-fidelity mesoscale DWI at 550 um isotropic resolution could be obtained in\u0000vivo by capitalizing on the high-performance gradients of the Connectome 2.0\u0000scanner. Conclusion: The proposed PRIME sequence enabled highly accelerated,\u0000high-resolution, and distortion-free dMRI using an additional echo without\u0000prolonging scan time when gSlider encoding is utilized.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abdullah Alharthi, Ahmed Alqurashi, Turki Alharbi, Mohammed Alammar, Nasser Aldosari, Houssem Bouchekara, Yusuf Shaaban, Mohammad Shoaib Shahriar, Abdulrahman Al Ayidh
The complex nature of disease mechanisms and the variability of patient symptoms present significant obstacles in developing effective diagnostic tools. Although machine learning has made considerable advances in medical diagnosis, its decision-making processes frequently lack transparency, which can jeopardize patient outcomes. This underscores the critical need for Explainable AI (XAI), which not only offers greater clarity but also has the potential to significantly improve patient care. In this literature review, we conduct a detailed analysis of analyzing XAI methods identified through searches across various databases, focusing on chronic conditions such as Parkinson's, stroke, depression, cancer, heart disease, and Alzheimer's disease. The literature search revealed the application of 9 trending XAI algorithms in the field of healthcare and highlighted the pros and cons of each of them. Thus, the article is concluded with a critical appraisal of the challenges and future research opportunities for XAI in human health monitoring.
{"title":"The Role of Explainable AI in Revolutionizing Human Health Monitoring","authors":"Abdullah Alharthi, Ahmed Alqurashi, Turki Alharbi, Mohammed Alammar, Nasser Aldosari, Houssem Bouchekara, Yusuf Shaaban, Mohammad Shoaib Shahriar, Abdulrahman Al Ayidh","doi":"arxiv-2409.07347","DOIUrl":"https://doi.org/arxiv-2409.07347","url":null,"abstract":"The complex nature of disease mechanisms and the variability of patient\u0000symptoms present significant obstacles in developing effective diagnostic\u0000tools. Although machine learning has made considerable advances in medical\u0000diagnosis, its decision-making processes frequently lack transparency, which\u0000can jeopardize patient outcomes. This underscores the critical need for\u0000Explainable AI (XAI), which not only offers greater clarity but also has the\u0000potential to significantly improve patient care. In this literature review, we\u0000conduct a detailed analysis of analyzing XAI methods identified through\u0000searches across various databases, focusing on chronic conditions such as\u0000Parkinson's, stroke, depression, cancer, heart disease, and Alzheimer's\u0000disease. The literature search revealed the application of 9 trending XAI\u0000algorithms in the field of healthcare and highlighted the pros and cons of each\u0000of them. Thus, the article is concluded with a critical appraisal of the\u0000challenges and future research opportunities for XAI in human health\u0000monitoring.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142175955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：