Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208017
H. Yen, Van‐Phuc Hoang, Quang-Kien Trinh, Van-Sang Doan, G. Sun
Sleep apnea syndrome is a prevalent condition among the elderly people that is potentially dangerous and causes fatal complications. However, this syndrome is often undiagnosed since most patients do not know they have this condition because it only occurs during sleep. In this study, we proposed a non-contact sleep monitoring solution. The system used the support vector machines (SVM) model with three classes classification. The monitoring results give the ratios of three time durations, including the normal sleeping time, body movement time, and time of cessation of breathing. The training model obtained an accuracy of 96.1%, and the model was applied to a patient with apnea syndrome in Yokohama Hospital, Japan, showing consistency with the hospital recordings.
{"title":"Sleep Apnea Patient Monitoring Using Continuous-wave Radar","authors":"H. Yen, Van‐Phuc Hoang, Quang-Kien Trinh, Van-Sang Doan, G. Sun","doi":"10.1109/SSP53291.2023.10208017","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208017","url":null,"abstract":"Sleep apnea syndrome is a prevalent condition among the elderly people that is potentially dangerous and causes fatal complications. However, this syndrome is often undiagnosed since most patients do not know they have this condition because it only occurs during sleep. In this study, we proposed a non-contact sleep monitoring solution. The system used the support vector machines (SVM) model with three classes classification. The monitoring results give the ratios of three time durations, including the normal sleeping time, body movement time, and time of cessation of breathing. The training model obtained an accuracy of 96.1%, and the model was applied to a patient with apnea syndrome in Yokohama Hospital, Japan, showing consistency with the hospital recordings.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124840598","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208044
N. Duong, Q. Nguyen, K. Ngo, Thai-Mai Dinh-Thi
In this paper, we introduce a novel estimation method for the downlink millimeter-wave (mmWave) multiple-input multiple-output (MIMO) channel. The proposed method is able to determine the angles, time delays, and gains of the multi-path components by using the spatially sparse nature of mmWave channels. We first use on-grid sparse Bayesian learning (SBL) to coarsely estimate the channel parameters in the beamspace domain. We then develop a refinement method based on Newton–Raphson and Least Square-based atomic tuning to generate a mismatch-free basis. Finally, we finely reconstruct the channel by SBL using the basis found in the previous step. Simulation results show that the proposed channel estimation method outperforms the traditional ones in terms of mean square error and algorithmic complexity.
{"title":"Sparse Bayesian Learning with Atom Refinement for mmWave MIMO Channel Estimation","authors":"N. Duong, Q. Nguyen, K. Ngo, Thai-Mai Dinh-Thi","doi":"10.1109/SSP53291.2023.10208044","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208044","url":null,"abstract":"In this paper, we introduce a novel estimation method for the downlink millimeter-wave (mmWave) multiple-input multiple-output (MIMO) channel. The proposed method is able to determine the angles, time delays, and gains of the multi-path components by using the spatially sparse nature of mmWave channels. We first use on-grid sparse Bayesian learning (SBL) to coarsely estimate the channel parameters in the beamspace domain. We then develop a refinement method based on Newton–Raphson and Least Square-based atomic tuning to generate a mismatch-free basis. Finally, we finely reconstruct the channel by SBL using the basis found in the previous step. Simulation results show that the proposed channel estimation method outperforms the traditional ones in terms of mean square error and algorithmic complexity.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125119586","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208084
Bui Tien Anh, Do Thanh Quan, Dung Duong Quoc, Pham Thanh Hiep
Wireless body area networks (WBANs) have recently become a topic of interest due to their large number of applications and the rapid development of individual gadgets and devices for medical purposes. The model in this study, called a "cell-free WBANs" scheme, is developed on the basis of a cell-free multiple-input multiple-output (MIMO) system where a lot of access points (APs) serve a number of sensors simultaneously. A new system model where the sensors are distributed around the body and communicate directly with APs rather than through a coordinator is proposed. The interference due to simultaneous signal transmission from multiple sensors is taken into consideration, and the transmission power control algorithm for uplink data is developed to enhance the spectrum efficiency of the system. According to simulation results, in all considered scenarios, the proposed system’s performance is considerably improved in comparison with the small-cell model.
{"title":"Optimizing Transmission Power for Uplink Data in Cell-Free Wireless Body Area Networks","authors":"Bui Tien Anh, Do Thanh Quan, Dung Duong Quoc, Pham Thanh Hiep","doi":"10.1109/SSP53291.2023.10208084","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208084","url":null,"abstract":"Wireless body area networks (WBANs) have recently become a topic of interest due to their large number of applications and the rapid development of individual gadgets and devices for medical purposes. The model in this study, called a \"cell-free WBANs\" scheme, is developed on the basis of a cell-free multiple-input multiple-output (MIMO) system where a lot of access points (APs) serve a number of sensors simultaneously. A new system model where the sensors are distributed around the body and communicate directly with APs rather than through a coordinator is proposed. The interference due to simultaneous signal transmission from multiple sensors is taken into consideration, and the transmission power control algorithm for uplink data is developed to enhance the spectrum efficiency of the system. According to simulation results, in all considered scenarios, the proposed system’s performance is considerably improved in comparison with the small-cell model.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129411690","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208027
Y. Rong, Matthew Fynn, S. Nordholm, Serena Siaw, G. Dwivedi
In this paper, we present a new wearable multichannel phonocardiography (PCG) and electrocardiography (ECG) device for cardiovascular disease (CVD) pre-screening and monitoring developed recently by researchers at Curtin University in collaboration with Ticking Heart, a health-tech start-up. An iterative Wiener filter based noise cancelation algorithm is proposed to improve the integrity of heart sound signals. We show that compared with an existing approach, the proposed algorithm has a better performance in suppressing the noise at 200-300 Hz. A convolutional neural network based classifier is implemented which exploits both the ECG and PCG signals to improve the pre-screening accuracy of CVD.
{"title":"Wearable Electro-Phonocardiography Device for Cardiovascular Disease Monitoring","authors":"Y. Rong, Matthew Fynn, S. Nordholm, Serena Siaw, G. Dwivedi","doi":"10.1109/SSP53291.2023.10208027","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208027","url":null,"abstract":"In this paper, we present a new wearable multichannel phonocardiography (PCG) and electrocardiography (ECG) device for cardiovascular disease (CVD) pre-screening and monitoring developed recently by researchers at Curtin University in collaboration with Ticking Heart, a health-tech start-up. An iterative Wiener filter based noise cancelation algorithm is proposed to improve the integrity of heart sound signals. We show that compared with an existing approach, the proposed algorithm has a better performance in suppressing the noise at 200-300 Hz. A convolutional neural network based classifier is implemented which exploits both the ECG and PCG signals to improve the pre-screening accuracy of CVD.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123254319","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10207980
Thai-Hoc Vu, K. Nguyen, Viet Quoc Pham, Thien Huynh-The, D. B. D. Costa, Vo Nguyen Quoc Bao, Sunghwan Kim
This paper investigates the performance of indoor terahertz (THz)-aided non-orthogonal multiple access (NOMA) systems in the context of spherical stochastic distances in downlink channel models. With the aim of improving system performance gains, a novel user pairing scheme subject to power control criterion is proposed to adaptively change with regard to the users’ location acquisition and signal’s transmit power. Then, we derive exact closed-form expressions for the user’s outage probability (OP) in order to gain some engineering insights, i.e., key parameters affecting the system performance trend. Monte Carlo simulation is presented to corroborate the accuracy of the theoretical analysis as well as demonstrate the effectiveness of the proposed user-pairing approach.
{"title":"Outage Performance of THz-aided NOMA Systems with Spherical Stochastic Model","authors":"Thai-Hoc Vu, K. Nguyen, Viet Quoc Pham, Thien Huynh-The, D. B. D. Costa, Vo Nguyen Quoc Bao, Sunghwan Kim","doi":"10.1109/SSP53291.2023.10207980","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10207980","url":null,"abstract":"This paper investigates the performance of indoor terahertz (THz)-aided non-orthogonal multiple access (NOMA) systems in the context of spherical stochastic distances in downlink channel models. With the aim of improving system performance gains, a novel user pairing scheme subject to power control criterion is proposed to adaptively change with regard to the users’ location acquisition and signal’s transmit power. Then, we derive exact closed-form expressions for the user’s outage probability (OP) in order to gain some engineering insights, i.e., key parameters affecting the system performance trend. Monte Carlo simulation is presented to corroborate the accuracy of the theoretical analysis as well as demonstrate the effectiveness of the proposed user-pairing approach.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132626253","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10207953
Wenfu Xia, Ziping Zhao, Ying Sun
Covariance matrix estimation is a fundamental task in many fields related to data analysis. As the dimension of the covariance matrix becomes large, it is desirable to obtain a sparse estimator and an efficient algorithm to compute it. In this paper, we consider the covariance matrix estimation problem by minimizing a Gaussian negative log-likelihood loss function with an ℓ1 penalty, which is a constrained non-convex optimization problem. We propose to solve the covariance estimator via a simple iterative shrinkage-thresholding algorithm (C-ISTA) with provable convergence. Numerical simulations with comparison to the benchmark methods demonstrate the computational efficiency and good estimation performance of C-ISTA.
{"title":"C-ISTA: Iterative Shrinkage-Thresholding Algorithm for Sparse Covariance Matrix Estimation","authors":"Wenfu Xia, Ziping Zhao, Ying Sun","doi":"10.1109/SSP53291.2023.10207953","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10207953","url":null,"abstract":"Covariance matrix estimation is a fundamental task in many fields related to data analysis. As the dimension of the covariance matrix becomes large, it is desirable to obtain a sparse estimator and an efficient algorithm to compute it. In this paper, we consider the covariance matrix estimation problem by minimizing a Gaussian negative log-likelihood loss function with an ℓ1 penalty, which is a constrained non-convex optimization problem. We propose to solve the covariance estimator via a simple iterative shrinkage-thresholding algorithm (C-ISTA) with provable convergence. Numerical simulations with comparison to the benchmark methods demonstrate the computational efficiency and good estimation performance of C-ISTA.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132340311","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208028
Khirakorn Thipprachak, P. Tangamchit, S. Lerspalungsanti
A reliable fall detection system can enhance the safety of senior citizens by detecting falls in private areas, such as restrooms, where accidents may go unnoticed. This study aimed to create a static human posture recognition system with a possibility of extension for detecting falls in private areas. The system used ultra-wideband (UWB) sensors to detect human body gestures and analyze an individual's posture to determine a laydown posture, which is abnormal in restroom usage. UWB is capable of protecting human privacy because its output contains limited information. This study implemented a convolutional neural network (CNN) model that classified signals from an ultra-wideband sensor in a bathroom into four categories: standing, sitting, lying down, and nobody. This paper proposes a CNN classifier with an overall accuracy of 93%. These results demonstrate the capability of the proposed system to recognize static human posture in private locations.
{"title":"A Convolutional Neural Network Model for Privacy-Sensitive Ultra-Wideband Radar-Based Human Static Posture Classification and Fall Detection","authors":"Khirakorn Thipprachak, P. Tangamchit, S. Lerspalungsanti","doi":"10.1109/SSP53291.2023.10208028","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208028","url":null,"abstract":"A reliable fall detection system can enhance the safety of senior citizens by detecting falls in private areas, such as restrooms, where accidents may go unnoticed. This study aimed to create a static human posture recognition system with a possibility of extension for detecting falls in private areas. The system used ultra-wideband (UWB) sensors to detect human body gestures and analyze an individual's posture to determine a laydown posture, which is abnormal in restroom usage. UWB is capable of protecting human privacy because its output contains limited information. This study implemented a convolutional neural network (CNN) model that classified signals from an ultra-wideband sensor in a bathroom into four categories: standing, sitting, lying down, and nobody. This paper proposes a CNN classifier with an overall accuracy of 93%. These results demonstrate the capability of the proposed system to recognize static human posture in private locations.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131617432","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208031
T. Vu, Sovit Bhandari, M. Minardi, Van-Dinh Nguyen, S. Chatzinotas
The advanced payload technology has opened up a new way to design future NGSO satellite systems exploiting the full flexibility in radio resource and beam coverage management. Conventional spatial multiplexing techniques, which require the CSI, however, cannot be efficiently applied in NGSO due to long round-trip time(RTT). In this paper, we tackle the long RTT in the precoding design by proposing a joint channel prediction and dynamic radio resource management framework. Our aim is to optimize the bandwidth and transmit power in every spot beam based on the predicted channel gains to maximize the system capacity. Since the satellite’s orbit is time-varying but predictable, Kalman filter-based channel estimation method is employed. Given the predicted channels, a joint bandwidth allocation and precoding design is formulated. The effectiveness of the proposed framework is demonstrated via practical satellite channel models using the STK software and 3GPP codebook- and non-codebook-based precoding designs.
{"title":"3GPP New Radio Precoding in NGSO Satellites: Channel Prediction and Dynamic Resource Allocation","authors":"T. Vu, Sovit Bhandari, M. Minardi, Van-Dinh Nguyen, S. Chatzinotas","doi":"10.1109/SSP53291.2023.10208031","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208031","url":null,"abstract":"The advanced payload technology has opened up a new way to design future NGSO satellite systems exploiting the full flexibility in radio resource and beam coverage management. Conventional spatial multiplexing techniques, which require the CSI, however, cannot be efficiently applied in NGSO due to long round-trip time(RTT). In this paper, we tackle the long RTT in the precoding design by proposing a joint channel prediction and dynamic radio resource management framework. Our aim is to optimize the bandwidth and transmit power in every spot beam based on the predicted channel gains to maximize the system capacity. Since the satellite’s orbit is time-varying but predictable, Kalman filter-based channel estimation method is employed. Given the predicted channels, a joint bandwidth allocation and precoding design is formulated. The effectiveness of the proposed framework is demonstrated via practical satellite channel models using the STK software and 3GPP codebook- and non-codebook-based precoding designs.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114859411","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208045
Tung X. Hoang, T. X. Ngo, Hieu D. T. Phan, H. Pham, Tuan H. Nguyen, T. T. N. Nguyen
Fine particulate matter (PM2.5) pollution is a serious problem in Vietnam, especially in mega-cities such as Hanoi or Ho Chi Minh City. High levels of PM2.5 concentration have negative impacts on public health even if the exposure is short-term. New advancements in satellite observations can capture a lot of detailed information on air quality. Via proper processing methods, those satellite observations can produce high quality PM2.5 concentration maps that facilitates PM2.5 impact assessment and mitigation measures at national and local scales. In this paper, we present an application service, called Pollution Observation Platform on GIS, or POPGIS, that collects inputs from multiple satellite data sources and applies new research techniques in satellite-based PM2.5 concentration estimation and presents near real-time results to users. The system is also designed for data sharing and can be used for analysis and re-evaluation of PM2.5 distribution maps.
{"title":"POPGIS – An Application Service for Air Pollution Management and Analysis in Vietnam","authors":"Tung X. Hoang, T. X. Ngo, Hieu D. T. Phan, H. Pham, Tuan H. Nguyen, T. T. N. Nguyen","doi":"10.1109/SSP53291.2023.10208045","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208045","url":null,"abstract":"Fine particulate matter (PM2.5) pollution is a serious problem in Vietnam, especially in mega-cities such as Hanoi or Ho Chi Minh City. High levels of PM2.5 concentration have negative impacts on public health even if the exposure is short-term. New advancements in satellite observations can capture a lot of detailed information on air quality. Via proper processing methods, those satellite observations can produce high quality PM2.5 concentration maps that facilitates PM2.5 impact assessment and mitigation measures at national and local scales. In this paper, we present an application service, called Pollution Observation Platform on GIS, or POPGIS, that collects inputs from multiple satellite data sources and applies new research techniques in satellite-based PM2.5 concentration estimation and presents near real-time results to users. The system is also designed for data sharing and can be used for analysis and re-evaluation of PM2.5 distribution maps.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115901620","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10207958
Byung-Kwan Lim, Mai H. Vu
We propose a graph neural network (GNN) architecture to optimize base station (BS) beamforming and reconfigurable intelligent surface (RIS) phase shifts in a multi-RIS assisted wireless network. We create a bipartite graph model to represent a network with multi-RIS, then construct the GNN architecture by exploiting channel information as node and edge features. We employ a message passing mechanism to enable information exchange between RIS nodes and user nodes and facilitate the inference of interference. Each node also maintains a representation vector which can be mapped to the BS beamforming or RIS phase shifts output. Message generation and update of the representation vector at each node are performed using two unsupervised neural networks, which are trained offline and then used on all nodes of the same type. Simulation results demonstrate that the proposed GNN architecture provides strong scalability with network size, generalizes to different settings, and significantly outperforms conventional algorithms.
{"title":"Graph Neural Network Based Beamforming and RIS Reflection Design in A Multi-RIS Assisted Wireless Network","authors":"Byung-Kwan Lim, Mai H. Vu","doi":"10.1109/SSP53291.2023.10207958","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10207958","url":null,"abstract":"We propose a graph neural network (GNN) architecture to optimize base station (BS) beamforming and reconfigurable intelligent surface (RIS) phase shifts in a multi-RIS assisted wireless network. We create a bipartite graph model to represent a network with multi-RIS, then construct the GNN architecture by exploiting channel information as node and edge features. We employ a message passing mechanism to enable information exchange between RIS nodes and user nodes and facilitate the inference of interference. Each node also maintains a representation vector which can be mapped to the BS beamforming or RIS phase shifts output. Message generation and update of the representation vector at each node are performed using two unsupervised neural networks, which are trained offline and then used on all nodes of the same type. Simulation results demonstrate that the proposed GNN architecture provides strong scalability with network size, generalizes to different settings, and significantly outperforms conventional algorithms.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116608687","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：