2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)最新文献

Knowledge-Driven Machine Learning-based Channel Estimation in Massive MIMO System 基于知识驱动机器学习的海量MIMO系统信道估计

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420022

Daofeng Li, Yamei Xu, Ming Zhao, Sihai Zhang, Jinkang Zhu

{"title":"Knowledge-Driven Machine Learning-based Channel Estimation in Massive MIMO System","authors":"Daofeng Li, Yamei Xu, Ming Zhao, Sihai Zhang, Jinkang Zhu","doi":"10.1109/WCNCW49093.2021.9420022","DOIUrl":"https://doi.org/10.1109/WCNCW49093.2021.9420022","url":null,"abstract":"Accurate channel state information is critical for the massive multiple-input multiple-output(MIMO) system. However, due to the fundamental issue of pilot contamination, most existing works have to use additional channel information or complex machine learning network to design channel estimator. In this paper, we propose a knowledge-driven machine learning (KDML)-based channel estimator, which has a simple network structure and low training overhead. Firstly, we analyze the channel estimation problem under both uncorrelated and correlated channel models and convert it into the well-studied image denoising problem. Then, without any prior information about channel, we take advantage of the traditional channel estimation algorithms to construct the knowledge module in KDML, which maps the input data into object space without any training. After that, we use the denoising convolutional neural network (DnCNN) to build the learning module in KDML, where the residual learning accelerates the training process neural network. Finally, we obtain the estimation of the latent noise from the polluted channel matrix and then calculate the output of the proposed channel estimator. Simulation results demonstrate that the proposed channel estimator outperforms the traditional channel estimator in terms of the normalized mean-squared error (NMSE) without any statistical information about the channels. Besides, the proposed estimator also significantly better than the conventional machine learning-based estimator under the same network depth.","PeriodicalId":262379,"journal":{"name":"2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115820747","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}

引用次数: 5

Gossip Learning of Personalized Models for Vehicle Trajectory Prediction 车辆轨迹预测个性化模型的八卦学习

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420038

Mina Aghaei Dinani, A. Holzer, Hung Nguyen, M. Marsan, G. Rizzo

{"title":"Gossip Learning of Personalized Models for Vehicle Trajectory Prediction","authors":"Mina Aghaei Dinani, A. Holzer, Hung Nguyen, M. Marsan, G. Rizzo","doi":"10.1109/WCNCW49093.2021.9420038","DOIUrl":"https://doi.org/10.1109/WCNCW49093.2021.9420038","url":null,"abstract":"Gossip Learning (GL) is a peer-to-peer machine learning protocol based on direct, opportunistic exchange of models among nodes via wireless D2D communications, and on collaborative model training, which has recently proven to scale efficiently to large numbers of nodes, and to offer better privacy guarantees than traditional centralized learning architectures. Existing approaches to GL are however limited to scenarios in which nodes are static, or in which the node connectivity graph is fully connected, and they are fragile to node churn as well as to any change in network configuration. To overcome this limitation, we present a new decentralized architecture for GL suitable for setups with dynamic nodes, which benefits from node mobility instead of being hampered by it. In our approach, nodes improve their personalized model instance by sharing it with neighbors, and by weighting neighbors’ contributions according to an estimate of their marginal utility. We apply our GL algorithm to short-term vehicular trajectory estimation in realistic urban scenarios. We propose a new strategy for the estimation of the neighbors’ instances marginal utility, which yields satisfactory trajectory estimation accuracy for nodes with long enough sojourn times.","PeriodicalId":262379,"journal":{"name":"2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129999558","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}

引用次数: 11

Tradeoff between Model Accuracy and Cost for Federated Learning in the Mobile Edge Computing Systems 移动边缘计算系统中联邦学习模型精度与成本的权衡

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9419985

Xueting Luo, Zhongyuan Zhao, M. Peng

引用次数: 0

Secure Transmission for Intelligent Reflecting Surface-Aided Communication System 智能反射地面辅助通信系统的安全传输

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420018

Yuxin Wei, Li Guo, Chao Dong, Xidong Mu

{"title":"Secure Transmission for Intelligent Reflecting Surface-Aided Communication System","authors":"Yuxin Wei, Li Guo, Chao Dong, Xidong Mu","doi":"10.1109/WCNCW49093.2021.9420018","DOIUrl":"https://doi.org/10.1109/WCNCW49093.2021.9420018","url":null,"abstract":"Intelligent reflecting surface (IRS) is convinced to have a wide range of applications in the future wireless networks by dynamically configuring signal propagation in order to enhance communication performance. In this paper, we focus on the IRS-assisted communication system, where a multiple-antennas base station communicates with a single-antenna receiver in the presence of a single-antenna eavesdropper. The base station can control the phase shifts of the IRS, and further enhance the secrecy rate. Under the assumption that the eavesdropper’s channel statistical information is known, we derive a lower bound of secrecy rate and aim to maximize it. To solve the resulting non-convex optimization problem, an alternating optimization approach is proposed. In particularly, the coordinate descent method (CDM) is invoked in the process of designing the phase shifts at the IRS, which can achieve a similar performance with the semi-definite relaxation (SDR) approach, but requires a lower computational complexity. Simulation results show that our proposed algorithm can improve the secure performance of the considered system, and deploying a 3-bit quantizer at IRS is enough to obtain a good performance as compared to the continuous quantizer.","PeriodicalId":262379,"journal":{"name":"2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129360345","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}

引用次数: 1

On the Analysis and Optimization of BER Performance of Symmetrical Coding Based NOMA 基于NOMA的对称编码误码率分析与优化

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420021

Qiling Gao, Min Jia, Qing Guo, Xuemai Gu

{"title":"On the Analysis and Optimization of BER Performance of Symmetrical Coding Based NOMA","authors":"Qiling Gao, Min Jia, Qing Guo, Xuemai Gu","doi":"10.1109/WCNCW49093.2021.9420021","DOIUrl":"https://doi.org/10.1109/WCNCW49093.2021.9420021","url":null,"abstract":"Non-orthogonal multiple access (NOMA) has been regarded as a promising technique in the future generation wireless communications due to its superior spectral efficiency. However, according to the key conception of NOMA, the distant user (DU) which is far from the base station will be allocated more power than near user (NU) to guarantee fairness. With the utilization of successive interference cancellation (SIC), the signal of NU can be decoded after subtracting the signal of DU, which will deteriorate the performance of NU due to the error bit delivery. In this paper, the analysis and optimization on bit error rate (BER) performance of symmetrical coding (SC) based NOMA (SC-NOMA) scheme is studied under Nakagami-m fading channel. First, closed-form BER expressions of DU and NU are derived simultaneously in SC-NOMA scheme. Second, based on the closed-form expressions, a power allocation algorithm is proposed in SC-NOMA to achieve a better BER performance, and the trade-off between BER performances of NU and DU can be achieved with the proposed algorithm. Finally, simulation results are conducted to verify the validity of analysis. Results show that the proposed SC-NOMA can achieve a better BER performance compared with conventional NOMA.","PeriodicalId":262379,"journal":{"name":"2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127041921","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}

引用次数: 2

Medical Waste Classification System Based on OpenCV and SSD-MobileNet for 5G 基于OpenCV和5G SSD-MobileNet的医疗垃圾分类系统

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420036

Xiaoxiao Bian, Yuchao Chen, Shuyi Wang, Fengyi Cheng, Haotong Cao

{"title":"Medical Waste Classification System Based on OpenCV and SSD-MobileNet for 5G","authors":"Xiaoxiao Bian, Yuchao Chen, Shuyi Wang, Fengyi Cheng, Haotong Cao","doi":"10.1109/WCNCW49093.2021.9420036","DOIUrl":"https://doi.org/10.1109/WCNCW49093.2021.9420036","url":null,"abstract":"In the coming 5G era, the medical waste is mostly sorted manually, and medical staff involved in sorting is at great risk of being infected with virus. To solve this problem, a medical waste automatic identification and classification system is designed, which adopt technology of machine vision and deep learning algorithm. The system firstly detects and locates medical waste by cross-platform computer vision library (Open CV), then applies SSD-Mobile Net model to train and classify medical waste. The existing background subtraction algorithm and SSD-MobileNet model structure are improved. Examples of hemostatic forceps, gloves, infusion bags and syringes are tested. Experimental results show that recognition accuracy of medical waste classification system is more than 98.5%, and average recognition time is 52 milliseconds, and the system has strong robustness. The application of the proposed method in actual medical waste classification is of great significance in reducing manual input and reducing the risk of virus infection for medical personnel involved in sorting.","PeriodicalId":262379,"journal":{"name":"2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129245607","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}

引用次数: 5

Distributed Tracking Stopping Time Using Average Consensus 使用平均共识的分布式跟踪停止时间

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420035

Jia Ye, Yinfei Xu

引用次数: 0

Rate-Splitting and NOMA-Enabled Uplink User Cooperation 速率拆分和支持noma的上行用户协同

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9419994

Omid Abbasi, H. Yanikomeroglu

引用次数: 9

CFN-dyncast: Load Balancing the Edges via the Network CFN-dyncast:通过网络进行边负载均衡

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420028

Bing Liu, Jianwei Mao, Ling Xu, Ruizhao Hu, Xia Chen

引用次数: 6

Content-driven Joint Resource Allocation Based on Vehicle-edge Synergy in Vehicular Networks 基于车边协同的车联网内容驱动联合资源分配

2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW) Pub Date : 2021-03-29 DOI: 10.1109/WCNCW49093.2021.9420007

Xu Zhu, Fangfang Liu, Zhimin Zeng, Caili Guo, Jiujiu Chen

{"title":"Content-driven Joint Resource Allocation Based on Vehicle-edge Synergy in Vehicular Networks","authors":"Xu Zhu, Fangfang Liu, Zhimin Zeng, Caili Guo, Jiujiu Chen","doi":"10.1109/WCNCW49093.2021.9420007","DOIUrl":"https://doi.org/10.1109/WCNCW49093.2021.9420007","url":null,"abstract":"With the rapid growth of computer vision applications, a large amount of video data in vehicular networks are used for content analysis. As a representative technology in the field of artificial intelligence, deep learning has been widely used in video content understanding. However, deep learning models are usually accompanied by huge amount of calculation, which put great pressure on traditional wireless communication resource and Mobile Edge Computing (MEC) server. To solve this problem, in this paper, we first propose a DNN model segmentation strategy, and then propose a content-driven joint resource allocation scheme based on vehicle-edge synergy to maximize the accuracy of video content understanding under the constraints of communication and computing resources. Due to the real-time nature of resource allocation and the variability of the environment in vehicular networks, we design a Multi-agent Distributed Q-Learning algorithm to solve such multi-constrained nonlinear programming problems. Finally, the simulation results show that our proposed vehicle-edge synergy based joint resource allocation scheme has better video content understanding performance and system delay.","PeriodicalId":262379,"journal":{"name":"2021 IEEE Wireless Communications and Networking Conference Workshops (WCNCW)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115562586","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}

引用次数: 1