报告主题：Deep Learning Empowered Fundamental Design for Intelligent Reflecting Surface-Assisted Wireless Communications（刘畅）
报告摘要：Recently, intelligent reflecting surfaces (IRSs) have been proposed as a promising technology for the upcoming sixth-generation (6G) wireless networks. Channel estimation (CE) is one of the main tasks in realizing IRS-assisted systems. However, the unique cascaded channel characteristics and large numbers of reflecting elements of IRSs bring problems of limited CE accuracy and large CE overhead, which makes the implementation of IRSs more challenging. In this talk, we will exploit a deep learning (DL) approach to rethink the fundamental design of IRSs, developing two novel DL-based frameworks, i.e., deep residual learning (DReL)-based channel estimation and location-aware predictive beamforming, to improve the practicability of IRSs. In the first framework, we model the CE as a denoising problem and adopt a DReL approach to further improve the CE accuracy. To reduce the CE overhead, we adopt a DL approach to implicitly learn the historical channel features and directly predict the IRS phase shifts for the next time slot to maximize the average achievable sum-rate of the IRS-assisted wireless system. Finally, simulation results demonstrate the performance gains brought by the developed learning-based methods and draw useful insights.
Dr. Chang Liu received the Ph.D. degree in signal and information processing from Dalian University of Technology, China, in 2017 and was a joint Ph.D. (supervised by Prof. Husheng Li) from the University of Tennessee, USA. He is currently a Research Fellow (supervised by Prof. Derrick Wing Kwan Ng) with the University of New South Wales, Sydney, Australia. He was a postdoctoral research fellow (supervised by Prof. Ying-Chang Liang) with the University of Electronic Science and Technology of China. To date, he has published more than 40 journal and conference papers which have been cited over 470 times in Google Scholar with an h-index of 13 and 4 journal papers were listed among the top 50 popular papers ranked by IEEE Xplore. He serves as a Lead Guest Editor of Future Internet and a foundation member of IEEE Comsoc special interest group on orthogonal time frequency space. His research interests include machine learning for communications, integrated sensing and communication (ISAC), orthogonal time frequency space (OTFS), intelligent reflecting surface (IRS)-assisted communications, unmanned aerial vehicle (UAV) communications, Internet of Things (IoT), and cognitive radio.
报告主题：SWIPT-based IoT Networks: Opportunities and Challenges（唐杰）
报告摘要：Establishing a sustainable Internet of Things (IoT) framework is of critical importance for emergency communication systems. However, sensor nodes, being the core of the IoT, are facing severe energy endurance challenge. Due to the high density and wide coverage of sensor nodes, the traditional energy supply methods may cause huge manpower and material resources. It is known that the radio frequency (RF) signals are the carriers of both information and energy, which makes it possible to combine wireless power transfer (WPT) and wireless information transmission (WIT) in wireless communication systems. Motivated by this, an advanced technology named simultaneous wireless information and power transfer (SWIPT) has emerged recently, aiming to prolong the battery-life of devices by achieving the parallel transmission of information and energy. Considering the inherent characteristics and requirements of IoT-enabled emergency communication systems, this talk introduces SWIPT strategies from two levels, the algorithm and the system, in order to solve the theoretical problems of the energy efficiency restriction caused by the interference energy waste under power constraints conditions.
Jie Tang (S’10–M’13-SM’18) is a professor at the School of Electronic and Information Engineering, South China University of Technology, China. His research interests include SWIPT, UAV communications, NOMA, RIS. He is currently serving as an Editor for IEEE WIRELESS COMMUNICATIONS LETTERS, IEEE SYSTEMS JOURNAL, and EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING. He is the Guest Editor for two special issues in IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING, and one special issue in IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY. He also served as a Track Co-Chair of IEEE VTC-Spring 2018 and 2022, Symposium Co-Chair of IEEE/CIC ICCC 2020, IEEE ComComAp 2019, TPC Co-Chair of EAI GreeNets 2019, and Workshop Co-Chair of IEEE ICCC/CIC 2019. He received the IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award in 2021. Also, he was the co-recipient of Best Paper Awards at the ICNC 2018, CSPS 2018, WCSP 2019, 6GN 2020 and AICON2021. He is the current Vice Chair of the Special Interest Group on Green Cellular Networks within the IEEE ComSoc Green Communications and Computing Technical Committee.
报告主题：Mobile Crowd Sensing Based on V2X Networks（王朝炜）
报告摘要：With the development of smart city, the primary goal is to solve problems that are closely related to people's life, such as traffic congestion and environmental pollution. Substantial urban environmental information is needed to provide data support for intelligent solutions. Therefore, collecting urban environmental information has become the basis of building a "smart city". To manage and control the development of city effectively, Mobile Crowd Sensing (MCS) technology can help a lot. MCS based on V2X has the advantages of high mobility, flexible deployment, low operating cost and a wide range of applications. MCS can effectively collect, upload and process sensing data. However, how to make good use of urban vehicles to realize the effective coverage of smart cities is an urgent problem to be solved. In this talk, the presenter is going to introduce the key techniques such as coverage enhancement, task scheduling, energy efficiency promotion of MCS.
Dr. Chaowei Wang is with the School of EE, Beijing University of Posts & Telecomm. since Jul. 2010. He was with the Visiting Scholar of University of California, Irvine, CA and Queen Mary University of London. UK. He received BSc and Ph.D. degrees in the School of ICE, Beijing University of Posts & Telecomm. in 2004 and 2010, respectively. He authored about 80 journal/conference papers (IEEE JSAC, China Science, 2014 IEEE WCNC Best Paper Award, etc.) and 2 books (in Chinese). He’s holding 15 invention patents (13 Chinese patents and 2 US patents). He was granted the Beijing Talents Foundation in 2017. Dr. Wang was TPC member/session chair for several flagship conferences: IEEE VTC, WCNC, Globecom and ICC. He’s currently the AE of Frontiers in Computer Science and reviewers of IEEE TVT, JSAC, TGCN, TITS, TCOM and TII.
报告主题：Goal-Oriented Semantic Communications（杨照辉）
报告摘要：Future wireless communication requires high data rate and massive connection for emerging applications such as Internet of things (IoT). In particular, in human-computer interaction scenarios, humans may simultaneously control multiple IoT devices using speech command, thus making audio communication pervasive in a small-range wireless network. However, a spectrum resource-constrained network may not be able to support the broad and prolonged wireless audio communication. This, in turn, motivates the development of semantic communication technique that allows devices to only transmit small amounts of semantic information. Semantic communication aims at minimizing the difference between the meanings of the transmitted messages and that of the recovered messages, rather than the recovered symbols. Using semantic communication technique, one can reduce the communication overheads. In this talk, I will talk about the research about goal-oriented semantic communication, including audio semantic communication, semantic communication with distributed implementation, and a compute-then-transmit framework for semantic communication.
Zhaohui Yang received the B.S. degree in information science and engineering from Chien-Shiung Wu Honors College, Southeast University, Nanjing, China, in June 2014, and the Ph.D. degree in communication and information system with the National Mobile Communications Research Laboratory, Southeast University, Nanjing, China, in May 2018. From May 2018 to October 2020, he was a postdoctoral research associate with the Center for Telecommunications Research, Department of Informatics, King's College London, UK. He is currently a visiting associate professor with College of Information Science and Electronic Engineering Zhejiang Key Lab of Information Processing Communication and Networking, Zhejiang University, and also a research fellow with the Department of Electronic and Electrical Engineering, University College London, UK. He is an Associate Editor for the IEEE Communications Letters, IET Communications and EURASIP Journal on Wireless Communications and Networking. He has guest edited a feature topic of IEEE Communications Magazine on Communication Technologies for Efficient Edge Learning. He was a Co-Chair for workshops on edge learning and wireless communications in several conferences including the IEEE International Conference on Communications (ICC), the IEEE Global Telecommunication Conference (GLOBECOM), the IEEE Wireless Communications and Networking Conference (WCNC), and the IEEE International Symposium on Personal, Indoor and Mobile Radio Communication (PIMRC). His research interests include federated learning, reconfigurable intelligent surface, UAV, and NOMA. He was a TPC member of IEEE ICC during 2015-2021 and GLOBECOM during 2017-2021. He was an exemplary reviewer for IEEE Transactions on Communications in 2019 and 2020.
刘韬，四川大学博士，西南交通大学博士后, 美国哥伦比亚大学访问学者,第十一批四川省学术和技术带头人后备人选,目前就职于西南民族大学计算机科学与工程学院。长期从事无线传感器网络的研究。主持国家自然科学基金面上项目一项和省部级项目3项，主研国家自然科学基金2项,在《IEEE Trans. On Wireless Communications》、《IEEE Trans. On Communications》和《电子学报》、《通信学报》等国内外期刊发表学术论文40余篇。