Prof. Gang Wu
University of Electronic Science and Technology of China
Experience: Gang Wu, Professor of UESTC, PhD supervisor, IEEE Chengdu Chapter, received his PhD degree in Communication and Information Systems from UST in June 2004. From September 2009 to September 2010, he was a visiting scholar at the Georgia Institute of Science and Technology. He has presided over 1 national 863 project, 1 national natural science foundation project, 2 national science and technology major special projects, 2 national 863 projects, 2 national 973 projects, 2 international science and technology cooperation projects, and 3 other national research projects as the second person in charge. He has published more than 20 SCI papers, applied for 12 invention patents, and co-authored "Modern Wireless and Mobile Communication Technology" (Science Press, September 2006). He is currently an IEEE Member, an editorial board member of China Science - Information Science, a member of the Special Committee on Information and Communication Testing Technology of the Chinese Society of Communication, and a reviewer for several IEEE journals, and received the 2011 IEEE Communications Letter Exemplary Reviewer Award and the 2012 IEEE Globecom Best Paper Award.
Speech Title: Distributed Two-tier Deep Reinforcements Learning Framework for Cell-Free Network
Abstract: Intelligent wireless networks have long been expected to have self-configuration and self-optimization capabilities to adapt to various environments and demands. In this talk, we present a novel distributed hierarchical deep reinforcement learning (DHDRL) framework with two-tier control networks in different timescales to optimize the long-term spectrum efficiency (SE) of the downlink cell-free multiple-input single-output (MISO) network, consisting of multiple distributed access points (AP) and user terminals (UT). To realize the proposed two-tier control strategy, we decompose the optimization problem into two subproblems, AP-UT association (AUA) as well as beamforming and power allocation (BPA), resulting in a Markov decision process (MDP) and Partially Observable MDP (POMDP). The proposed method consists of two neural networks. At the system level, a distributed high-level neural network is introduced to optimize wireless network structure on a large timescale. While at the link level, a distributed low-level neural network is proposed to mitigate inter-AP interference and improve the transmission performance on a small timescale. Numerical results show that our method is effective for high-dimensional problems, in terms of spectrum efficiency, signaling overhead as well as satisfaction probability, and generalize well to diverse multi-object problems.
Prof. Tang Liu
Sichuan Normal University,China
Experience: Tang Liu, He received his B.S. degree in Computer Science and Engineering from the University of Electronic Science and Technology in 2003, his M.S. degree in Computer Science from Sichuan University in 2009, and his Ph.D. degree in Computer Science from Sichuan University in 2015. he was a visiting scholar at the University of Louisiana from 2015 to 2016.
He is currently a professor and vice dean of the School of Computer Science, Sichuan Normal University, a master's degree supervisor, a reserve candidate of Sichuan academic and technical leader, a high-level overseas talent of Sichuan Province, a deputy director of Sichuan Key Laboratory of Visual Computing and Virtual Reality (concurrently), a director of the Institute of Mobile Computing and Intelligent Perception of Sichuan Normal University, a member of the Chengdu Branch of the Chinese Computer Society, a member of the Internet of Things of the Chinese Computer Society He is a member of the Executive Committee of the Chinese Computer Society, and a member of the Young Professional Technical Group of the Chinese Institute of Electronics for the Internet of Things. He is currently a member of IEEE Transactions on Mobile Computing (CCF Recommended Class A Journal), ACM Transactions on Sensor Networks (CCF Recommended Class B Journal), Computer Networks (CCF Recommended Class B Journal), IEEE Internet of Things Journal (SCI Zone 1), Journal of Network and Computer Applications (CCF Class C), Computer Communications (CCF Class C), Pervasive and He is also a member of the program committee of HPCC (CCF recommended C conference), MSN (CCF recommended C conference) and other international academic conferences.
Speech Title: The Challenges and Opportunities of Wireless Rechargeable Sensor Networks
Abstract: Recently, the breakthrough of wireless charging technology gave birth to the concept of Wireless Rechargeable Sensor Networks (WRSNs). To achieve high efficiency wireless charging, there are several challenges: how to full use of the energy emitted from the charger; how to trade off the number of dead sensors and the charging efficiency in multi-node charging paradigm; how to transfer energy to mobile devices with non-deterministic mobility. In this talk, we will introduce several charging schemes and discuss the opportunities for the future development of wireless charging.
Prof. Nikolaos M. Freris
University of Science and Technology of China (USTC), China
Experience: Nick Freris is Professor in the School of Computer Science at USTC, and Vice Dean of the International College. He received the Diploma in Electrical and Computer Engineering from the National Technical University of Athens (NTUA), Greece, in 2005, and the M.S. degree in Electrical and Computer Engineering, the M.S. degree in Mathematics, and the Ph.D. degree in Electrical and Computer Engineering all from the University of Illinois at Urbana-Champaign (UIUC) in 2007, 2008, and 2010, respectively.His research lies in AIoT/CPS/IoT: machine learning, distributed optimization, data mining, wireless networks, control, and signal processing, with applications in power systems, sensor networks, transportation, cyber security, and robotics. Dr. Freris has published several papers in high-profile conferences and journals held by IEEE, ACM, and SIAM and holds three patents. His research has been sponsored by the Ministry of Science and Technology of China, Anhui Dept. of Science and Technology, Tencent, and NSF, and was recognized with the USTC Alumni Foundation Innovation Scholar award, the IBM High Value Patent award, two IBM invention achievement awards, and the Gerondelis foundation award. Previously, he was with the faculty of NYU and, before that, he held senior researcher and postdoctoral researcher positions at EPFL and IBM Research, respectively. Dr. Freris is a Senior Member of ACM and IEEE, and a member of CCF and SIAM.
Speech Title: Adaptive Compression of Deep Neural Networks
Abstract: Model compression is crucial for accelerating deep neural networks while maintaining high prediction accuracy. In this talk, I will present a lightweight compression method termed Adaptive SensiTivity-basEd pRuning (ASTER) which dynamically adjusts the filter pruning threshold concurrently with the training process. This is accomplished by computing the sensitivity of the loss to the threshold on the fly (without re-training), as carried with minimal overhead on the Batch Normalization (BN) layers. ASTER then proceeds to adapt the threshold so as to maintain a fine balance between pruning ratio and model accuracy. Extensive experiments on numerous neural networks and benchmark datasets illustrate a state-of-the art trade-off between FLOPs reduction and accuracy, along with formidable computational savings.
Assoc.Prof. IKRAM UD DIN
University of Haripur, Pakistan
Experience: IKRAM UD DIN, Associate Professor, IEEE Senior Member, H-index of 33. In 2016, he received a doctorate in computer science from the School of Computer Science, National University of Malaysia ( UUM ). He also served as the professional chairman of the IEEE UUM Student Association. At present, he is an associate professor in the Department of Information Technology, Haripur University. He has 13 years of teaching, research and management experience in different universities / organizations. His current research interests include traffic measurement and analysis for monitoring quality of service, mobility and cache management in information-centric networks, the Internet of Things, and metaspaces.
Speech Title: Optimizing Crop Yields and Reducing Costs in Precision Agriculture through Metaverse-based Simulation and IoT-enabled Data Analysis
Abstract: Precision agriculture is an emerging field that has the potential to improve crop yields and reduce costs. With the advent of the metaverse, there is growing interest in exploring how precision agriculture can be integrated into virtual environments. We need to have a novel approach for optimizing crop yields and reducing costs using IoT-enabled precision agriculture in the metaverse. The approach should be designed to be scalable, robust, flexible, energy-efficient, reusable, and maintainable. The effectiveness of the approach must be demonstrated through a simulation-based evaluation using real-world data. This will highlight the immense potential of IoT-enabled precision agriculture in the metaverse and provide insights for future research and development in this exciting area.