Speakers

Prof. Guan Gui, Nanjing University of Posts and Telecommunications, China

IEEE Fellow, IET Fellow, AAIA Fellow

Guan Gui (Fellow, IEEE) received the Ph.D. degree from the University of Electronic Science and Technology of China, Chengdu, China, in 2012. From 2009 to 2014, he joined Tohoku University as a Research Assistant and a Post-Doctoral Research Fellow. From 2014 to 2015, he was an Assistant Professor with Akita Prefectural University, Akita, Japan. Since 2015, he has been a Professor with the Nanjing University of Posts and Telecommunications, Nanjing, China. He has published more than 200 IEEE journals/conference papers. His recent research interests include intelligence sensing and recognition, intelligent signal processing, and physical layer security. Dr. Gui contributions to intelligent signal analysis and wireless resource optimization have earned him the title of fellow of the IEEE, IET, AAIA, and ACIS. He was a recipient of several Best Paper Awards, such as ICC 2017, ICC 2014, and VTC 2014-Spring. He received the IEEE Communications Society Heinrich Hertz Award in 2021, top 2% scientists of the world by Stanford University from 2021 to 2024, the Clarivate Analytics Highly Cited Researcher in Cross-Field from 2021 to 2023, the Highly Cited Chinese Researchers by Elsevier from 2020 to 2023, a member and Global Activities Contributions Award in 2018, the Top Editor Award of IEEE Transactions on Vehicular Technology in 2019, the Outstanding Journal Service Award of KSII Transactions on Internet and Information System in 2020, the Exemplary Reviewer Award of IEEE Communications Letters in 2017, the 2012 Japan Society for Promotion of Science (JSPS) Postdoctoral Fellowships for Foreign Researchers, and the 2018 Japan Society for Promotion of Science (JSPS) International Fellowships for Overseas Researchers. He was also selected as the Jiangsu Specially-Appointed Professor in 2016, the Jiangsu High-Level Innovation and Entrepreneurial Talent in 2016, and the Jiangsu Six Top Talent in 2018. Since 2022, he has been a Distinguished Lecturer of the IEEE Vehicular Technology Society. He is serving or served on the editorial boards of several journals, including IEEE Transactions on Vehicular Technology, IEICE Transactions on Communications, Physical Communication, Wireless Networks, IEEE Access, Journal of Circuits, Systems and Computers, Security and Communication Networks, IEICE Communications Express, and KSII Transactions on Internet and Information Systems, and Journal on Communications. In addition, he served as the IEEE VTS Ad Hoc Committee Member in AI Wireless; the Executive Chair of IEEE ICCT 2023; the Workshop Chair of LANTINCOM2023; the TPC Chair of PRAI 2022, ICGIP 2022, PHM 2021, and WiMob 2020; the Executive Chair of VTC 2021-Fall; the Vice Chair of WCNC 2021; the Symposium Chair of WCSP 2021; the General Co-Chair of Mobimedia 2020; the Track Chairs of EuCNC 2021 and 2022, and VTC 2020 Spring; the Award Chair of PIMRC 2019; and a TPC Member of many IEEE international conferences, such as GLOBECOM, ICC, WCNC, PIRMC, VTC, and SPAWC.

Title: Intelligent Signal Sensing and Recognition Towards Physical Security

Abstract:

The advent of 6G wireless communication marks a transformative era defined by pervasive sensing and advanced intelligent identification, both of which are crucial for ensuring physical security. This keynote speech emphasizes the integration of Artificial Intelligence (AI) and Deep Learning (DL) as pivotal solutions for addressing the dynamic and complex challenges presented by 6G networks. We highlight the role of AI in revolutionizing signal sensing and recognition, focusing on the application of neural networks to enhance signal detection, classification, and Specific Emitter Identification (SEI). By employing gradient-based optimization techniques, we demonstrate how Artificial Neural Networks (ANNs) can optimize model and algorithm parameters, facilitating a data-driven approach that surpasses traditional rule-based systems. This advancement is essential in the physical layer of wireless communications, where intelligent signal recognition is vital for maintaining security and efficiency. Additionally, we explore the challenges faced by conventional model-based methods in the evolving landscape of 6G communication systems, characterized by complex interference and uncertain channel conditions. DL offers innovative strategies for redesigning baseband module functionalities, including coding/decoding and detection processes, thus enhancing overall performance.

Prof. Lei Shu,Nanjing Agricultural University, China

IEEE Senior Member

Prof. Lei Shu received his Bachelor's degree in Computer Science from Central South University for Nationalities in 2002. In 2005, he received his Master's degree in Computer science from Kyung Hee University, South Korea. He studied for a PhD with the National University of Ireland, Galway. In addition, he was a special researcher at Osaka University in Japan, and is currently a professor at the University of Lincoln in the United Kingdom, a professor at Nanjing Agricultural University, and the Director of Bion Intelligent Plant Protection Research Institute at Nanjing Agricultural University. The research field is Internet of Things, big data, artificial intelligence, intelligent plant protection.

Prof. Chen Gong,Nanjing University of Science and Technology, China

IEEE Senior Member

Chen Gong is a full professor in the School of Computer Science and Engineering, Nanjing University of Science and Technology. He received his B.E. degree from East China University of Science and Technology (ECUST) in 2010, and dual doctoral degree from Shanghai Jiao Tong University (SJTU) and University of Technology Sydney (UTS) in 2016 and 2017, respectively. He has published more than 100 technical papers at prominent journals and conferences such as IEEE T-PAMI, IEEE T-NNLS, IEEE T-IP, IEEE T-CYB, ICML, NeurIPS, CVPR, AAAI, IJCAI, ICDM, etc, and also holds 7 granted inventory patents. He serves as the associate editor for IEEE T-CSVT, NN, NePL, FR and CJE, reviewer for more than 30 international journals such as AIJ, JMLR, IEEE T-PAMI, IJCV, IEEE T-NNLS, IEEE T-IP,IEEE T-KDE, and also the SPC/PC member of several top-tier conferences such as ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, AAAI, IJCAI, ICDM, etc. He received the "Wu Wen-Jun AI Excellent Youth Scholar Award", "Young Elite Scientists Sponsorship Program" of China Association for Science and Technology, The Science Fund for Distinguished Young Scholars of Jiangsu Province, "Hong Kong Scholar", the second prize of Shanghai Natural Science Award, and "Excellent Doctorial Dissertation award" by Shanghai Jiao Tong University (SJTU) and Chinese Association for Artificial Intelligence (CAAI). He was also selected to the Global Top Chinese Young Scholars in AI released by Baidu, and World's top 2% scientists list by Stanford University.

Title:Neural Network Compression under Imperfect Conditions

Abstract: Deep model compression aims to compress large deep neural networks into lightweight and high-performance small ones while maintaining their performance, promoting the widespread application of computer vision and pattern recognition technologies in embedded devices. Knowledge Distillation (KD), a representative network compression method, regards the large network as a teacher and the small network as a student, which compresses the large network by transferring knowledge from the teacher to the student. However, in many real-world scenarios, mainstream KD methods usually fail due to various limitations and non-ideal conditions, such as discrepancies between the distributions of the teacher network's training data and the student network's application data, or the inaccessibility of the teacher's training data due to privacy concerns. Therefore, this talk mainly explores KD-based model compression methods under non-ideal conditions, which proposes direct cross-domain distillation, and data-free distillation using collected noisy data. The related works have been published in top-tier international journals and conferences including ICCV, ECCV, and IEEE T-IP.