Professor Junhui Zhao

IET Fellow

Beijing Jiaotong University, China

Biography: 

Junhui Zhao received the M.S. and Ph.D. degrees from Southeast University, Nanjing, China, in 1998 and 2004, respectively. From 1998 to 1999, he worked with Nanjing Institute of Engineers at ZTE Corporation. He is currently a Professor at the School of Electronics and Information Engineering in Beijing Jiaotong University. His current research interests include wireless communication, internet of things, and information processing in transportation.

Speech Title: BEV perception in autonomous driving

Abstract: Environmental perception is the core technology for achieving autonomous driving, enhancing both driving safety and efficiency. This presentation first introduces single-vehicle perception techniques, including sensor fusion and BEV perception, which serve as the foundation for collaborative perception. Second, it explores multi-vehicle collaborative perception, where information sharing between vehicles expands perception range and improves accuracy. Finally, it investigates collaborative perception under real-world communication constraints, analyzing the impact of factors like communication loss on system performance and proposing optimization strategies. This research provides theoretical support and technical direction for autonomous driving perception in complex traffic environments.

Professor Yisheng An

Dean, School of Information Engineering

Chang'an University, China

Biography: 

安毅生，男，1972年6月生，陕西西安人，博士、教授，博士生导师，长安大学信息工程学院院长。长安大学计算机科学与技术专业建设负责人，“交通信息工程及控制”学科A岗责任教授，交通运输部认定自动驾驶封闭场地测试基地副主任。陕西省计算机学会理事，陕西省计算机教育学会副理事长，中国计算机学会杰出会员，中国自动化学会、ACM、IEEE会员，中国自动化学会网络信息服务专委会委员。教育部工程教育认证专家，教育部学位与研究生教育发展中心评审专家，国家自然科学基金委函评专家，陕西省、重庆市科学技术奖评审专家，陕西省、西安市青年拔尖创新人才评审专家。

近年来主要从事自动驾驶系统测试、交通流建模与仿真、数字孪生系统构建等方面的科学研究和技术开发工作，围绕“封闭场地自动驾驶虚实融合测试”和“基于数字孪生的自动驾驶虚拟测试”等方向，作为项目负责人，主持完成了包括国家重点研发计划课题、国家自然科学基金面上项目、陕西省工业公关重点项目、陕西省自然科学基金重点项目以及中兴通讯、陕西交控等知名企业委托的纵、横向研究课题等20余项。作为教育部长江学者和创新团队发展计划项目“多源异构交通信息智能检测与融合技术”的骨干成员，参与完成了多项重要技术的研发与测试工作。作为核心成员，荣获国家科技进步奖二等奖一项、陕西省科学技术奖一等奖一项。获得发明专利12项，发表学术论文70余篇，培养博士和硕士研究生30余人.

Speech Title: Intelligent and Connected Transportation System (ICTS)

Abstract: 

With the rapid advancement of artificial intelligence, communication technologies, and autonomous driving, intelligent connected transportation systems (ICTS) are gradually reshaping human travel modes and urban traffic patterns. Centered on intelligent vehicles, ICTS integrate perception, communication, big data, and autonomous control technologies to achieve efficient interconnection and collaborative management among vehicles, infrastructure, users, and cloud platforms. This transformation is driving transportation toward greater intelligence, sustainability, and safety. 

This report begins by tracing the evolution of modern transportation and explores global trends in intelligent connected vehicle development. It focuses on key technological innovations by leading enterprises such as Tesla, Google, and Huawei in areas like autonomous driving, environmental sensing, and visual navigation. The presentation further outlines the system architecture of ICTS and delves into critical technologies including traffic scenario construction, multimodal communication, high-precision positioning, vehicle-infrastructure coordination, cloud-based integration, and cybersecurity. In addition, the report compares policy strategies, technological roadmaps, and pilot applications across major regions such as China, the United States, Europe, and Japan. Special attention is given to China’s efforts in developing a “vehicle-road-cloud integrated” infrastructure, along with progress in standardization and testing. The discussion concludes with an outlook on the future direction of smart transportation and the challenges it may face.

Professor Zhiwei Ye

Dean of School of Computer Science

Hubei University of Technology, China

Biography: 

Ye Zhiwei, male, professor, is the dean of the School of Computer Science at Hubei University of Technology and the executive dean of the Big Data and Artificial Intelligence Industry College. He is also the director of the Hubei Provincial Key Laboratory of Green and Intelligent Computing Power Network, the leader of the Hubei Provincial Excellent Middle-aged and Young Scientific and Technological Innovation Team, the deputy director of the Data Science Committee of the National Higher Education Computer Basic Education Research Association, director of Hubei Computer Society, expert of Engineering Education Accreditation of Ministry of Education and the vice chairman of the Xining Smart Cloud Digital Economy Research Institute. He has won two second prizes of the Hubei Provincial Science and Technology Progress Award, and in 2021, he won the first prize of the China Innovation Challenge Competition in the High-end Equipment Manufacturing Special Session in Hubei and Wuhan organized by the Torch High-tech Industry Development Center of the Ministry of Science and Technology. He has guided students to win five special and first prizes in the National Challenge Cup Competition. He has supervised over 40 master's students, obtained 23 authorized invention patents, and published 115 research papers in important domestic and international academic journals and conferences, among which 75 papers have been indexed by SCI or EI, with a total citation count of over 2,000 times. He has led and participated in more than 10 projects including the National Natural Science Foundation of China and the Hubei Provincial Key Research and Development Program. Currently, his main research directions include machine learning, image processing, and  evolutionary computation.

Speech Title: Feature selection based on Hybrid breeding optimization algorithm

Abstract: With the advancement of data collection technology, more and more observational data can be obtained. However, the increase in data dimensions leads to the inclusion of a large number of irrelevant or weakly correlated features in the data set. These features not only increase the computational time of subsequent machine learning models but also may reduce the accuracy of classification. Therefore, feature selection is a very important step. The problem of feature selection is computationally very complex, and it is difficult to obtain the global optimal solution through traversal or branch and bound methods for high-dimensional feature selection. In recent years, some random optimization algorithms have performed well in the feature selection problem. However, there are still problems such as being prone to getting stuck in local optimal solutions and long computation time. The hybrid breeding optimization algorithm is a new type of intelligent optimization algorithm proposed by the reporting team under the inspiration of the three-line hybrid rice breeding mechanism and heterosis. This algorithm has the advantages of strong optimization ability and fast convergence speed. This report attempts to explore the application of the hybrid breeding optimization algorithm and various improved algorithms in the optimization solution of feature selection, providing new attempts for the solution of high-dimensional feature selection problems.