Title: Security, Trust, and Privacy in Vehicular Networks
Summary: Vehicular networks, as an important application of Internet of things in the automotive industry, and as the core component of intelligent transportation system, can realize all-round network connection and efficient information interaction between vehicles and other nearby vehicles, road infrastructures, pedestrians, and network, etc., so as to provide various information services, improve driving safety and efficiency, and promote energy saving and emission reduction. Vehicular networks are regarded as a global innovation hotspot and an important commanding point of economic development, with huge industrial development potential and application market space. However, due to the large, open, highly dynamic, delay sensitive, and other characteristics, the security, trust, and privacy in vehicular networks face huge challenges.
This workshop focuses on highlighting the recent advances, challenges, and approaches for the security, trust, and privacy in vehicular networks. Topics of interest include, but are not limited to:
* Security protocols for vehicular networks.
* Trust management for vehicular networks.
* Privacy preservation for vehicular networks.
* Blockchain technologies for vehicular networks.
* Artificial intelligence algorithms for vehicular networks.
* Intrusion detection algorithms for vehicular networks.
* Emergency message dissemination for vehicular networks.
Chair 1: Prof. Yong Ma, Jiangxi Normal University (China)
Yong Ma, a professor of Jiangxi Normal University. He received the M.S. degree in computer science from Xidian University, Xi’an, China, in 2003, and the Ph.D. degree in computer science from Wuhan University, Wuhan, China, in 2006. His research interests include Internet of vehicles security, cloud computing, edge computing, data science, etc.
Chair 2: Assist. Prof. Zhiquan Liu, Jinan University (China)
Zhiquan Liu, an associate professor and master supervisor of Jinan University. His research interests include Internet of vehicles security, UAV security, web security, trust and privacy, artificial intelligence, blockchain, etc. In recent years, he has published more than 50 outstanding papers on Information Fusion, IEEE TDSC, IEEE TITS, IEEE IoTJ, IEEE TII, IEEE TCC, IEEE TVT, IEEE ICWS, IEEE WCNC, etc. His homepage is https://www.zqliu.com.
Title: Affective Computing Based on Computer Vision
Summary: Affective computing is a rapidly growing multidisciplinary field that explores how technology can understand the emotional state of human, how interaction between humans and technologies can be impacted by affect, how systems can be designed to utilize affect to enhance capabilities, and how sensing and affective strategies can transform human and computer interaction. Image and video carry huge resourceful cues of human affection, including facial expression, posture, action, and gaze etc. Computer vision based affective computing explores the cues of human affection carried by image and video, and develops algorithms and systems to recognize, interpret, process, simulate, and utilize human affects.
The aim of this workshop is to collect the latest research advancement and emerging applications of computer vision based affective computing to spark future work. Interest topics include, but not limited to:
Algorithms and features for the recognition of affective state from face and body gestures
Methods for multi-modal recognition of affective state
Tools and methods of annotation for provision of emotional corpora
Computational models of human emotion processes
Applications of affective computing
Hardware implementation of affective computing algorithms
Chair: Assoc. Prof.Dong Zhang, Sun Yat-sen University, China
Dong Zhang received his B.S.E.E. and M. S. degrees from Nanjing University, China, in 1999 and 2003, respectively, and Ph.D. degree from Sun Yat-sen University, China, in 2009. From 2008 to 2009, he was as a visiting scholar at the department of Electrical and Computer Engineering of Brigham Young University, Utah, U.S.A. He is currently an associate professor of the School of Electronics and Information Technology, Sun Yat-sen University. His research interests include image processing, computer vision, affective computing, and information hiding. He serves and served the guest editor of three special issues of Electronics, MDPI, and a co-editor of International Journal of Advanced Robotic Systems.
Title: Next-Generation Multiple Access for 6G
Summary: Due to the limited spectrum resource, multiple access design is one of the most challenging problems for each generation of wireless networks. Among the multiple access families, next generation multiple access (NGMA) is a promising technique since it accommodates multiple users over the same resource block, thus enhancing the connectivity and spectrum efficiency. Recall the fact that the communication requirements in 6G are stringent, it force the current Non-orthogonal multiple access (NOMA) to evolve into the next generation with the aid of new techniques.
This workshop focuses on attracting novel and solid contributions on the emerging topic of NGMA for 6G. Both theoretical and more applied contributions are solicited, covering, but not necessarily limited to, the following topics:
Fundamental limits and performance analysis of NGMA
Advanced channel coding and modulation for NGMA
NGMA for ultra-reliable low-latency communication (URLLC)
NGMA enhanced multi-function communications, e.g., ISAC and Integrated Navigation and Communication
NGMA for emerging technologies, e.g., THz, CoMP, OTFS, VLC
Keywords: NGMA, 6G
Chair 1: Assoc. Prof. Tianwei Hou, Beijing Jiaotong University, China
Tianwei Hou, Beijing Jiaotong University (BJTU), China (email@example.com) received Ph.D. degree from BJTU in 2021. He was a visiting scholar at Queen Mary University of London (QMUL) (Sep. 2018- Nov. 2020). Since 2021, he has been an associate professor at BJTU. Dr. Hou's current research interests include next generation multiple access (NGMA), reconfigurable intelligent surface (RIS) aided communications, UAV communications, multiuser multiple-input multiple-output (MIMO) communications, and stochastic geometry. He has granted a Marie Sklodowska-Curie fellowship by European Research Executive Agency in 2023 with the topic of NGMA-RIS. He has been selected as a young elite scientist sponsorship program by China Association for Science and Technology in 2022. He received the Exemplary Reviewer of the IEEE COMMUNICATION LETTERS and the IEEE TRANSACTIONS ON COMMUNICATIONS in 2018, 2019 and 2022. He has served as a TPC Member for many IEEE conferences, such as GLOBECOM, VTC, etc. He served as the publicity officer for the Next Generation Multiple Access Emerging Technology Initiative (NGMA-ETI). He has served as a Co-Chair in the 2nd, 4th and 5th NGMA-for-future-wireless-communication workshops in IEEE VTC 2022-Fall, IEEE VTC 2023-spring, IEEE ISCT-2022, IEEE PIMRC 2023. He has also served as a co-chair in the RIS and Smart Environments Symposium of IEEE ICCT 2023.
Chair 2: Assoc. Prof. Zhengyu Song, Beijing Jiaotong University
Zhengyu Song, Beijing Jiaotong University, China (firstname.lastname@example.org) received Ph.D. degree from Beijing Institute of Technology in 2016. He was a visiting scholar at Lancaster University (Nov. 2014- Dec. 2015). He is currently with the School of Electronic and Information Engineering, Beijing Jiaotong University. Dr. Song's current research interests include next generation multiple access (NGMA), reconfigurable intelligent surface (RIS) aided communications, UAV communications, mobile edge computing (MEC), and terrestrial-satellite-integrated communications.
Title: Recent Advances and Challenges of Satellite and Aerial Communication Networks
Summary: Due to the seamless connectivity and high data rate of Satellite and Aerial Communication (SAC), it has been viewed as a key element to bring real-time, higher capacity communication and wider coverage in the connection and deployment of a plethora of applications such as smart grids, Internet-of-Things (IoT), wireless sensor networks, space-based cloud for big data, and vehicular ad-hoc networks. The ASC is also regarded as a key element of the Beyond Fifth Generation (B5G) networks in emergency rescue for earthquakes and fire disasters, and transoceanic communication that current terrestrial communications cannot cover.
Nevertheless, owing to the inherent nature of satellite broadcasting and huge areas coverage, SAC can be easily exposed to eavesdroppers, leading to various security issues. Secure information transmission has aroused extensive interest from the wireless communications community in order to prevent eavesdroppers by taking advantage of the uniqueness characteristic of the realistic radio propagation channels to intercept confidential messages.
Energy efficiency is a significant metric for the next wireless communication networks from green and economic perspectives. To fulfill this goal, reconfigurable intelligent surfaces (RISs) come to our sights, which have been considered as an alternative and effective method to improve energy efficiency. RIS is a type of human-created surface with electromagnetic (EM) material which can be easily electronically handled to adjust the directions of reflective signals. RISs have attracted much attention from both academic and industry directions in recent five years. However, the investigation for the RIS application in the SAC is quite insufficient, thus it is worth to exploring the combination of RISs to boost the performance of SAC Networks.
Therefore, the theme of this topic is to investigate secrecy and high energy efficiency transmission problem in SAC and potential topics may include, but are not limited to the following:
·Security Protocol for Satellite and Aerial Communications
·Network Safety Measures in Satellite and Aerial Communications
·Developments in Cloud Storage Security
·Interception Prevention in Satellite and Aerial communications
·Developments in Radio Propagation Mediums
·Satellite Broadcasting and Security research
·Satellite UAV-assisted Communications
·RIS-based Satellite and Aerial Communications
·Covert Satellite Communications
·NOMA-based Secure Satellite and Aerial Communications
·Network Optimization and Communication Protocol for Satellite and Aerial networks;
·Efficient Resource Allocation Strategies for Satellite and Aerial networks;
·AI Enabled Intelligent Service for Satellite and Aerial networks;
·Cloud/edge Computing for Satellite and Aerial networks;
·Security and Privacy Solutions for Satellite and Aerial networks;
·Implementation/testbed/deployment of Satellite and Aerial networks;
·Integration of Satellite and Aerial Networks with State-of-the-Art Wireless Technologies (e.g., NOMA, backscatter communication, massive MIMO, physical layer security, millimeter-wave communication, cognitive radio, cooperative communication, energy harvesting, integrated sensing and communication)
Keywords: Satellite and Aerial Communication Networks, Reconfigurable Intelligent Surfaces, NOMA, Covert Communication
Chair 1: Assoc. Prof. Kefeng Guo, Space Engineering University, China
Kefeng Guo received his B.S. degree from Beijing Institute of Technology, Beijing, China in 2012, and the Ph.D. degree in Army Engineering University, Nanjing, China in 2018. He is a Lecturer in School of Space Information, Space Engineering University. He is also the associate professor in the College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics. He has authored or coauthored nearly 70 research papers in international journals and conferences. His research interests focus on cooperative relay networks, MIMO communications systems, multiuser communication systems, satellite communication, hardware impairments, cognitive radio, NOMA technology and physical layer security. He was a recipient of exemplary Reviewer for IEEE Transactions on Communications in 2022. He was the recipient of the Outstanding Ph.D. Thesis Award of Chinese Institute of Command and Control in 2020. He also was the recipient of the Excellent Ph.D. Thesis Award of Jiangsu Province, China in 2020. He also serves as an Editor on the Editorial Board for the EURASIP Journal on Wireless Communications and Networking. He was the Guest Editor for the special issue on Integration of Satellite-Aerial-Terrestrial Networks of Sensors, also the Guest Editor for the special issue on Recent Advances and Challenges of Satellite and Aerial Communication Networks of Electronics.
Dr. Guo has been the TPC member of many IEEE sponsored conferences, such as IEEE ICC, IEEE GLOBECOM and IEEE WCNC.
Chair 2: Dr. Min Wu, Space Engineering University, China
Min Wu received the M.S. degree from Space Engineering University, Beijing, China, in 2021, where she is currently pursuing the Ph.D. degree in Space Engineering University. Her research interests include on satellite-terrestrial networks, RIS-assisted wireless communication systems, multiuser communication systems and Deep Reinforcement Learning.
Title:Research on Human behavior Sensing Technology based on WIFI signal
With the development of computing technology, the machine-centered computing mode is shifting to the human-centered computing mode. The future development direction is to make people become a part of the computing link, promote the integration of the physical world and the information world, and realize high-level human-computer interaction. Accurate perception and interpretation of human behavior are essential technical support. In recent years, with the increasing number of WiFi hotspots deployed and the wide application of WiFi in the field of perception, especially positioning, human behavior sensing technology based on WiFi signal has attracted extensive attention. Its basic principle is that when WiFi signal meets the human body in the process of transmission, phenomena such as reflection, refraction, diffraction and scattering occur, which will cause disturbance to the normal propagation of the signal.
By analyzing the received signal and detecting the characteristics of signal disturbance change, the state of the human body encountered in the process of signal transmission can be perceived. WiFi behavior sensing is based on existing communication devices and makes use of WiFi signals widely existing in the environment, which has good universality and scalability. Perception method with the traditional human behavior, such as computer vision perception technology, infrared sensing technology and special sensors technology, based on the WiFi signal perception technology of human behavior with non line-of-sight, passive perception (do not need to carry sensing), low cost, easy deployment, without being limited by the light conditions, strong expansibility and so on a series of advantages.
Chair : Assoc. Prof. Bin Chen, Lijiang culture and tourism college, China
Bin Chen, Associate professor, Master degree of Beijing University of Posts and Telecommunications, visiting scholar of Peking University, presided over the Science and Technology Fund project of Yunnan Provincial Education Department and the Science and Technology Department Project. Published academic papers are: the time sensitive collaborative filtering algorithm based on restrictive random walk, the application of artificial intelligence technology in the field of network security, network data protection based on space confusion nearest neighbor query methods, multi-node network time series data similarity measure algorithm and data applications, computer network attack grey evaluation model and algorithm, etc. More than 20 academic papers. Such as neural network algorithm analysis in computer network model, computer network information security protection strategy and its key technologies, etc., participated in the construction of the digitalization project of Lijiang City Government in Yunnan Province. Lijiang ancient town, including "smart mind", lijiang, epidemic prevention and control platform, lijiang area monitoring for the rational use of drugs and prescriptions circulation service platform, lijiang national health information platform construction projects of all digital platform for the local digital construction put forward the professional opinion, especially in view of the system platform of user privacy, information security, network security issues such as effective feasible solutions are put forward. He has been serving in the organization teams of some international conferences, e.g. Imodern electronic technology,IoTBDSC 2022, CECNet2022.
Title:Optical Wireless Communications for B5G and 6G
As the emerging and promising candidates for B5G and 6G, visible light communications, and other emerging optical wireless techniques are earning increasing attention and investigation from both the wireless communication and the optical communication communities. These various and distinct hybrid techniques open the novel research opportunities for numerous application scenarios, including but not including but not limited to indoor wireless communications, indoor positioning and sensing, wireless backhaul, vehicular applications, underwater wireless applications, satellite applications, underground wireless applications, high speed train applications, healthcare wireless applications, retro reflection communications applications, unmanned aerial vehicular wireless applications, and other developing fields.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The main goal is to show the latest research works in the field of visible light communications & positioning, hybrid optical wireless techniques, especially for empowering 6G development. We encourage prospective authors to submit related research papers on the following subjects: Emerging Wireless Optical Communications, Visible Light Communications & Positioning & Sensing, Hybrid Optical Wireless, Free Space Optics, Radio Over Fiber, Thz Communications, and B5G&6G. Both theoretical and more applied contributions are solicited, covering, but not necessarily limited to, the following topics:
Keywords: Emerging Wireless Optical Techniques, Visible Light Communications,
ireless Optical Communications, Wireless Optical Positioning, Wireless Optical Sensing, Free Space Optics, Radio Over Fiber, Thz Communications, 6G
Chair : Assoc. Prof. Jupeng Ding, Xinjiang University, China
Jupeng Ding, received the M.Sc. and Ph. D. degree from the Communication, Beijing University of Posts and Telecommunications (BUPT), Beijing, China. In 2013, he joined Key Laboratory of Wireless-Optical Communications, Chinese Academy of Sciences, Optical Wireless Communication and Network Center, School of Information Science and Technology, University of Science and Technology of China, Hefei, China. In 2017, he worked in one world top 500 enterprises. Then he joined Xinjiang University working on optical wireless communication. His current research interests include visible light communication, optical wireless links, B5G&6G mobile systems & networks, and free space optics.
Now he is an Associate Professor in College of Information Science and Engineering, Xinjiang University. He has published more than 50 journal and conference papers and holds more than 20 national and international patents, in most of which he worked as the first author, the first author & corresponding author, or the first inventor. He works as one active reviewer of numerous high level journals including IEEE Wireless Communications Magazine, IEEE Communications Magazine, IEEE Communications Letters, IEEE Wireless Communications Letters, IEEE Journal of Lightwave Technology, Elsevier Optics Communications, OSA Optics Letters, and OSA Optics Express. He is a senior member of Chinese Institute of Electronics, Chinese Optical Society, and China Institute of Communications.
Title:Future Network and Intelligent Computing
The next-generation communication network has the characteristics of ultra-wide bandwidth, low latency and high reliability, and can carry more complex services. Artificial intelligence (AI) capability is one of the endogenous capabilities in next-generation networks. AI services not only occur at the application layer, but may also occur at the link layer or network layer. The new type of AI service bearing brings new and huge challenges to communication and networking. AI services are different from traditional services in that they have special resource requirements, different service quality assurance requirements, and different adjustment and control methods.
This workshop focuses on the convergence of AI and communication networks. AI for network and network for AI are discussed in this workshop. Topics that may design the AI algorithms to solve the communication/networking problem and the communication/networking solutions to bear the AI services, but not limited to:
·The system architecture for the next generation mobile communication
·The convergence of communication/networking and AI
·AI for computing networks
·AI for radio resource management
·AI for network operation and maintenance
·AI for network planning and optimization
·Network planning and optimization for AI services
·Resource allocation for AI services
·Routing protocol for AI services
·AI QoS guarantee
·AI as a service
·Digital Twin Network technology
Keywords: artificial intelligence, 6G, the convergence of communication/network and AI
Chair 1: Prof. Yong Zhang, Beijing University of Posts and Telecommunications, China
Yong Zhang, Beijing University of Posts and Telecommunications (BUPT), China (Yongzhang@bupt.edu.cn) received the Ph.D. degree from BUPT in 2007. He was a visiting scholar at the Pennsylvania State University (Dec. 2013 – Jan. 2015). Currently he is a Professor at school of electronic engineering, BUPT. He is the Director of Fab.X Artificial Intelligence Research Center, BUPT. He is the Deputy Head of the mobile internet service and platform working group, China communications standards association. His research interests include Artificial intelligence, wireless communication, and Internet of Things.
Chair 2: Senior Researcher, Qin Li, China Mobile Research Institute, China
Qin Li, senior researcher of China Mobile Research Institute. She received her master’s degree from Chongqing University, Chongqing, China, in 2002. She has engaged in technical and application research on core network and content network for more than 20 years. Her research interests cover 5G/6G architecture, network intelligence and digital twin network.
In the future, as the wireless network is becoming more complex and more heterogeneous. Artificial Intelligence will play a critical role in designing and optimizing 6G architectures, protocols, and operations. In contrast to previous generations, 6G will be transformative and will revolutionize the wireless evolution from “connected things” to “connected intelligence”. In particular, to support AI-based applications, the network entities have to support diverse capabilities, including communications, content caching, computing, and even wireless power transfer.
First, the PHY layer of wireless communication systems suffers from a wide variety of impairments, including hardware impairments such as amplifier distortion, local oscillator leakage, and channel impairments such as fading, interference, and so on. The“intelligent PHY layer” paradigm in 6G, where the end-to-end system is capable of self-learning and self-optimization by combining advanced sensing and data collection, AI technologies, and domain-specific signal processing approaches.
Second, the design of the 6G architecture shall follow an “AI native” approach where Intelligentization will allow the network to be smart, agile, and able to learn and adapt itself according to the changing network dynamics. It will evolve into a “network of sub-networks,” allowing more efficient and flexible upgrades, and a new framework based on intelligent radio and algorithm-hardware separation to cope with the heterogeneous and upgradable hardware capabilities.
Third, descriptive analytics of historical data in a wireless network get insights on network performance, traffic profile, channel conditions, user perspectives, and so on. It greatly enhances the situational awareness of network operators and service provider. The AI
technology can best exploit the the value of the historical data and configure the network condition accordingly.
Key issues addressed by Artificial Intelligence-assisted for Future Wireless Networks, include the following:
Key issues addressed by Artificial Intelligence-assisted for Future Wireless Networks, include the following:
(1)Research on AI-assisted communications technology such as adaptive modulating, channel estimation, beam-forming and precoding for massive MIMO systems ;
(2)Research on AI-assisted caching, edge computing, data offloading strategies and so on;
(3)AI-assisted prediction on future events of the network such as traffic patterns, user locations, user behavior and preference;
(4) AI-assisted resource optimization, network slicing and virtualization, cell handover, load balancing and interference coordination in network level.
Chair: Assoc. Prof. Feng Ke, South China University of Technology, China
Ke Feng works at South China University of Technology. He is currently an associate professor in the School of Electronic and Information Engineering. He serves as the Vice Director for the Intelligent Communication Network and Computer Engineering Technology Engineering Center, SCUT, and the Chief Scientist of the Guangdong Chinese-Network Electrical Engineering Research Institute. He also serves as an Expert Advisor of the Guangzhou Science and Technology Bureau and Guangdong Science and Technology Department. His research interests include communications and information theory, with special emphasis on future wireless communication and network, joint sensing and communication, and artificial intelligence technology used in wireless network. He has published more than 60 papers in academic authoritative journals such as IEEE TCOM, IEEE TVT, IEEE CL and Computer Communications, and famous academic conferences such as IEEE WCNC, IEEE GLOBECOM. Also, he has obtained more than 20 patents.
Title:Multi-modal learning and its applications in autonomous vehicles
Intelligent agents with autonomous systems promise to enhance driving safety and improve the efficiency and reliability of transportation systems. Multi-modal learning-based situational awareness, guidance, and control technologies for autonomous vehicles are rapidly advancing. Intelligent agents that can sense the surrounding environment in real-time and navigate without human input require robust situational understanding, autonomous guidance, and control capabilities to operate efficiently in various environments and weather conditions. In order to achieve robust and accurate scene understanding, autonomous systems are usually equipped with different sensors (e.g., cameras, LiDARs, and radars), and multiple sensing modalities can be fused to exploit their complementary properties.
This workshop will seek original contributions covering advanced topics related to the state of the art and future trends in deep learning based multi-modal learning algorithms, multi-modal learning based situational awareness and prediction technologies, as well as control and guidance technologies for intelligent agents. Topics of interest include, but are not limited to:
1. Deep Learning models in Multi-modal processing
2. Situational awareness technology for intelligent agents
3. Advanced wireless technologies and methods for transportation communication in autonomous systems
4. Uncertainty modeling, assessment, and propagation in autonomous systems
5. Advanced AI-based multi-system fusion for guidance and control of intelligent agents
6. Edge-computing methods for efficient heterogeneous data processing
7. Automation and autonomy for intelligent agents
8. Strategies for the fusion of multi-modal heterogeneous data in autonomous systems
9. Multi-view, multi-temporal, and multi-modal image analysis for autonomous systems
10. Innovations in other autonomous systems
11. Evaluation benchmarks for assessing method performance, robustness, explainability, scalability, and generalization
Keywords: Multi-modal learning, Deep Learning, Situational awareness, transportation communication, Internet of Things, uncertainty modeling, edge-computing, heterogeneous data processing
Chair:Prof. Jiu Liu, Shanghai Maritime University, China
Jin Liu received his B.S.degree from Lanzhou University, Lanzhou, China in 1997; M.S.degree from University of Electrical Technology of China, Chengdu, China in 2002; and Ph.D degree from Washington State University, Pullman, USA in 2007. Dr. Jin Liu is currently a professor with College of Information Engineering at Shanghai Maritime University. His research interests include machine learning, multi-modal learning, Internet of things and related information systems. He has co-authored over 80 technical papers, co-chaired a number of international conferences, and been serving as Academic Editor for SCI journals such as PLOS ONE, Journal of Sensors. He had won the 2022 Second Prize of SHANGHAI Municipal Science and Technology Advancement Award, the 2021 first prize of Science and Technology Progress Award of China Institute of Navigation. He is currently the Secretary-General of Shanghai Association for Noetic Science, the deputy Secretary-General of Shanghai Association for Artificial Intelligence, and a Member of Council for Shanghai Computer Society. He is also member of Committee of Machine Learning, member of Committee of Intelligent City for China Association of Artificial Intelligence (CAAI), and member of IEEE and CCF.
Title:Artificial intelligence technology applied in agriculture
This workshop is committed to focusing on and promoting the artificial intelligence technology application and innovation in smart agriculture at home and abroad. It aims to build a forum to discuss and share successful experiences in the innovation and development in this area, and promote further cooperation. With focus on topics such as agricultural sensors, agricultural artificial intelligence, agricultural automatic control, agricultural robots and intelligent equipment, precision agriculture and smart farms.
Interest topics include, but not limited to:
·The application of machine vision and artificial intelligence in smart agriculture
·Innovation and practice of intelligent management and control technology for agricultural facilities
·A traceability system for agricultural product quality based on the Internet of Things
·Research and innovation on key technologies of agricultural Internet of Things
·Application of photoelectric sensing technology in agriculture production
·Innovation and practice of intelligent management for agricultural facilities and control technology
·Intelligent drying technology for agricultural products
Chair:Assoc. Prof. Hua Yin, JiangXi agricultural University, China
Hua Yin(email@example.com),received his D.r. degree in Mechanical Engineering from NanChang University, NanChang, China, in 2017. He is currently an associate professor of the School of Software, JiangXi Agricultural University. He is a lifetime member of CAAI. His research interests include smart agriculture and machine vision.
Title: Computer vision models, algorithm research and applications
Summary: Computer vision is an interdisciplinary discipline covering several fields, aiming to enable computers to mimic the human visual system and achieve the ability to understand and cognize the visual world. It involves various fields such as digital image/video processing, pattern recognition, machine learning, deep learning, computational geometry, etc. The core tasks include image/video processing, target detection, image classification, semantic segmentation, etc.
With the development of deep learning technologies, such as convolutional neural networks, recurrent neural networks and generative adversarial networks, many advances and achievements have been made in the field of computer vision, which in turn has led to the wide application of computer vision in various fields, such as medical care, transportation, agriculture, security, smart home, etc. At the same time, computer vision is also one of the important directions of future artificial intelligence technology, which will have a profound impact and change on human life and work.
Primary submission areas:
1.Image/video processing and computer vision algorithm design
2.Three-dimensional computer vision modeling
3.Deep learning and neural network research
4.Computer vision applications and research
5.Data set construction and evaluation methods and research
6.Intersection of computer vision and other fields of study
Chair: Assoc. Prof. Yang Wenji, Jiangxi Agricultural University, China
Yang Wenji, Ph.D., Associate Professor, Master's Supervisor, Director of Teaching and Research Office, Research Secretary, and CCF Member. She is currently working at the School of Software, Jiangxi Agricultural University, selected for the "Future Star" and "Young Associate Professor" Top Talent Program, selected for the General Program of the National Scholarship Council and the “Far East Navigation Engineering” Project of Jiangxi Provincial. She is a communication evaluation expert of the National Natural Science Foundation of China, paper evaluation expert of the Degree Center of the Ministry of Education, reviewer of magazines such as "Knowledge based systems", "Multimedia Tools and Application", and "Journal of Xi'an Jiaotong University", and awarded the title of "Excellent Class Teacher". She teaches undergraduate courses such as "C Language Programming", "Data Structure", and graduate courses such as "Fundamentals of Big Data Mathematics"; She has been engaged in research in fields such as computer vision, image processing, machine learning, deep learning, pattern recognition, and agricultural information technology for a long time. As the project leader, she has presided over 1 National Natural Science Foundation project, 2 Provincial Natural Science Foundation projects, and 5 department level projects; and participated as a key member in three National Natural Science Foundation projects. She has published over 38 related academic papers, including 16 papers indexed by SCI and EI.
Title: Research on scalable computing methods, models and applications
Summary: Currently, information technology is developing rapidly, which promotes the rapid development of digital economy. In particular, various information technologies based on parallel distributed computing, such as cloud computing, collaborative computing, distributed machine learning, privacy technology, and blockchain technology, are core support forces for the development of the digital economy, but these key technologies have common bottlenecks that are difficult to scale. This theme is oriented to the core technologies supporting the development of digital economy, and explores the bottlenecks and problems of these core technologies breaking through the difficulty of scaling from the perspective of scalability, and studies the core algorithms of cloud platform in terms of computing power, storage, and resource provisioning to realize the scientific, accurate, and elastic scaling of cloud platform to meet the dynamic and diversified needs of users for computing power and resources; uses new intelligent technologies such as machine learning to realize the performance of collaborative computing. The scientific definition and concept of blockchain scalability are explored to standardize and guide the development of scalable blockchain construction, and to study the models, methods and technologies of blockchain scalability in multiple dimensions, such as function and performance, to cope with the growing data storage demand of blockchain systems and to meet the urgent needs of blockchain security interaction and interconnection in various industries and fields
The scope of the paper includes but is not limited to:
1.Architectures, models, methods and applications of scalable cloud computing;
2. Architectures, models, methods, and applications of scalable collaborative computing;
3. Key technologies for scalable federated learning;
4. The definition of scalable blockchain, the scalable storage model of blockchain, the scalable methods and applications of blockchain;
5. Blockchain security cross-chain models, methods and applications.
Chair: Assoc. Prof. Huanliang Xiong, Jiangxi Agricultural University, China
Huanliang Xiong, Ph.D., Associate Professor, Master Advisor, graduated from the Department of Computer Science and Technology, Tongji University. His main research interests include: parallel computing, scalable computing, machine learning, and blockchain technology. He is currently working in the School of Software of Jiangxi Agricultural University and the Key Laboratory of Agricultural Information Technology of Jiangxi Higher Education Institution. He is also a member of the Special Committee on Collaborative Computing of the Chinese Computer Society, a senior member of the Chinese Computer Society, a professional member of IEEE, and a dissertation reviewer of the Degree Center of the Ministry of Education. He has taught C Programming and Data Structures for undergraduates and Software Development and Applications for postgraduates; he has hosted and participated in 15 national and provincial projects. He has published more than 15 research papers as the first or corresponding author, including 10 SCI and EI retrieved papers; published 3 undergraduate textbooks; been authorized 3 national invention patents and more than 10 software copyrights; actively participated in academic exchange activities of famous universities and research institutions at home and abroad, and presented more than 5 times in academic conferences at home and abroad.
Title: Research on AI technology methods, models and algorithms in the field of intelligent ecological agriculture
Summary: The report of the 20th Party Congress first proposed to accelerate the construction of a strong agricultural country, pointing out that a strong agricultural country is the foundation of a strong socialist modernization country, that a strong country must first strengthen agriculture, and that a strong agriculture makes a strong country, and that the road of sustainable agricultural development is taken. In the sustainable development of agriculture, smart ecology is an inevitable trend, and smart ecological agriculture is an important support for rural revitalization and an important symbol of agricultural modernization. This theme is oriented to the development needs of smart ecological agriculture, exploring strategies and measures for the development of smart ecological agriculture, and constructing key AI technology methods, models and algorithms for smart ecological agricultural production and production activities. Through intelligent monitoring system, it realizes intelligent perception, intelligent information, intelligent analysis, intelligent warning, intelligent decision-making and expert online guidance in the fields of agricultural production, rural ecology and farmers' life. It provides suggestions for developing smart ecological agriculture technology and implementing sustainable development of China's agricultural modernization.
Main submission scope:
1. Key technologies of intelligent question and answer system for knowledge in agriculture
2. Intelligent diagnosis and identification modeling technology for crop pests, water and fertilizer
3. Key core technologies of unmanned AI intelligent planting and breeding
4. Biological multi-characteristic coarse and fine-grained intelligent identification technology
5. Smart ecological agriculture and virtual reality integration technology
Keywords: 3D visualization modeling, computer vision, machine learning, deep learning
Chair: Prof. Hongyun Yang, Jiangxi Agricultural University, China
Hongyun Yang is a professor and master supervisor. He is now working in the School of Software of Jiangxi Agricultural University/Key Laboratory of Agricultural Information of Jiangxi Higher Education Institution, and is also a member of the Special Committee of Intelligent Agriculture of China Artificial Intelligence Society, an invited reviewer of Southern Agricultural Journal, and a dissertation reviewer of the Degree Center of Ministry of Education. His research interests include virtual agriculture, machine vision and machine learning. His research interests include virtual agriculture, machine vision, machine learning, etc. He teaches undergraduate courses such as "c programming", "data structure", "algorithm design and analysis", and "mathematical foundation of machine learning" for graduate students. He has presided over 2 projects of National Natural Science Foundation of China and 3 provincial and departmental projects; participated in 1 National Key Research and Development Program, 3 National Natural Science Foundation of China and 10 provincial and departmental science and technology projects as a major member; published more than 40 research papers in core academic journals as the first or corresponding author; published 1 monograph and 2 textbooks as an associate editor; actively participated in academic exchange activities at home and abroad.
Title:Edge-native Architectures, Algorithms and Applications
Summary: It is well acknowledged that we’re entering a new age of data decentralization, which will be enabled by the powerful computing devices, the pervasive 5G/6G networks, and the advances in IoT/IIoT and AI/ML. In this new scenario, instead of a centralized cloud, an edge cloud that is distributed by nature is required as a service platform, and instead of the cloud-native approach, an edge-native approach is required and it is designed to meet the challenges of the edge, built for distributed architectures, and optimized for decentralization.
Particularly, the applications that operate near the edge are not the same as that in the hyperscale cloud. The cloud-native applications are designed to leverage the unlimited horizontal scaling, with the rapid change and rapid deployment as the key. On the other hand, the edge-native design is focused on the real-time and dynamic automation of the physical systems, including things and people.
Moreover, the cloud native approaches that work well in the centralized architectures would not work as well in this new paradigm of dispersion and decentralization, because it does not face the same barriers as the distributed architecture, for example, the extremely low latency and high reliability, the extremely high throughput, and the inherently complex service orchestration.
In order to address these challenges, the systems and networks in the edge-native scenarios should be revalued and redesigned in terms of the architecture, the algorithm, and the application. With the purpose of pushing forward the research and understanding in this field, we cordially invite your submissions of research articles, communications, and perspectives to this track.
Chair: Dr. Fengyou Sun, Zhejiang Normal University, China
Fengyou Sun received his PhD degree in Information Security and Communication Technology from NTNU–Norwegian University of Science and Technology, Trondheim, Norway in 2020. He is currently working at the Department of Computer Science and Technology, Zhejiang Normal University. His research interests include applied probability and stochastic process, especially queueing theory and stochastic network calculus, and their applications to wireless channels and computer networks. Recently, he has been doing research on the smart utilization of the wireless channel resources, like stochastic dependence, and the emergence of disruptive applications, such as holographic communication, and the corresponding traffic engineering and service guarantee mechanisms, for instance edge-native computing and networking.
Title: Explainable Machine learning and Natural Language Processing for Intrusion Detection
Summary: With the complexity of network attacks, traditional intrusion detection technologies have high false positive rate and false negative rate, low accuracy rate and poor generalization ability. In recent years, Machine Learning (e.g., Deep leaning) and Natural Language Processing (i.e., NLP) have led to vast progress in the field of pattern recognition, machine learning and anomaly detection. Machine Learning technology has excellent performance in processing complex large-scale data, and NLP technology enables computers to analyze, understand and process natural language. Meanwhile, We also need explainable machine learning to break down the drawbacks of end-to-end learning. Thus, they can bring new ideas for processing multi-source heterogeneous intrusion data, and effectively improve the detection performance and the generalization ability.
Both theoretical and more applied contributions are solicited, covering, but not necessarily limited to, the following topics:
·Representation of semantic comprehension of Cyber Threat Intelligence based on NLP
·Representation of network confrontation capability
·Generation and comprehension and entity behavior semantics
·Construction of security knowledge base
·Few-shot learning for intrusion detection
·Intrusion detection framework based on Explainable Machine learning
Chair: Assoc. Prof., Tianbo Wang, Beihang University, China
Tianbo Wang received the Ph.D. degree from the Beihang University. He is currently an associate professor with the School of Cyber Science and Technology, Beihang University. He has participated in several National Natural Science Foundations and other research projects as a Contributor. His research interests include network and information security, intrusion detection technology, system security. and information countermeasure. He has published a number of papers, such as IEEE Transactions on Dependable and Secure Computing (TDSC), IEEE Transactions on Information Security and Forensics (TIFS)，IEEE Transactions on Mobile Computing (TMC) and ACM Computing Surveys (CSUR) . He also served as TPC member for some International Conferences, such as ISPA 2019 and Trustcom 2022.
Title: Remote Sensing Data analysis and Application
Summary: Remote sensing technology provides possibilities for observing the Earth from different perspectives. Multi-platform-source remote sensing data enriches the connotation of observations. Designing excellent methods is a necessary way to unleash the value of these data. Machine learning, especially artificial intelligence methods, will explore the rich information contained in remote sensing data and promote the implementation of remote sensing applications.
This workshop focuses on providing a platform for sharing knowledge and experience on recent developments and advancements in geoscience and remote sensing technologies, particularly in the context of earth observation, disaster monitoring and risk assessment. Both theoretical and more applied contributions are solicited, covering, but not necessarily limited to, the following topics:
·Feature Extraction and Reduction
·Object Detection and Recognition
·Classification and Clustering
·Change Detection and Temporal Analysis
·Spectral Data Processing and Analysis
·LiDAR Data Processing and Analysis
·SAR Imaging and Processing Techniques
·RFI Detection and Mitigation
·Multi-source Data Fusion
·Soil Composition Analysis
·Automatic Road Inspection
Keywords: Remote sensing, AI, Multi-source data
Chair 1: Prof. Qingwang Wang, Kunming University of Science and Technology
Qingwang Wang received the B.E. degree and Ph.D. degree in electronics and information engineering, and information and communication engineering from the Harbin Institute of Technology, Harbin, China, in 2014, and 2020, respectively. From 2020 to 2021, he worked as a senior engineer in Huawei Technology Co., Ltd. to study autonomous driving. Now he joined Kunming University of technology as a high-level talent. His research interests include machine learning and its application to remote sensing data analysis, autonomous driving and edge calculation. More specially, his studies currently focus on using kernel methods, deep learning, broad learning and graph convolutional neural networks to extracting information from RGB-T images, hyperspectral image, LiDAR data, and multispectral LiDAR point clouds.
Chair 2: Prof. Yiming Yan, Harbin Engineering University
Yiming Yan received the B.E. degree, M.S. degree and Ph.D. degree in electronics and information engineering, and information and communication engineering from the Harbin Institute of Technology, Harbin, China, in 2006, 2008 and 2013, respectively. From 2013 to 2016, he worked as a postdoctoral in department of Control Science and Engineering, Harbin Institute of Technology to study remote sensing image processing and 3D reconstruction.
Now he joined Harbin Engineering University as an associate professor. His research interests focus on multi-modal information extraction, image retrieval and 3D modeling based on Satellite/Aerail optical images, SAR images and LiDAR data.
Title: Human Modeling and Applications in Aviation
Summary:Human modeling has advanced to the point that it is able to represent relatively complex aircraft–air traffic control interactions with sufficient realism to assess the performance of alternative systems and procedure designs. They facilitate the use of body dimensions and shape, human postures and motions, human physical performance and their variability. In addition to physical accommodation and performance, they allow analyses of vision, comfort and workload (both physical and cognitive). Other models also exist to process optimization, and hazards such as thermal and radiation. They have become more powerful recently. Intelligent Human Models or Virtual Humans have become more popular for gaming, education, and training. In these models, Virtual Environments, and the appearances of humans and their behavior are becoming more realistic than before. New developments in the fields of artificial intelligence (AI), Virtual and Augmented Reality (VR/AR) are also leading us to new approaches for a comprehensive three dimensional realistic models.
Key issues addressed in this session include the following:
(1)Digital Human Modeling Tools and Platforms
(2)Human Behavior Representation and Models
(3)Human performance and risk assessment
(4)Process Modeling and Simulation
Keywords: Human modeling, Human factor, Human performance, Risk assessment, Pilot performance, Human error
Chair : Associate Prof. Xiaoyan Zhang, Northwestern Polytechnical University
Xiaoyan Zhang works at Northwestern Polytechnical University. She is currently an associate professor in the School of Marine Science and Technology. Her research interest covers Human performance and modeling. In the past ten years, she has published more than 50 papers in international academic journals and international famous academic conferences. Presided over and participated in a number of national fund and Ministry of Education research projects.