MLCCIM | workshop22

Workshop 1

Summary: Due to the diversification of network application requirements such as cloud computing, big data and Internet of Things, computer networks need to provide differentiated network transmission services for different applications. Some important research topics for current computer network technology include:
(1)How to allocate network resources reasonably for different network applications with different Quality of Service (QoS, such as bandwidth, delay, and jitter)?(2)How to optimize the performance of the network globally so as to avoid network congestion and improve the utilization of network resources?

Compared with traditional network architecture, Software-Defined Network (SDN) decouples the control plane and data plane of network devices by realizing a more flexible network controller, which can accelerate the speed of network application innovation. The centralized management mode based on SDN controller provides favorable conditions for network resource allocation and global performance optimization. In addition, the algorithms based on Machine Learning (supervised and unsupervised learning, reinforcement learning, deep learning, etc.) can also easily be applied in SDN controller for various tasks, such as network traffic prediction, network resource allocation, network security protection, network performance optimization and so on. The main goal of this workshop is to show the latest research results by researchers from academia and the industry in the field of SDN based on Machine Learning. We encourage prospective authors to submit related distinguished research papers on the subject of theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshop title".

Keywords: Software Defined Network, Machine Learning, Reinforcement Learning, Deep Learning, Network Resource Allocation, Network Security, Network performance optimization

Prof. Zhaogang Shu is currently an associate professor at the College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou, China. He is also the director of the department of computer science and Cloud Computing Lab, Fujian Agriculture and Forestry University. He received B.S. and M.S. degrees in computer science from Shantou University, China in 2002 and 2005 respectively. He also received his Ph.D. degree from South China University of Technology, Guangzhou, China in 2008. During the time of Sep. 2008 to July 2012, he worked as a senior engineer and project manager at Ruijie Network Corporation, Fuzhou, China. From Oct. 2018 to Oct. 2019, he worked as a visiting professor at the department of communications and networking, School of Electrical Engineering, Aalto University, Finland.His research interests include software-defined network, network function virtualization, 5G network, network security, machine learning and cloud computing. He serves as the reviewer of many famous journals on network technology, including IEEE Network, IEEE/ACM Transactions on Networking, ACM/Springer Mobile Networks and Applications, Transaction on Network and Service Management, Transaction on Mobile Computing. He had directed more than 8 research projects and has published more than 30 papers.

Workshop 2

Summary: How does the Brain/Mind work at an algorithmic level? Currently, deep learning has shown tremendous technological power in different areas, there is an unsettling feeling of a lack of “conceptual” understanding of why it works and to what extent it will work in each area. Meanwhile, there is a lot of excitement and achievement about deep learning study. The workshop on Deep Learning Theory and Applications (DLTA) aims to bring together theorists and practitioners to develop an understanding of deep learning from the algorithmic view of brain functioning, characterizing the class of functions that can be learned, coming up with the right learning architecture that can learn multiple functions and concepts. In addition, the workshop aims to attract papers for different applications with deep learning, especially focusing on image/video processing and data-driven self-tuning control. In this sense, the workshop on DLTA will provide a forum for the presentation and discussion of novel research ideas or actual deployments focused on the development of both the novel theories and the advanced applications related to Deep Learning. We encourage prospective authors to submit their research papers on the subject of both theoretical approaches and practical case reviews on deep learning.

Keywords: Deep learning, Theoretical analysis, Image/video processing, Intelligent control, Conceptual explanation

Prof. Wanquan Liu received his MSc degree in Control Theory and Operation Research from the Chinese Academy of Science in 1988, and a Ph.D. degree in Control Engineering from Shanghai Jiaotong University in 1993. He once worked in Australia for 28 years at different Universities. Meanwhile, He held the ARC Fellowship, U2000 Fellowship, and JSPS Fellowship. He once worked at Curtin University for 21 years doing research on machine learning and computer vision. He joined Sun Yat-sen University in 2021 as a Professor in the School of Intelligent Systems Engineering. Now he is the Editor-in-chief for the international journal of Mathematical Foundation of Computing while on the editorial board for other seven international journals. He has attracted research funds from different resources for over 15 million RMB, his current research interests include intelligent control systems, large-scale pattern recognition, and smart home for the aged.

Prof. Huafeng Wang received his Master's degree in Software Engineering from Beihang University in 2004, and a Ph.D. degree in Computer Science from Beihang University in 2011. He is currently an Associate Professor in the Department of Information Technology at the North China University of Technology. His current research interests include unmanned AI, deep learning, enforcement learning, and computer vision.

Workshop 3

Summary:Evolutionary computation technique has been widely used for addressing various challenging problems due to its powerful global search ability. There are many complex optimization tasks in the fields of deep learning and machine learning such as neural architecture search, hyper-parameter search, feature selection, feature construction, etc. This workshop aims to collect original papers that develop new evolutionary computation techniques to address any kind of deep learning and machine learning tasks. For all the aforementioned, we kindly invite the scientific community to contribute to this workshop by submitting novel and original research related but not limited to the following topics:

Neural Architecture Search (NAS)Evolutionary Deep Learning/Evolving Deep LearningEvolutionary Deep Neural NetworksEvolutionary Computation for Deep Neural NetworksEvolutionary Neural Architecture Search (ENAS)Deep NeuroevolutionNeural Networks with Evolving StructureAutoMLEvolutionary Computation for Neural Architecture SearchHyper-parameter Tuning with Evolutionary ComputationHyper-parameter OptimizationEvolutionary Computation for Hyper-parameter OptimizationEvolutionary Computation for Automatic Machine LearningEvolutionary Transfer LearningDifferentiable NASHybridization of Evolutionary Computation and Neural NetworksLarge-scale Optimization for Evolutionary Deep LearningEvolutionary Multi-task Optimization in Deep Learning
EvolNAS
NASNet
Neuroevolution
Self-adaptive Evolutionary NAS
Hyper-parameter Tuning with Self-adaptive Evolutionary Algorithm
Evolutionary Computation in Deep Learning for Regression/Clustering/Classification
Full-space Neural Architecture Search
Evolving Neural Networks
Automatic Design of Neural Architectures
Evolutionary Neural Networks

Feature Selection, Extraction, and Dimensionality Reduction on High-dimensional and Large-scale Data
Evolutionary Feature Selection and Construction
Multi-objective Feature Selection/Multi-object classification/ Multi-object clustering
Multi-task optimization, Multi-task learning, Meta learning
Learning Based Optimization
Hybridization of Evolutionary Computation and Cost-sensitive Classification/Clustering
Bi-level Optimization (BLO)
Hybridization of Evolutionary Computation and Class-imbalance Classification/Clustering

Numerical Optimization/Combination optimization/ Multi-objective optimization
Genetic Algorithm/Genetic Programming/Particle Swarm Optimization/Ant Colony Optimization/Artificial Bee Colony/Differential Evolution/Fireworks Algorithm/Brain Storm Optimization
Classification/Clustering/Regression
Machine Learning/Data Mining/Neural Network/Deep Learning/Support Vector Machine/Decision Tree/Deep Neural Network/Convolutional Neural Network/Reinforcement Learning/Ensemble Learning/K-means
Real-world Applications of Evolutionary Computation and Machine Learning, e.g. Images and Video Sequences/Analysis, Face Recognition, Gene Analysis, Biomarker Detection, Medical Data Analysis, Text mining, Intrusion Detection Systems, Vehicle Routing, Computer Vision, Natural Language Processing, Speech Recognition, etc.

Yu Xue received the Ph. D. degree from School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, China, in 2013. He is a professor at School of Computer and Software, Nanjing University of Information Science and Technology. He was a visiting scholar in the School of Engineering and Computer Science, Victoria University of Wellington, New Zealand (2016.8-2017.8). He was a research scholar in the Department of Computer Science and Engineering, Michigan State University, the United States of America (2017.10-2018.11). His research interests include Deep Learning, Evolutionary Computation, Machine Learning, and Computer vision.

Bing Xue is currently a professor in Artificial Intelligence, and Program Director of Science in School of Engineering and Computer Science at VUW. She has over 300 papers published in fully refereed international journals and conferences and her research focuses mainly on evolutionary computation, machine learning, classification, symbolic regression, feature selection, evolving deep neural networks, image analysis, transfer learning, multi-objective machine learning.

Prof. Xue is currently the Chair of IEEE Computational Intelligence Society (CIS) Task Force on Transfer Learning & Transfer Optimization, Vice-Chair of IEEE CIS Evolutionary Computation Technical Committee, Editor of IEEE CIS Newsletter, Vice-Chair of IEEE Task Force on Evolutionary Feature Selection and Construction and Vice-Chair IEEE CIS Task Force on Evolutionary Deep Learning and Applications. She also served as associate editor of several international journals, such as IEEE Computational Intelligence Magazine and IEEE Transactions on Evolutionary Computation.

Yong Zhang received the BSc and PhD degrees in control theory and control engineering from the China University of Mining and Technology in 2006 and 2009, respectively. He is a professor with the School of Information and Electronic Engineering, China University of Mining and Technology. His research interests include intelligence optimization and data mining.

Adam Slowik was born in Warsaw, Poland, in 1977. He received the Ph.D. degree in electronics with distinction from the Department of Electronics and Computer Science, Koszalin University of Technology, Koszalin, Poland, in 2007, and the Dr. Habil. (D.Sc.) degree in computer science from the Department of Mechanical Engineering and Computer Science, Czestochowa University of Technology, Czestochowa, Poland, in 2013. Since October 2013, he has been an Associate Professor with the Department of Electronics and Computer Science, Koszalin University of Technology. His research interests include soft computing, computational intelligence, machine learning, and bioinspired global optimization algorithms and their applications. He is an Associate Editor for the IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS.

Ferrante Neri (M’03–SM’19) received a Laurea degree (BSc + MSc) and a PhD in Electrical Engineering from the Technical University of Bari, Italy, in 2002 and 2007 respectively. In 2007, he also received a PhD in Scientific Computing and Optimization from University of Jyvaskyla, Finland. From the latter institution, he received the DSc degree in Computational Intelligence in 2010. Dr. Neri moved to De Montfort University, United Kingdom in 2012, where he was appointed Reader in Computational Intelligence and in 2013, promoted to Full Professor of Computational Intelligence Optimisation. Since 2019 Ferrante Neri moved to the School of Computer Science, University of Nottingham, the United Kingdom. His research interests include algorithmics, hybrid heuristic-exact optimisation, memetic computing, differential evolution, and membrane computing. Dr. Neri published nearly 200 items including two editions of the textbook “Linear Algebra for Computational Sciences and Engineering”.

Workshop 4

Summary:Visual understanding and multi-modality representation fusion are essential to intelligent scene perception. With the rapid progress in machine learning technologies, there are tons of remarkable advances in intelligent scene understanding, whose performance and application fields are extended greatly. However, the complexity of scene could be a challenge for efficient perception. For some applications as automatic drive, pedestrian re-identification and robot tracking, the performance and efficiency are typically affected by disturbances in the natural scene. How to efficiently combine information from visual and other modalities to enhance the robustness of perception systems under accidental perturbation and complexity issues is crucial and meaningful.
This workshop aims to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of intelligent scene perception. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.

Keywords: Computer Vision, Multi-modality Representation Learning, Intelligent Scene Perception and Application, Person re-identification, Deep Learning.

Zhigang Liu received a Ph.D. degree in Computer Resources and Information Engineering from Northeast Petroleum University, and was a visiting scholar with the Department of Electrical & Computer Engineering at National University of Singapore from 2018 to 2019. As a member of IEEE and CCF, he is currently the Department Director of Computer Science and Engineering, Northeast Petroleum University. His research interests include machine learning, computer vision, especially, data/label- and computation-efficient deep learning for visual recognition. He participated in the National Natural Science Foundation, Natural Science Foundation of Heilongjiang Province, Scientific and Technological Projects of Petro-China, and Youth Science Foundation of Northeast Petroleum University. Based on these projects, he published many academic papers.

Workshop 5

Summary:The growth of Internet services has promoted the popularity of many large-scale data-intensive applications (e.g. video conferences, cloud services, and financial data analysis) recently. As a result, large-scale networks are increasingly experiencing burst flows and the traditional network architecture exposes three major flaws: complex architecture, high resource redundancy, and limited network management. Though the resource utilization can be improved by leveraging some state-of-the-art technologies, such as software-defined networking and edge computing, current resource management strategies cannot perfectly deal with the unpredictable traffic demand and ensure the Quality of Services (QoS) provided to tenants, which hurts the system scalability and robustness. This workshop aims to bring together researchers from academia and industry, presents the latest research results in areas such as cloud computing, edge computing, cloud-edge synergy, 5G, data center networks, and software-defined networks. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with ‘paper title_workshop title’.

Keywords: Cloud Computing, Edge Computing, Cloud-Edge Synergy, 5G, Data Center Networks, Software-Defined Networks, NFV-enabled Networks

Gongming Zhao received a Ph.D. degree in computer software and theory at the University of Science and Technology of China (USTC) in 2020. He was a visiting scholar with the State University of New York at Buffalo (UB). He works as a research associate professor at the University of Science and Technology of China (USTC). His research interests include cloud computing, edge computing, and software-defined networks. He authored or co-authored more than 20 papers in famous journals and conferences, including the IEEE/ACM Transactions on Networking (ToN), IEEE Journal on Selected Areas in Communications (JSAC), IEEE Transactions on Parallel and Distributed Systems (TPDS), IEEE Transactions on Communications (TCOM), IEEE Conference on Computer Communications (INFOCOM), IEEE International Conference on Network Protocols (ICNP), IEEE/ACM International Symposium on Quality of Service (IWQoS), etc.

Workshop 6

Summary: With the rapid development of urbanization, the data generated by the city shows an explosive growth trend. How to analyze these data effectively, find the pattern inherent in the data is a good assist to the planning and decision-making of the city. However, these data are faced with various problems such as diversified sources, diversified formats, sparse information content, strong timeliness, and implicit user sensitive information. How to solve these challenges, realize the co-construction of data-driven smart cities, and promote the stable and healthy development of the city, has very broad research value and application prospects.
This workshop is dedicated to attracting researchers from academia or industry, the original research results in theoretical or experimental method are welcomed. The topics in the workshop included but are not limited to:
Ubiquitous data perception and collection
Multi-source heterogeneous data management
Data analysis and mining
Data driven user feature analysis
Data sharing and data security
Smart city services
The title of the submission email is suggested to name with “paper title_workshop title". Warmly welcome to your join.

Keywords: Ubiquitous data perception, data analysis, data security, user feature, smart city

Prof. Yuanbang Li got the Master's degree in School of Information Engineering from Zhengzhou University, and got the Ph.D. degree in School of Computer Science from Wuhan University. He is an Associate Professor working at Zhoukou Normal University. His research interests include ubiquitous computing, requirements engineering, location-based social network and smart city. Dozens of the research papers he published have been indexed by SCI and EI.

Workshop 7

Summary: Visual analysis and machine learning are two important techniques in most academic, industrial, business, and medical applications. Visual analysis including image/video processing and computer vision systems is closely related to various fields, such as automatic navigation, intelligent robots and smart healthcare, etc. Machine learning has obtained great success in vision, graphics, natural language processing, gaming, and controlling.
The workshop aims to bring together the leading researchers and developers from both academia and industry to discuss and present their latest research and innovations on the theory, algorithms, and system technologies that can substantially improve existing image/video processing and computer vision based on machine learning and artificial neural network. We encourage prospective authors to submit related distinguished research papers on this subject, including new theoretical methods, innovative applications and system prototypes.

Keywords: machine learning, deep learning, image/video processing, computer vision, pattern recognition, artificial neural network

Lei Chen received the B.Sc. and M.Sc. degrees in electrical engineering from Shandong University, Jinan, China, and the Ph.D. degree in electrical and computer engineering from University of Ottawa, Ontario, Canada. He is currently an Associate Professor with the School of Information Science and Engineering, Shandong University, China. His research interests include image processing and computer vision, visual quality assessment and pattern recognition, machine learning and artificial intelligence. He was the principal investigator of projects granted from the National Natural Science Foundation of China, National Natural Science Foundation of Shandong Province, China Postdoctoral Science Foundation, etc. He has published more than 30 papers on top international journals and conferences in recent years including IEEE TIP, Signal Process., ICME, etc. He was awarded the Future Plan for Young Scholars of Shandong University. He served for the ICIGP 2021 and 2022 as Publicity Co-Chair.

Workshop 8

Summary:Large volumes of spatio-temporal data are increasingly collected and benefited to diverse domains, including transportation, urban optimization, community detection, climate science, etc. How to feed these large-scale spatio-temporal data into many practical applications is a promising problem. Spatio-temporal data can, for example, predict the crowd flow in a city’s subway network through analyzing the city-wide commuting data. This investigation betters the formulation of city’s transportation planning. Another example is to forecast the trajectory. Transportation managers are interested in the picture of the future trajectories across the entire road network, and estimate how would it affect other regions. Such studies have gained extensive attentions to address such issue to improve the quality of living conditions.

The goal of this workshop is to attract researchers from academia and the industry to investigate wonderful technics of mining knowledge from spatio-temporal data. We invite all researchers and practitioners to participate in this event and share, contribute, and discuss the emerging challenges in spatial and spatiotemporal data mining.

Keywords: spatio-temporal data mining, geospatial data, time-series model, multi-modal spatiotemporal datasets, spatial constraints, data mining, sequential pattern mining, artificial intelligence.

Prof. Yongshun Gong received his Ph.D. degree from University of Technology Sydney. He is an associate professor at School of Software, Shandong University, China. His principal research interest covers the data science and machine learning, in particular, the following areas: urban computing; spatiotemporal data mining; urban flow prediction; recommender system and sequential pattern mining. He has published about 30 papers in top journals and refereed conference proceedings, including the IEEE T-KDE, IEEE T-NNLS, IEEE T-CYB, IEEE T-MM, Pattern Recognition, NeurIPS, KDD, MM, CIKM, AAAI, IJCAI, etc.

Workshop 9

Summary:With the development of machine learning, In particular, the widely successful application of deep learning, cyberspace security can be solved by machine learning. For example, the detection of inferior chip or hardware Trojan horse, pseudo-base station detection, virtualization security, credit card fraud and so on can be abstracted as classification problems; Device identity authentication, abnormal social network account detection, network intrusion detection and so on can be abstracted as clustering problems; User identity authentication, malicious/abnormal/intrusion detection, forensics analysis, network public opinion and other issues can be abstracted as both classification problems and clustering problems.

Keywords: Machine Learning; Deep learning; Pattern recognition; Intrusion Detection; Malicious code classification

Haixia Long, Professor, Master's Tutor, Doctor of Engineering, Major in Computer Application. Hainan Nanhai Famous Masters, Hainan Province High-level Top-notch Talents. Three textbooks and two monographs have been published by her. She Presided over 1 National Natural Science Foundation under research, 3 Hainan Natural Science Foundation projects and 1 Hainan Education Department project. As the first finisher, she won one third prize of Hainan Provincial Science and Technology Progress Award, and as the first finisher, she won one third prize of Hainan Provincial University Outstanding Scientific Research Achievement Award; She has published more than 30 research papers.

Workshop 10

Summary:Due to stronger learning ability, deep learning techniques, especially convolutional neural networks (CNNs) are developed in text, image and video processing. However, deep learning techniques usually increase the depth of CNNs to extract more accurate features. However, that may cause difficult training and huge computational costs. To address this issue, attention methods are presented. They are used to extract salient information to accelerate training efficiency and improve performance in image, text and video processing. Thus, studying attention methods are very important meaning, which makes this workshop be proposed. Also, aim of this workshop helps researchers to summary attention methods, i.e., self-attention, Transformer for multimedia applications and it brings together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of attention technology and understand how governance strategy can influence it. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”.

Keywords: Attention, Transformer, Deep Learning, CNN, multimedia

Chunwei Tian received his Ph.D degree in Computer Application Technique from Harbin Institute of Technology, in Jan, 2021. He is currently an Associate Professor with the School of Software, Northwestern Polytechnical University. Also, he is a member of National Engineering Laboratory for Integrated Aerospace Ground-Ocean Big Data Application Technology. He was a Research Fellow with the Department of Electrical Engineering, City University of Hong Kong.
He is a member of Shenzhen Key Laboratory of Visual Object Detection and Recognition. His research interests include image restoration and deep learning. He has published over 30 papers in academic journals and conferences, including IEEE TNNLS, IEEE TMM, IEEE TSMC, NN, Information Sciences, KBS, PRL, ICASSP, ICPR, ACPR and IJCB. He has four ESI highly-cited papers, three homepage papers of the Neural Networks, one home paper of the IEEE T-MM, one excellent paper in 2018 and 2019 for the CAAI Transactions on Intelligence Technology. Also, his three codes are rated as the contribution codes of the GitHub 2020. His two paper techniques are integrated on the iHub and Profillic. Besides, he is an associate editor of the Journal of Electrical and Electronic Engineering and International Journal of Image and Graphics, a guest editor of Mathematics, a workshop chair of ICCBDAI 2021, a PC of the IEEE DASC 2021, ACAIT 2021, IEEE DASC 2020, a PC Assistant of IJCAI 2019, a reviewer of some journals and conferences, such as the IEEE TIP, the IEEE TII, the IEEE TMM, the IEEE TSMC, the NN, the CVIU, the Neurocomputing, the Visual Computer, the PRL and the SPL, etc.

Wenqi Ren received the Ph.D. degree from Tianjin University, Tianjin, China, in 2017. He is an Associate Professor with the Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China. From 2015 to 2016, he was supported by the China Scholarship Council and working with Prof. M.-H. Yang as a joint-training Ph.D. student with the Electrical Engineering and Computer Science Department, University of California at Merced, Merced, CA, USA. His research interests include image processing and related high-level vision problems. Dr. Ren received the Tencent Rhino Bird Elite Graduate Program Scholarship in 2017 and MSRA Star Track Program in 2018.

Dongwei Ren received the Ph.D. degree in computer application technology from the Harbin Institute of Technology, Harbin, China, in 2017. From 2018 to 2021, he was an Assistant Professor with the College of Intelligence and Computing, Tianjin University. He is currently an Associate Professor with the School of Computer Science and Technology, Harbin Institute of Technology. His research interests include computer vision and deep learning.

Qing Gao received a Ph.D. degree in Pattern Recognition and Intelligent Systems from State Key Laboratory of Robotics, University of Chinese Academy of Sciences, joint training of doctoral students of University of Portsmouth. He is working in The Chinese University of Hong Kong, Shenzhen. His research interests include Deep Learning, Machine Vision, and Human-robot Interaction. He hosts the National Natural Science Foundation, Natural Science Foundation of Guangdong Province, and Shenzhen Technology Research Project. Based on these projects, he published more than 20 academic papers.

Qi Zhang received his Ph.D. from Harbin Institute of Technology in 2021. She is an assistant professor at Harbin Institute of Technology, Weihai. She has published paper more than 10 papers. Her research interests include machine learning, big data techniques, technology innovation.

Di Yuan received his Ph.D. degree in computer applied technology from Harbin Institute of Technology in 2021. Currently, he is a lecturer at Guangzhou Institute of Technology, Xidian University, Guangzhou, China. He was sponsored by China Scholarship Council as a Visiting Ph.D. student at the Faculty of Information Technology, Monash University Clayton Campus, Australia from 2019 to 2021, working with Prof. Xiaojun Chang. His current research interests include object tracking, machine learning, self-supervised learning, and active learning.

Huale Li, is a Ph.D. candidate in computer science at Harbin Institute of Technology, Shenzhen, China. He received the Master degree in Circuits and Systems at Lanzhou University, China in 2017. His research interests include computer game, reinforcement learning, and machine learning. He participated in National Natural Science Foundation, Natural Science Foundation of Guangdong, key fields R&D project of Guangdong Province and CCF-Tencent Open Fund. He is a member of PINGAN-HITsz Intelligence Finance Research Center. He has published many academic journal papers in recent years.

Workshop 11

Summary:By combining deep learning and reinforcement learning techniques, deep reinforcement learning (deep RL) achieves big successes in a lot of complex decision-making tasks, particularly in games, such as Atari games, the game of Go, and even StarCraft II. A deep RL agent learns like people do, taking in high-dimensional raw data, such as image and sensor input, and refining its predictions and decisions through trial and error. Recently, multi-agent systems attract great attention because of a wide range of potential applications, and they also bring a lot of interesting problems and great challenges, such as distributed learning problem and communication problem among the agents. Another interesting problem is how to understand the behavior of the deep RL agents and improve their interpretability.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in related field of deep learning, reinforcement learning, multi-agent systems, and distributed learning. We encourage prospective authors to submit related research papers about theoretical approaches or practical case studies. Please name the title of the submission email with “paper title_workshp title”. The scope of this workshop includes, but is not limited to the following topics:
• Deep learning
• Reinforcement learning
• Reward structures for learning
• Multi-agent learning
• Distributed learning systems
• Collective intelligence
• Practical algorithms for games
• Behavioral models of games
• Interpretability of deep RL
• Applications
Keywords: Deep Learning, Reinforcement Learning, Mulit-agent, Game Theory

Dr. Chang Wang is currently an assistant professor at the College of Intelligence Science and Technology, National University of Defense Technology (NUDT), China. He obtained the PhD degree on robot learning from Delft University of Technology (The Netherlands) in 2016, the master degree on applied mathematics from NUDT in 2009, and the bachelor degree on mathematics from University of Science and Technology of China (USTC) in 2007. His research interests include reinforcement learning, developmental robotics, multi-agent systems, UAV swarms, human-robot teamwork, augmented reality, etc. He has published more than 40 peer-reviewed papers, including IEEE Transactions on Industrial Informatics (TII), Swarm and Evolutionary Computation(SWEVO), Knowledge-based Systems(KBS), Chinese Journal of Aeronautics(CJA), Neurocomputing, Robotics and Autonomous Systems (RAS) , JAAMAS, IROS, ACML, et al.

Dr. Dong Yin is currently an associated professor of the College of Intelligence Science and Technology, National University of Defense Technology (NUDT), China. He obtained his master degree and PhD degree from Northwestern Polytechnical University (China) at 2007 and 2011. He was a visiting scholar at the University of Massachusetts during 2008-2010. He has published more than 50 peer-reviewed journal and conference papers. His research interests include UAV air combat, UAV swarm networking, UAV relative localization and information security, embedded systems, FPGA, et al.

Workshop 12

Summary:Intelligence agriculture has become an area of growing interest due to the growing importance of the role of agriculture in China recently. Big Data and computer vision techniques have been widely used in the area of agriculture to effectively increase crop yield and save costs. Big Data techniques can enable the huge amount of data transfer between different devices, discover potential rules from massive data, and make reasonable forecasts. Moreover, computer vision techniques can take advantage of visual information for multiple applications, such as detecting diseases, crop yield estimation.
This workshop aims to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of intelligence and, how big data and computer vision techniques can influence them. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”.

Keywords: Intelligence Agriculture, Big Data, Computer Vision, Artificial intelligence

Bin Liu serves as an associate professor at college of Information Engineering of Northwest A&F University in China. He received a Ph.D. degree in computer science and technology at Xi’an Jiaotong University in China, in 2014. He worked as a member at Key Laboratory of Agricultural Internet of Things of Ministry of Agriculture and Rural Affairs and Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service. His research interests include computer Vision, intelligent agriculture, deep learning and agricultural pest monitoring and early warning. He participated in projects supported by National Natural Science Foundation, National Key Projects, National Key Research and Development Project, Natural Science Foundation of Shaanxi Province. Based on these projects, he published many academic papers. Moreover, he serves as a reviewer for Computers and Electronics in Agriculture, Frontiers in Plant Science, IEEE Trans. on Computers, the Journal of Supercomputing, etc.

Workshop 13

Summary:Sentiment Analysis refers to the process of analyzing, processing and extracting subjective texts with emotional color by using natural language processing and text mining techniques. At present, the research of text sentiment analysis covers many fields including natural language processing, text mining, information retrieval, information extraction, machine learning and ontology, etc. which has attracted the attention of many scholars and research institutions. In recent years, it continues to become one of the hot issues in the field of natural language processing and text mining. This Workshop includes but is not limited to the following research directions:
(1) Performance improvement strategies for traditional text sentiment analysis.
(2) Fine-grained text sentiment analysis.
(3) Implicit emotion analysis.
(4) Multi-entity sentiment analysis.
(5) Fusion of text emotion analysis and brain science.
The aim of the symposium is to bring together the findings of researchers in academia and industry. Another goal is to present and share the latest research in the field of text sentiment analysis. Prospective authors are encouraged to submit relevant outstanding research papers on the topic of theoretical approach and practical case review. Please name the title of the submission email "Paper title_Workshop Title".

Keywords: Text sentiment analysis, implicit sentiment analysis, fine-grained sentiment analysis, brain science, robustness

Duan Liguo received a Ph.D. degree in Computer Science and Technology from Taiyuan University of Technology, Taiyuan, China, in 2011. CCF senior member, member of Chinese Information Society of China. His current research interests include AI,natural language processingand Software Engineering.
He participated in the National Natural Science Foundation, National Key Projects, National Key Research and Development Project, Natural Science Foundation of Shanxi Province, Tackling Key Scientific and Technological Problems in Shanxi Province. Based on these projects, he published many academic papers.

Workshop 14

Summary:Current Cyberspace are increasingly becoming pervasive, complex, and ever-evolving due to factors like enormous growth in the number of network users, continuous appearance of network applications, increasing amount of data transferred, and diversity of user behaviors. Understanding traffic and behaviors in such networks is a difficult yet vital task for network management but recently also for cybersecurity purposes. Security big data analysis can, for example, enable the analysis of the spreading of malicious software and its capabilities or can help to understand the nature of various network threats including those that exploit users’ behavior and other user’s sensitive information. On the other hand cyberspace governance can help to assess the effectiveness of the existing countermeasures or contribute to building new, better ones. Recently, cyber security big data analysis have been utilized in the area of economics of cybersecurity e.g. to assess ISP “badness” or to estimate the revenue of cybercriminals.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of cybersecurity technology and understand how governance strategy can influence it. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”.

Keywords: Cybersecurity, Cyberspace Governance, Security Big Data, Artificial intelligence, International Strategy for Cyberspace

Wenjie Chen received his B. Eng. degree and M. Eng. degree in mechanical engineering from Beijing University of Aeronautics and Astronautics in 1985 and 1988 respectively, and Ph.D. degree in mechatronics from Nanyang Technological University, Singapore, in 1999. Currently, he is a professor and doctoral supervisor with the School of Electrical Engineering and Automation, Anhui University, Hefei, China; the expert of "100 Talents Plan" of Anhui Province, the senior member of IEEE, and the executive deputy director of "Anhui Province Engineering Laboratory of Human-Machine Integration Systems and Intelligent Equipment". He is now leading a team to engage in the research of flexible assembly and intelligent robotic manipulation & grasping.
Prof. CHEN has a more than 30 years’ experience in the research, design and development of industrial automation equipment, with particular expertise in the application of "Mechanical Intelligence" technologies to solve adaptive problems in precision assembly and robot control. He has presided or participated over 5 projects funded by National Natural Science Foundation of China and dozens of robotic projects funded by Singapore government and industrial partners, with a cumulative project funding of more than RMB 50 million, publishing more than 90 papers in refereed journals and conferences. His research achievements have been successfully applied in the production line or assembly process of the famous international enterprises such as Rolls-Royce, Philips and PSA Singapore.

Workshop 15

Summary:In the last decade, as the Internet evolved into an artificial intelligence for large-scale online services, the contradiction between information explosion and personalized service is a core task of recommender systems to undertake. Fortunately, there have been many tools, algorithms and frameworks in recommender systems, which are searching through large volume of dynamically generated information to provide users with personalized content and services. As such, recommender systems are not only central to academic attentions but also highly indispensable in some industries.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in related field of machine learning, deep learning, reinforcement learning, meta-learning, transfer learning and any novel industrial frameworks for recommender systems. We encourage prospective authors to submit related research papers about theoretical approaches or practical case studies. Please name the title of the submission email with “paper title_workshop title”. The scope of this workshop includes, but is not limited to the following topics:
•Social RS
•Deep Learning-based RS
•Cold-start problem in RS
•Point-of-interest (POI) RS
•Efficient RS
•Exploitation-Exploration RS
•Explainability RS
•CTR prediction
•Knowledge Graph for RS
•Conversational RS
•Industrial RS
Privacy&Security RS

Keywords: recommender system, information retrieval, machine learning, deep learning, artificial intelligence

Zhongsheng Qian received a Ph.D degree in Engineering from the School of Computer Engineering and Science of Shanghai University, in 2008. Now, he is a professor and doctoral supervisor at Jiangxi University of Finance and Economics. His research interests include machine learning, algorithm optimization, recommender system, intelligent software engineering and so on.
He has presided the National Natural Science Foundationof China, the China Postdoctoral Science Fund, the Jiangxi Provincial Natural Science Foundation, etc. He has published more than 50 papers and one monograph, as well as guided graduate students to win more than 20 awards in various competitions.

Workshop 16

Lin Tao, received a Ph.D. degree in Computer Application Major from Northeast University, worked in Huawei Hisilicon semiconductor company, participated in the development of Kirin chip, and has rich experience in the research and development of artificial intelligence chip. Participated in many national projects, obtained many patents and published many papers.

Workshop 17

Summary:Artificial Intelligence is going to influence the way we work and live in the future. Innovative applications created with the use of artificial intelligence will determine our quality of life, our health, our longevity, and the way we work, where we work, and how we work. Blockchain with its immutability, transparency, consensus, decentralised distributed ledgers, enhanced security, and peer-to-peer network nodes will grow and get embedded in technologies and applications of the future. After the success of blockchain technology with bitcoins and other cryptocurrencies, a number of blockchain platforms have been developed each improving and getting more efficient and innovative than the previous ones. Blockchain uses “smart contracts” to ensure trust and transparency and to verify and validate a record of transactions (block) that it is going to add to other (chain) records in the database (distributed ledger). The smart contract is a set of codes (a program) that automatically and autonomously executes when a transaction has satisfied predetermined conditions. This is where (in the smart contract) artificial intelligence can be used to make the smart contracts more intuitive, adaptive and intelligence by adjusting the smart contracts accordingly when faced with transactions that it has not encountered before.

The Call for Papers is to see artificial intelligence and blockchain as supplementing each other, not competing. The intention is to use them to augment the weaknesses of the other and exploit its strength to promote innovative opportunities. The whole idea of the convergence of artificial intelligence and blockchain is to do whatever was not possible with each in isolation. To be the future driving force of the industry (4th Industrial Revolution), creativity, and innovative applications as well as the challenges of these converged technologies. Artificial intelligence is a powerful tool that can be used for malicious activities as well. For example, hackers when launching a cyber-attack can use artificial intelligence to learn the mitigation cyber security techniques being used. Then, they can program their artificial intelligence to write malicious codes based on what it has learnt to bypass the mitigation strategies and breach cyber security. And as the artificial intelligence learns more, it becomes better and will need some extraordinary countermeasures. These are some of the challenges of converged technologies. Then there are challenges of many of our jobs being replaced with AI.

Keywords: Convergence, Artificial Intelligence, Blockchains, Machine Learning, Intelligent Systems, Smart Contracts, Predictive Analytics, Distributed Ledger Technology, Super Converged Technologies
Suggested Topics:
AI and Blockchain for Big Data
AI and Blockchain for Cyber Security
AI and Blockchain for Industry 4.0
AI and Blockchain for Digital Transformations
AI and Blockchain for Metaverse
AI and Blockchain for Education
AI and Blockchain for Cloud Computing
AI and Blockchain for Mobile Edge Computing
AI and Blockchain for Smart Cities
AI and Blockchain for Sustainable Development
AI and Blockchain for Multi-Agent Systems
AI and Blockchain for the Internet of Things
AI and Blockchain for 5G Networks

Professor Dr. Sam Goundar is an International Academic having taught at twelve different universities in ten different countries. He is the Editor-in-Chief of the International Journal of Blockchains and Cryptocurrencies (IJBC) - Inderscience Publishers, Editor-in-Chief of the International Journal of Fog Computing (IJFC) - IGI Publishers, Section Editor of the Journal of Education and Information Technologies (EAIT) - Springer and Editor-in-Chief (Emeritus) of the International Journal of Cloud Applications and Computing (IJCAC) - IGI Publishers. He is also on the Editorial Review Board of more than 20 high impact factor journals. He has 105 publications in total. These research publications appear in journals and as chapters in books (many of them indexed by Scopus and Web of Science). He has worked and currently working (writing/editing) on fifteen book projects. Ten have been published and the other five are expected to be published in 2022.
A number of PhD and Master’s Students have successfully completed their thesis under his supervision. He is also on the PhD examination panel for many international universities and is regularly called upon by international universities to review and examine PhD thesis. His research students and colleagues are spread across internationally and so are his research topics. As a researcher, apart from Blockchains, Cryptocurrencies, e-Services, Digital Transformations, Fog Computing, Industrial Internet of Things, Enterprise Systems, Big Data, Mobile Cloud Computing, Cloud Computing, Educational Technologies, Dr. Sam Goundar also researches on Management Information Systems, Technology Acceptance Model (TAM), Massive Open Online Courses (MOOC), Gamification in Learning, Cyber Security, Artificial Intelligence, Internet of Things, Network Intrusion Detection, Data Security Analysis, e-Sports, ICT in Climate Change, ICT Devices in the Classroom, Using Mobile Devices in Education, e-Government, and Disaster Management. He has published on all these topics.

Workshop 18

Summary:Low-quality scene text images, including low-resolution, blurred, low-contrast, noisy, etc., are often seen in natural scenes such as traffic signs captured by mobile phones. Detecting and Recognizing low-quality text images is a fundamental and important step towards many downstream text-related applications, including image retrieval, card recognition, license plate recognition, auto-driving, etc. However, it is still a great challenge because they lose detailed content information.
This workshop aims to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of scene text detection and recognition how to enhance low-quality scene text images for them. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”

Zhu Xiaobin, received his Ph.D. degree from Institute of Automation, Chinese Academyof Sciences, Beijing, China, in 2013.He is currently an Associate Professor at the School of Computer & Communication Engineering, University of Science and Technology Beijing. His research interests include machine learning,pattern recognition, video and image analysis, etc. He has published over 20 papers in top journals and refereed conference proceedings, including the IEEE T-NNLS, IEEE TITS, Pattern Recognition, AAAI, ICCV, CVPR, etc.

Workshop 19

Summary:In recent two decades, China has become a factor cyberspace power, with the world’s largest population of Internet users and e-commerce transactions. Particularly after Xi Jinping took office in 2012, China’s involvement in global governance has increased significantly. Therefore, in the opaque and volatile domain of cyberspace, it is essential to keep lines of diversified discussions open to constructively and proactively find areas where we multi-laterally have shared interests.
Cyberspace can be characterized into three layers – the infrastructure, the application, and the cores. At different levels, cyberspace shall be treated distinctively and require different understanding between each actor, which differs at each level. As a comprehensive workshop discussion, there are following topics over cyber sovereignty that are worth looking into:
• The application of intelligence under the new generation communication technology
• City personality evaluation based on SNS
• Trust transitivity in complex networks
• Cyberspace narratives for global interconnectivity based on content analysis

Keywords：Communication, cyberspace governance, societal Systems，trusttransitivity，application of intelligence, global interconnectivity

Yancong Su was born in Fujian, China PRC in 1987. He received two B.A. degrees in Japanese including Media Studies form the double degree program between Northeast Electric Power University and Yamanashi Eiwa University in 2009, and his M.A. degree and Ph.D. degree in Computers and Communication from Kobe University in 2011 and 2014.
He worked as an outside lecturer at the Faculty of Media and Arts in Otemae University and the Faculty of Home Economics in Kobe Women's University from 2013 to 2014. He was employed as a full-time lecturer in Xiamen University of Technology from August 2014. Now, he is working as an associate professor of Digital Media Technology course in School of Design Art. His research interests include soft computing, human computer interaction and new media art.

Workshop 20

Summary:Wind-induced vibration has complex characteristics such as turbulence, randomness, and coupling, and is a common aero-instability phenomenon. In studying the effects of complex surface structures and different arrangements of bluff bodies on aero-instability, the traditional methods based on wind tunnel experimental and computational fluid dynamics (CFD) technology require a lot of time, labor, and cost, and can no longer meet the needs of processing a large amount of data. Machine learning technology can make decisions or predictions on unknown events by learning a large data set and has broad application prospects in the field of engineering, such as applying machine learning to structural health monitoring and using machine learning to predict wind strength. Using machine learning techniques to study the aerodynamic instability of complex structures is a difficult but crucial subject. Recently machine learning has been used in the study of aerodynamic instability, such as the prediction of energy harvesting for wake galloping vibrations.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results of machine learning techniques in the field of wind-induced vibration and to understand the impact of machine learning techniques on future research in the field of aerodynamic instability.We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshop title”.

Keywords：Aerodynamic instability, machine learning, computational fluid dynamics,Fluid solid coupling

WANG JUNLEI, received a Ph.D. degree in School of Power Engineering at the Chongqing University. He was a visiting scholar at the Department of Mechanical Engineering, University of Auckland. He is the director of the Rotordynamics Branch of the Chinese Mechanical Engineering Society. His research work is mainly focused on the energy harvesting from flow induced vibration with the aim of powering low consumption electronics, including wireless sensors and sensors networks.
He was twice awarded grants from the National Natural Science Foundation of China (NSFC), and also received Natural Science Foundation of Excellent Youth of Henan Province. He has published over 80 SCI papers in international and world-leading journals (more than 50 during the past three years) and has over 10 ESI High-Cited Papers or Hot papers. He has been among the most influential 100 papers in China (2019), once the most influential researchers of Springer (2020), and one of his articles has received the award of Applied Physics letters (2021). His recent research paper - high-performance piezoelectric wind energy harvester with Y-shaped attachments, which was published and selected as the most cited paper in Energy Conversion and Management journal, has been highly cited by some world-leading professors and journals.

Workshop 21

Summary:Manufacturing is the foundation of the real economy and the key to high-quality economic development. In the global competition facing the era of digital economy, it has become the strategic consensus of all countries to accelerate the integrated development of digital technology and real economy, and develop advanced manufacturing with higher level and more competitive relying on digital technology. Smart factory is a general term for "comprehensive intelligence" of manufacturing enterpriseswith integration of intelligent technology, digital technology, information technology.Based on content networking equipment monitoring, data acquisition, to complete dynamic monitoring data, based on the multi-sensor data fusion, integration within the plant personnel, machinery, equipment and infrastructure implementation of real-time management, coordination between multiple systems and control. On this basis, production is managed in a more detailed and dynamic way to achieve the "Smart" state, which helps enterprises to achieve workshop standardization, equipment status visualization, real-time monitoring of product quality, intelligent control of energy consumption level.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of Multi-sensor Data Fusion technology and understand how governance strategy can influence it. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”.

Keywords：Multi-sensor Data Fusion, IOT, Smart Factory, Equipment ManagementandControl, Energy Management and Control

GAO FAN, Chief engineer of Chongqing Chuanyi Automation Co.,Ltd., Assistant to the General Manager and minister of engineering department of ChongQing ChuanYi Software Co.,Ltd., member of National Technical Committee on Industrial Process Measurement and Control of Standardization Administration(SAC/TC124/SC10), ISO 18436-2 International Vibration Analyst, 《Metallurgical Industry Automation》Young Editorial Board. Recent years have published almost 20 EI and Chinese core papers on engineering applications. As the first inventor, he has obtained 5 authorized patents (4 invention patents) and reviewed 3 national standards. Participated in several scientific research projects of Ministry of Industry and Information Technology, Chongqing Economic and Information Commission, China Silian Instrument group Co. LTD, participated in several engineering projects of China Baowu Group, Angang Group, Shougang Group and Hunan Iron and Steel.

Workshop 22

Summary:The increasing availability of large and complex data sets to the research community triggers the need to develop more advanced and sophisticated data and text mining techniques to exploit and mange these all kinds of data. For example, high throughput technologies generate large data sets and new problems in bioinformatics. The volume of published research and the underlying knowledge base with unstructure text is expanding at an increasing rate. Among the tools that can aid researchers in coping with this information overload are text mining and knowledge extraction.
To provide a forum for data miners .data scientists and biomedical researchers. We will organize the international workshop on data and text mining in biomedicine, social computing, and knowledge engineering. This workshop includes a range of techniques of artificial intelligence and pattern recognition, such as biomedical data processing and analysis using machine learning, natural language processing, social computing, knowledge engineering, knowledge graphs.

Keywords：Biomedical data processing; Machine learning; Natural language processing ; Knowledge graphs; Knowledge engineering, Social computing

Lejun Gong received her PhD degree in Biomedical Engineering from Southeast University, P.R. China in 2012. Currently, she is an associate professor in the School of Computer Science at Nanjing University of Posts and Telecommunications, P.R. China. She worked as a member at the Jiangsu Key Lab of Big Data Security & Intelligent Processing. She is focused primarily on data and text mining, bioinformatics, and pattern recognition. And she has published about 30 papers in journals and conferences in these research areas. She is a member of Natural Language Processing Committee of Jiangsu Artificial Intelligence Society, a member of Jiangsu Bioinformatics Committee and a member of Natural Language Generation and Intelligent Writing Committee of Chinese Information Society of China. She has presided over and completed the National Natural Science Foundation of China, the Natural Science Foundation of Jiangsu Province, the Natural Science Foundation of Jiangsu Province, the Postdoctoral Foundation of Jiangsu Province, and the China postdoctoral Project successively.

Huakang Li, received his PhD degree in Computer Science from School of Computer Science and Engineering, University of Aizu in 2011. Currently, he is working as an associate professor at the School of Artificial Intelligence and Advanced Computing, XJTLU Entrepreneur College (Taicang).
From May 2011 to Sep. 2013, Dr. Li worked as a postdoctoral research fellow in the Department of Computer Science and Engineering, Shanghai Jiaotong University. During that period, he went to Ali Cloud Computing Ltd. as a visiting researcher to develop the National 863 Project. From Sep. 2013 to July 2020, Dr. Li was a lecturer at School of Computer Science, Nanjing University of Posts and Telecommunications.
Hie research interests are focused on artificial intelligence and big data mining, specifically natural language processing, social computing, knowledge engineering, knowledge graphs and the related domain applications. So far, he has published over60 academic journals and conference papers, and authorized more than 20 invention patents. He also serves as a reviewer of KBS, KAIS, AIHC and other journals.

Workshop 23

Summary:Summary: Nowadays, the world is moving toward digitalization. To communicate with one another, transfer money to anyone and to upgrade the knowledge is become very easy due to smartphone apps. Everyone is depend upon these apps to perform their daily routines. On daily basis, smartphone users download and install number of apps without the proper knowledge of the permissions that are required for its proper working. Cybercrooks are taking the advantage of these permissions and developed malware-infected apps and upload to official play store or third-party store for users. Smartphone users download and install these apps and become victim.

The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of smartphone security. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”.

Keywords：Smartphone Security, Security Big Data, Artificial intelligence, Android apps, Machine Learning.

Arvind Mahindru is an Assistant Professor in the Department of Computer Science and Applications, DAV University Jalandhar. He has received his B. Tech. degree from Punjab Technical University, Jalandhar in 2007 and M. Tech. degree from Dr. B R Ambedkar National Institute of Technology, Jalandhar in 2013. He has received his Ph.D. degree in “Dynamic Analysis Based Android Malware Detection using Machine Learning Techniques” from Dr. B R Ambedkar National Institute of Technology, Jalandhar in 2021. His research expertise is in smartphone security. His research areas also include software testing and quality assurance, model-driven development, empirical methods, and software maintenance. He has 13 years of teaching experience. He is also serving as a reviewer for various International Journals including IEEE and Springer.

Workshop 24

Summary:As a large-scale data acquisition method, mobile crowd sensing (MCS) has been widely used in smart city sensing, social sensing, battlefield situation sensing, space environment sensing, disaster scene sensing, intelligent low-carbon sensing, smart mine sensing, traffic situation sensing. In order to solve a series of general and personalized problems encountered in MCS, MCS platforms such as Crowdos, Ear Phone, Chimera, CreekWatch and Photocity have emerged. Using machine learning algorithm to analyze and mine the massive sensing data of the MCS platform can make the MCS platform more intelligent and optimized. Sensing data often are spatiotemporal data, include events, trajectories, time series, spatial maps and spatiotemporal grids. Mining useful information from spatiotemporal data is very important for many applications such as intelligent transportation, urban planning, processmining and so on. Traditional data mining methods have poor effect because of the spatiotemporal characteristics and high correlation characteristics of spatiotemporal data, and are overwhelmed with the increasing capacity of spatiotemporal data. Recently, deep learning technology with independent feature representation ability and powerful function approximation ability has achieved great success in spatiotemporal data mining.different application scenarios and spatiotemporal data types lead to different types of data mining tasks and problem expressions. Different deep learning models usually have different preferences for the types of spatiotemporal data, and have different requirements for the input data format, so it is necessary to classify spatiotemporal data.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of sensing data analysis and mining. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”.

Keywords：Mobile crowd sensing, Sensing Data Analysis and Mining, spatiotemporal Data Analysis and Mining, Deep Learning

Yu Qiancheng, received a Ph.D. degree in Computer Science and Technology from School of Computer Science at Northwestern Polytechnical University. Currently, he is an associate professor in the school of computer science in Northern MinZu University. His research interests include Pervasive computing, context-aware systems, Mobile social networks, Mobile Crowd Sensing, Graph Deep Learning ,etc.

Workshop 25

Summary:With the development of computer technology and intelligent hardware, the field of mobile robots has received increasing attention. Due to the complexity of industrial scenarios and the diversity of social needs, traditional robots have to adopt some emerging algorithms to achieve high-precision, robust and real-time positioning requirements for mobile robots. As its underlying technology, synchronous positioning and mapping technology, namely SLAM, has been widely used because of its autonomous perception and mapping capabilities. Although the research results of SLAM have been very fruitful, there are still many problems to be solved in the existing SLAM research schemes, both in terms of theoretical innovation and engineering applications. The innovation and engineering application of SLAM technology remains a very difficult and crucial task. For example, the information fusion and application of multiple sensors,the balance between real-time and accuracy and the adaptation of algorithms and hardware are all problems that need to be solved at present. The purpose of this issue is to bring together the research results and innovations of researchers in academia and industry, provide their own ideas and insights for the development of SLAM, and explore how to apply them to practical engineering. We encourage future authors to provide relevant outstanding research papers on these two topics: theoretical studies and practical application case discussions.

Keywords：SLAM, multi-sensor fusion, engineering applications, nonlinear optimization, image matching, information fusion

Ping He received the B.S. degree in automation from Sichuan University of Science and Engineering, China, the M.S. degree in control science and engineering from Northeastern University, China, and the Ph.D. degree in electromechanical engineering from the Universidade deMacau, Macao. From 2015 to 2021, he had successively served as an Adjunct Associate Professor for many institutions. He is currently a Professor with Huazhong Agricultural University, China. His research interests include robot, artificial intelligence, control theory, and control engineering. Dr. He serves as a Section Editor, an Academic Editor, a Lead Guest Editor, and an Associate Editor for many Journals. He is also a Reviewer Member for Mathematical Reviews of the American Mathematical Society.

Workshop 26

Summary:With the development of science and technology as well as the advancement of production technology, contemporaryequipment is increasingly developing towards large-scale, complex, automated and intelligent direction. Fault diagnosis andprognosis technology is an important method and necessary means to improve the system operation reliability and reduce the system operation risk.In order to ensure the safetyand reliability of equipment, the fault diagnosis and prognosis technology has received widespread attention and beenwidely used. Traditional statistical data-driven methods are obviously influenced by the choice of models. Machine learning haspowerful data processing ability, and does not need exact physical models and prior knowledge of experts. Therefore, machinelearning has a broad application prospect in the field of fault diagnosis and prognosis .
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of fault diagnosis and prognosis technology and understand how machine learning strategy can influence it. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshp title”.The scope of this workshop includes, but is not limited to the following topics:

Condition monitoring and fault diagnosis with machine learning
Fault detection, diagnosis and prediction with machine learning
Fault tolerant control and safety control with machine learning
Safety analysis, design and evaluation with machine learning
Reliability assessment, prediction and design with machine learning
Prognosisand health management with machine learning
Intelligent maintenance technology with machine learning
Residual life prediction technology with machine learning
Computer vision aided Condition monitoring and fault diagnosis with machine learning
Deep neural network-based designs for complex equipment systems
Transfer learning- and reinforcement learning-inspired deep neural networks with application in complex equipment systems
Domain adaptation model-based deep learning framework aided fault diagnosis and prediction for complex equipment systems
Application and case analysis

Keywords：Machine learning, Condition monitoring ,Fault diagnosis and Prognosis, Fault-tolerant control, Safety and Reliability,Big data analysis, System safety ,predictive maintenance, transfer learning ,deep learning.

Zhao-Hua Liu (Senior member,IEEE) , received Ph.D. degree in automatic control and engineering from Hunan University, Changsha, China, in 2012. During 2015–2016, he was a Visiting Researcher with the Department of Automatic Control and Systems Engineering, University of Sheffield, Sheffield, U.K. He is currently aProfessor of AutomaticControl and Systems with the School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, China. He was a selected as a Hu-Xiang Excellent Young Talents of Hunan Province of China in 2018.His current research interests include intelligent information processing and control of wind turbines , computational intelligence and learning algorithms design, machine learning aidedfault diagnosis and prognosis ,parameter estimation and control of permanent-magnet synchronous machine drives, and condition monitoring and fault diagnosis for electric power equipment.Dr. Liuhas published a monograph in the field of Biological immune system inspired hybrid intelligent algorithm and its applications, and authored and co-authored more than 50 research papers in refereed journals and conferences, including IEEE TRANSACTIONS/JOURNAL/MAGAZINE. He is a regular reviewer for several international journals and conferences.

Lei Chen received the Ph.D. degree in automatic control and electrical engineering from the Hunan University, China, in 2017. He is currently a Lecturer with the School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, China. His current research interests include deep learning, network representation learning, information security of industrial control system and big data analysis.

Ming-Yang Lv,received the Ph.D. degree in automatic control and engineering from the Hunan University, China, in 2020. He is currently a Lecturer with the School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan, China. His current research interests include deep learning, network representation learning,condition monitoring and fault diagnosis for electric power equipments.

Workshop 27

Summary:Environment perception and semantic mapping technologies in LiDAR point clouds are critical for unmanned ground vehicles (UGVs) and mobile robots. Accurate 3D reconstruction and semantic segmentation of surrounding environment provides significant information for local path planning. The Simultaneous Localization and Mapping (SLAM) and Lidar Odometry and Mapping (LOAM) systems enable accurate and real-time autonomous terrain modeling to represent the geometric structures of dynamic environment, which facilitate the path-planning tasks. The growing interest in environment perception for UGVs has sparked interest in deep neural network researches of semantic segmentation, instance segmentation, and object recognition from LiDAR point clouds.

The aim of this workshop is to find robust methods of 3D scene modeling, autonomous exploration of unknown scenes, environmental understanding system, etc. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.

Keywords：Mobile Robot, Sensor Fusion, Terrain Reconstruction, Environment Perception, Semantic Segmentation, 3D Object Recognition

Prof. Wei Song is currently a professor at the School of Information Science and Technology, and vice dean of International School, North China University of Technology, China. He is also a Ph.D. Supervisor at Department of Multimedia Engineering, Dongguk University, Korea. He received B.S. degree in software engineering from Northeast University, China in 2005, M.S. and Ph.D. degrees in multimedia engineering from Dongguk University, Korea in 2008 and 2013, respectively.His current research interests include Environment Perception, 3D Object Recognition, Semantic Segmentation, 3D Reconstruction, and LiDAR applications. In current years, he published 2 textbooks about 3D Programming, 35 SCI papers, and 2 authorized patents. He finished more than 10 projects as PI, including National Natural Science Foundation of China (61503005), High-Potential Individuals Global Training Programs (2019-0-01585 and 2020-0-01576), etc.

Workshop 28

Summary:Snail rice noodle is the most famous snack with local characteristics in Liuzhou, Guangxi. In the past two years, snail powder has ushered in an online explosion, with a significant increase in both e-commerce sales, search and hot discussion trends. The construction of Snail rice noodle industry big data platform provides an important decision-making basis for the construction of Liuzhou Snail rice noodle industry big data center, accurate pulse market dynamics and industrial development. The article is mainly divided into three parts. The first is the business process of B2C and B2B orders. The business under these two application scenarios is different. It can be expected that with the development of business and the needs of marketing strategy, the business will become more and more complex. Therefore, we need to automatically improve business services according to data. The application service open platform in snail powder platform can provide support for business expansion according to business needs. Automatic improvement of business or intelligent decision-making of business need machine learning algorithm to give strategies according to industrial data; Secondly, there are several business roles corresponding to the application open platform, which mainly include application developers, service providers and self-developed applications. The platform can establish tasks to continuously test the interface, including test tracking, interface test and performance test. It is compatible with mainstream standards, facilitate the linkage between development and test teams, accelerate high-quality software delivery and promote the improvement of overall efficiency; The last is the setting of the application platform, which mainly includes application management, providing a convenient test service environment and providing data-based service computing.

Keywords：Snail rice noodle；big data；Social Media Monitor；Business intelligence

Yiming Wu, is an associate professor and master's tutor in the School of Software of Guangxi University of Science and Technology. He is the executive director of Liuzhou Data Intelligence Engineering Technology Research Center, the executive vice president and chief data officer of Liuzhou Big Data Industry Development Association, the digital economy expert of Liuzhou Big Data Development Bureau, the project evaluation expert and standardization consultant of Liuzhou Two Integration Promotion Center, and the project evaluation expert of service industry of Liuzhou Modern Trade Commission.Born in 1973, he graduated from Yunnan University with a master's degree in computer application, a visiting scholar in the UK, and a doctoral student. 2007 - present, he has been engaged in research and development of intelligent software body, software engineering, distributed computing and big data application in Guangxi University of Science and Technology. He has a deep understanding and engineering experience in the design and application of Internet, cloud computing and big data application technologies in the industry.
Scientific research projects presided over, participated in and completed in recent years: "Semantic-oriented flexible workflow mechanism" (National Natural Science Foundation of China); "Sugar enterprise resource planning management system" (Science and Technology Tackling Project of Guangxi Science and Technology Department); "Business information discovery platform based on intelligent agent" (Science and Technology Tackling Project of Guangxi Science and Technology Department); "Smelting enterprise resource planning management platform" (Scientific Research and Technology Development Project of Liuzhou Economic Committee) Technology Development Project) system; planning, design and development of community informatization in Liuzhou City (Liuzhou Information Industry Bureau); intelligent e-commerce platform oriented to behavioral characteristics (National Small and Medium Enterprises Innovation Fund), intelligent diagnosis system of Chinese medicine based on cloud computing (Liuzhou Science and Technology Bureau), knowledge base and reasoning system of Chinese medicine based on hadoop (Liudong National High-tech Zone), cloud computing in industrial development of Guangxi Application pre-research (autonomous region industry and information commission), data application support platform of Liuzhou health commission (Liuzhou health commission), urban health service station system based on hadoop (autonomous region industry and information commission special information service), Guangxi mobile Huizhou enterprise industrial cloud (Guangxi mobile), China. Liuzhou snail noodle trading big data platform and other projects.

Workshop 29

Summary:The next stage of development in Machine Learning is Automated Machine Learning! It’s a godsend for people who are not experts in the complicated world of Machine Learning and also for experienced data scientists and analysts. Automated Machine Learning allows these data scientists to create Machine Learning models with higher efficiency and productivity while having top-notch quality.So a tool like AutoML can be used to train high-quality custom machine learning models for classification, regression, and clustering without much knowledge of programming. It can easily deliver the right amount of customization without a detailed understanding of the complex workflow of Machine Learning. It can also help in using machine learning best practices while saving time and resources. One such example of AutoML is automated machine learningprovided by Microsoft Azure that you can use to build and deploy predictive models.
Keywords：Machine Learning, Automated Machine Learning, Data Science, Artificial intelligence, Learning Models

SUBHANI SHAIK, received a Ph.D. degree in Machine Learning techniques for signal classification from Acharya Nagarjuna University, joint training of doctoral students of VIT University. He worked as a Research member of Sreenidhi Institute of Science & Technology (Autonomous), Hyderabad, India. His research interests include Machine Learning, Artificial Intelligence, and Deep Learning.
He participated in the National and International conferences in India. He published IEE Transactions, Springer Publication journal papers. He received Elsevier Award for Best researcher. He acts as Journal editor and reviewer for different SCI and Scopus journals.

Workshop 30

Summary：

Optimization in Multi-agent system plays a prominent role in many applications including online learning, game theory, GANs, etc. As such there has been a lot of interest in understanding the dynamic behavior of learning process in multi-agent systems. Recently the dynamical systems involved in these learning processes are discovered to be complicated and even chaotic. We recommend further investigation in the uncertainty phenomenon in multi-agent learning. This topic also concerns non-convergence or convergence to undesirable solutions of optimization algorithms.

The aim of this workshop is to bring experts from different subjects (game theory, artificial intelligence, computer vision, learning theory, dynamical systems, statistics, etc.) together, and share the recent discoveries in complicated and unpredictive phenomenon that might be interpreted or understood from perspectives of statistics and dynamical systems. Both experimental and theoretical works are recommended to be submitted to the workshop.

Keywords：

Artificial intelligence, Multi-agent systems, Dynamical systems, Statistics, Online learning, Game theory.

WANG XIAO, received a Ph.D. in Mathematics from University at Buffalo. He is now an assistant professor at Shanghai University of Finance and Economics. Before joining SUFE, he was a postdoc at Singapore University of Technology and Design. His research includes theoretical aspects of machine learning (learning representation, non-convex optimization, and game theory).

Workshop 31

Summary：

With the explosive growth of visual data, how to automatically understand the visual semantics becomes an urgent demand. As a machine learning and artificial intelligence technique that can imitate the way humans understand the world, deep learning has achieved significant breakthroughs for almost all of visual fields, e.g., image classification, object detection, segmentation, etc. However, there are still many issues to be discussed, e.g., class imbalance, data deficiency, network lightweight, etc.

The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of deep learning for visual understanding, especially visual detection and recognition. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshop title”. Warmly welcome to your join.

Keywords：Deep learning, Visual understanding, visual detection, recognition

Dr. Yi Liu received a Ph.D. degree in Control Theory and Control Engineering from Xidian University. He once studied in Lancaster University and University of Warwick as a visiting scholar. He is currently working at Changzhou University, China. His research interests include saliency detection, few-shot object detection, 3D point cloud analysis, digital twin, etc. He was awarded grants from the National Natural Science Foundation of China and Natural Science Foundation of Jiangsu Province.

Dr. Biao Yang received a Ph.D. degree in Instrument Science and Engineering from Southeast University. He once studied in University of California, Berkeley as a visiting scholar. He is currently working at Changzhou University, China. His research interests include semantic segmentation, action prediction, trajectory prediction, etc. He was awarded grants from the National Natural Science Foundation of China and Natural Science Foundation of Jiangsu Province.

Pro. Dr. Hai Wang received a Master and Ph.D. degree in Instrument Science and Engineering from Southeast University. He once studied in Michigan State University and Hong Kong University as a visiting scholar. He is currently working as a full professor at Jiangsu University, China. His research interests include 2D/3D Object detection, semantic segmentation, trajectory prediction for intelligent vehicles, etc. He is awarded the Outstanding Scientific and Technological Talent Award in China's Auto Industry (3-4 persons per year) and has published more than 50 papers (more than 20 papers in IEEE trans.) and have project fundings of more than 5 million yuan.

Dr. Yining Hua is currently a UK Lecturer (Assistant Professor) at the School of Natural Computing Sciences, University of Aberdeen, U.K., and an honorary researcher at the University of Glasgow, U.K. She received her Ph.D. degree from the Department of Computer Science, Loughborough University, U.K., in 2020. Her research interests include computer vision (e.g., semantic segmentation, Generative adversarial network, etc.), AI/ML-powered autonomous systems, and future-generation networks (e.g., fog/edge computing, IoT, etc.).

Summary：

Deep convolutional neural networks have performed well for visual understanding via extracting discriminative regions. Recently, the capsule networks proposed by Hinton have been known to learn the scene equivariance for robust visual understanding via digging into the part-whole relationships, which find the associated parts of their familiar whole object for object recognition and detection. There are many issues to be discussed for the part-whole relational visual understanding, e.g., 1) how to design the lightweight capsule routing algorithm for exploring the part-whole relationships; 2) how to embed the part-whole relational information in different visual understanding tasks.

The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the filed of capsule network design and part-whole relationships for visual understanding. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews. Please name the title of the submission email with “paper title_workshop title”. Warmly welcome to your join.

Keywords：Capsule Networks, Part-whole relationships, visual understanding

Title：Software Defined Network based on Machine Learning

Chair: Prof. Zhaogang Shu, Fujian Agriculture and Forestry University, China

Title：Deep Learning Theory and Applications(DLTA)

Chair 1: Prof. Wanquan Liu, Sun Yat-sen University, China

Chair 2: Prof. Huafeng Wang, North China University of Technology, China

Title：Evolutionary Computation for Deep Learning and Machine Learning

Chair 1: Prof. Yu Xue, Nanjing University of Information Science & Technology, China

Chair 2: Prof. Bing Xue, Victoria University of Wellington, New Zealand

Chair 3: Prof. Yong Zhang, China University of Mining and Technology, China

Chair 4: Prof. Adam Slowik, Koszalin University of Technology, Poland

Chair 5: Prof. Ferrante Neri, University of Nottingham, UK

Title：Computer Vision for Intelligent Scene Perception

Chair: Prof. Zhigang Liu, Northeast Petroleum University, China

Title：Challenges and Opportunities in Cloud Computing and Edge Computing

Chair: Prof. Gongming Zhao, University of Science and Technology of China

Title：Ubiquitous perception data analysis in smart city

Chair: Prof. Yuanbang Li, Zhoukou Normal University, China

Title：Image Processing and Computer Vision based on Machine learning and Deep learning

Chair: Prof. Lei Chen, Shandong University, China

Title：Spatio-temporal Data Mining

Chair: Prof. Yongshun Gong, Shandong University, China

Title： Intelligent Computing in Cyberspace Security

Chair: Prof. Haixia Long, School of Information Science and Technology Hainan Normal University, China

Title： Attention methods based CNNs for multimedia applications

Chair 1: Prof. Chunwei Tian, Northwestern Polytechnical University, China

Chair 2: Prof. Wenqi Ren, Sun Yat-sen University, China

Chair 3: Prof. Dongwei Ren, Harbin Institute of Technology, China

Chair 4: Prof. Qing Gao, Harbin Institute of Technology, China

Member 1: Prof. Qi Zhang, Harbin Institute of Technology, China

Member 2: Dr. Di Yuan, Xidian University, China

Member 3: M.Sc. Huale Li, Northwestern Polytechnical University, China

Title： Multi-agent Deep Reinforcement Learning in Games

Chair 1: Dr. Chang Wang, National University of Defense Technology (NUDT), China

Chair 2: Dr. Dong Yin, National University of Defense Technology (NUDT), China

Title： Big Data and Computer Vision for Intelligence Agriculture Summary

Chair: Prof. Bin Liu, Northwest A&F University, China

Title: Text Sentiment Analysis

Chair: Prof. Liguo Duan, Taiyuan University of Technology, China

Title: Security Big Data and Governance for Cyberspace

Chair: Prof. Wenjie Chen, Anhui University, China

Title： Artificial Intelligence Booms Recommender Systems

Chair: Prof. Zhongsheng Qian, Jiangxi University of Finance and Economics, China

Title： Security Big Data and Governance for Cyberspace

Chair: Dr. Lin Tao, Huawei Hisilicon semiconductor company, China

Title： Convergence of Artificial Intelligence with Blockchains: Challenges and Opportunities

Chair: Prof. Sam Goundar, RMIT University, Australia

Title： Low-quality Scene Text Detection and Recognition

Chair: Assoc. Prof. Xiaobin Zhu, University of Science and Technology Beijing

Title： Intelligent communication technologies, and cyberspace governance in the dynamics of societal systems

Chair: Prof. Yancong Su, Xiamen University of Technology

Title： Machine Learning for Aero-Instabilities

Chair: Dr. Junlei Wang, Chongqing University

Title： Multi-sensor Data Fusionin IOT Device: Applications for Smart Factory Equipment and Energy Management

Chair: Gao Fan, Chongqing Chuanyi Automation Co.,Ltd

Title： Data and text mining in biomedicine, social computing and knowledge engineering

Chair 1: Assoc.Prof. Lejun Gong, Nanjing University of Posts and Telecommunications

Chair 2: Huakang Li, XJTLU Entrepreneur College

Title： Security and privacy challenges in smartphone

Chair: Assoc.Prof. Arvind Mahindru, DAV University

Title： Mobile Crowd Sensing Data Analysis and Mining via Deep Learning

Chair: Assoc. Prof. Qianchen Yu, Northern MinZu University

Title： Research and Implementation of Mobile Robot SLAM

Chair: Prof. Ping He, Huazhong Agricultural University, China

Title： Machine Learning Based Fault Diagnosis and Prognosis Methods for Complex Equipment System

Chair 1: Prof. Zhao-Hua Liu, Hunan University of Science and Technology

Chair 2: Dr. Lei Chen, Hunan University of Science and Technology

Chair 3: Dr. Ming-Yang Lv, Hunan University of Science and Technology

Title： LiDAR Applications to Environment Understanding and 3D Reconstruction

Chair: Prof. Wei Song, North China University of Technology

Title： The Application of Big Data Engineering and Computing in the Upgrading of Traditional Industries - Taking Liuzhou Conch Industry as an Example

Chair: Assoc.Prof. Yiming Wu, Guangxi University of Science and Technology

Title： Automated Machine Learning

Chair: Dr. SUBHANI SHAIK, Acharya Nagarjuna University

Title: Uncertainty and Chaos in Multi-agent Learning

Chair: Assit. Prof. Wang Xiao, Shanghai University of Finance and Economics, China

Title：Deep Learning for Visual Understanding

Chair 1: Dr. Yi Liu, Changzhou University, China

Chair 2: Dr. Biao Yang, Changzhou University, China

Chair 2: Dr. Hai Wang, Jiangsu University, China

Chair 4: Dr. Yining Hua, University of Aberdeen, U.K