Title: Multimodal Information Intelligent Processing Technology and Its Applications
Summary:
Multimodal information processing is developed based on single-media information processing such as text, image, and audio. The existing methods for processing single-media data are the basis for multimodal data processing. Research content specific to multimodal information processing focuses on modeling, acquisition, fusion, semantic metrics, analysis, and multimodal information retrieval. Many research results show that information processing algorithms and methods based on multimodal concepts often yield better performance and results than traditional methods. In content-based multimedia information retrieval, for the semantic gap problem in content-based video and audio retrieval, using textual information that is co-occurring or co-occurring with video and audio data to perform multimodal semantic analysis and similarity metrics is a very effective method to overcome the semantic gap problem. The semantic gap problem is common in cross-media information processing tasks. The semantics of the processed information objects, whether based on episodic semantics (denotational semantics) or connotational semantics (associative semantics) concepts, are not fully or finally expressed within the scope of single media information. Multimodal information processing methods provide new ideas and methods for solving this problem.Therefore, multimodal information inellegent processing is still under demand in both the new algorithms and the experience of applications. New algorithms, new appilications, even the improvements of the existed algorithms, might increase the capability of the sysytem such as the accuracy, percision, recall, and so on. Meanwhile, their applications in solving real-world problems in many areas such as image processing, pattern recognition, computer vision, natural language processing, et. al. are also important and would be a guide and experiential materials for new applications.
This workshop aims to bring together the latest research progress of academic and industry researchers, such as “text classification, text mining, sentiment analysis, video/image processing, video/image coding, video/image classification, video/image recognition, video/image understanding, speech processing techniques, speech recognition, speech synthesis, multimodal retrieval techniques, cross-modal retrieval" and their applications and so on. We encourage prospective authors to submit related distinguished research papers on the subject of multimodal information intelligent processing technology and its applications.
Key words: Text classification, text mining, sentiment analysis, video/image processing, video/image coding, video/image classification, video/image recognition, video/image understanding, speech processing techniques, speech recognition, speech synthesis, multimodal retrieval techniques, cross-modal retrieval.
Chair：Prof. Kurban Ubul, Xinjiang University, China
Kurban Ubul, Professor, Doctoral supervisor, Director of China Computer Federation (CCF)and China Image and Graphics Society(CISG), Vice Chairman of Urumqi branch ofCCF, Deputy Secretary General of Technical Committeeon Pattern Recognition and Machine Intelligenceof Chinese Automation Association (CAA-PRMI), member of Computer Vision TechnicalCommittee(CCF-CV)and Artificial Intelligence and Pattern Recognition Technical Committee (CCF-AI)of CCF, member of Document Analysis and Recognition Technical Committee of China Graphics and Image Society (CISG-DIAR), member of Pattern recognition TechnicalCommittee (CAAI-PR) and multilingual intelligent information processing Technical Committee (CAAI-IMLIP) of Chinese Association for Artificial Intelligence, senior member of CCF, member of IEEE, IAPR, ACM and IAENG, Director of Department of Electronics, School of Information Science and Engineering, Xinjiang University. He is reviewer of TPAMI, Neurocomputing, IEEE THMs,IET biometricsand other journals. Served as General Chair of NLPAI2020/ NLPAI2021/ NLPAI2022/MLPAO2023, Local Chair of NCIG 2020/CPCC2022/CCFAI2023, Area Chair of PRCV2019/ IJCB 2021 TPC chair of CCBR2018. He has hold the subproject of China's National Key R & D projects, 4 projects of National Natural Science Foundation of China, and more than 10 other projects, published more than 200 papers,10patents,more than 50 vomputer software copyrights, and more than 20 awards at the provical and minidterial level.
Title: Deep and Wide Applications of Intelligent Technologies in Education
Summary:
The development of intelligent technologies has opened countless possibilities in many industries. The field of education is taking a frontier position in the deep application of intelligent technologies The latest technologies such as virtual reality, augmented reality, learning analytics, big data analysis and processing, intelligent interaction and human-computer interfaces can find their respective pioneering application revenues in education. Significant and meaningful innovations and breakthroughs are just in the corner for such applications to transform education in both educational and technological sense.
This workshop provides a platform for cutting-edge discussions on the application and challenges of intelligent technologies in the education field, offering the possibility of transforming our theories and technologies in education with both depth and width. Potential topics include, but are not limited to:
·Artificial Intelligence in Education
·Virtual/Augmented/Mixed Reality in Education
·Learning Analytics
·Big Data Analysis and Processing for Learning and Education
·Intelligent Tutoring Systems
·Human-Computer Interface
·Education Data Mining
Key words: Artificial Intelligence in Education, Virtual/Augmented/Mixed Reality in Education
Learning Analytics, Big Data Analysis and Processing for Learning and Education, Intelligent Tutoring Systems Human-Computer Interface, Education Data Mining
Chair：Prof. Longkai Wu, Central China Normal University, China
Longkai Wu is a professor and PhD supervisor at the National Engineering Research Centre for E-Learning & MOE Educational Informatisation Strategy Research Base, Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China. He holds a Doctor of Philosophy degree in Learning Science and Technology from Nanyang Technological University (NTU), Singapore. His research interests include Artificial Intelligence in Education, Virtual and Augmented Reality, Formal and Informal Learning, STEM, Learning by Inquiry, Information Technology and Policy in Education. He has led and co-led several Singapore National Research Foundation and Ministry of Education funded research projects totaling over S$3 million. He has led the publication of three Springer books and published over 80 international journal articles, international book chapters and top conference papers. He is also program committee member for international conferences organized by IEEE Technical Committee on Learning Technology, International AI & Education Society, Asia-Pacific Society of Computers in Education, and Global Chinese Society on Computers in Education.
Title: Big Data & Artificial Intelligence with Applications
Summary:
With the rapid development of science and technology and the rapid rise of Internet information technology, people get more and more effective information from the Internet, and people's life has been greatly facilitated. With the gradual innovation and development of information technology, artificial intelligence has been paid more attention and applied in people's life. Artificial intelligence technology is developed by analyzing the law of people's activities through intelligent technology. It has a great degree of application function in robots, control systems and simulation. In artificial intelligence technology, the application of big data technology can analyze the potential law of data from a large amount of data, so as to summarize a certain development law, and then promote the further development of artificial intelligence.
This workshop aims to bring together the latest research progress of academic and industry researchers, such as big data science and foundations, big data infrastructure, big data management, big data search and mining, big data learning and analytics, data ecosystem, big data applications, artificial intelligence and technology, natural language processing, expert systems, multi-agent systems, knowledge engineering, neural network theory and architectures, artificial intelligence in modelling and simulation and so on. We encourage prospective authors to submit related distinguished research papers on the subject of big data and artificial intelligence. Please name the title of the submission email with “paper title_workshop title”.
Key words: Big Data, Artificial Intelligence, Data Mining, Data Science, Natural Language Processing, Expert Systems, Multi-Agent Systems, Knowledge Engineering, Neural Network
Chair：Prof. Shan Liu, Communication University of China
Shan Liu is professor and Chair of Intelligent Science Department at Communication University of China. She received her Ph.D. degree from Texas A&M University, in United States. Now she is a committee member of Chinese Association for Artificial Intelligence, committee member of Chinese Institute of Electronics, committee member of Beijing Society of Image and Graphics, committee member of Association of Fundamental Computing Education in Chinese Universities, Member of China Automation Society, Member of Institute of Electrical and Electronics Engineers. She has served as a peer reviewer for series of IEEE Transactions and other high-level SCI journals.
Her main research areas include complex networks, intelligent tags, big data and artificial intelligence. In recent years, she has been invited to the University of California, National Laboratory of the United States, and other countries such as Brussels and Belgium, to give lectures and speeches, and has gained broad academic influence. She has presided over more than 30 research projects such as National Science Foundation and National Science and Technology Support Program, published more than 100 high-level academic papers, received many best paper awards, and applied for more than 30 patents of invention.
Summary:
In the past few years, pre-trained Large Language Models (LLMs), such as ChatGPT and GPT-4, have succeeded in various fields, such as natural language processing, computer vision, speech recognition, and graphic learning. The prospect of pre-training is to use the input data as the signal for the learning model without the need for specific labeled data so that it can be trained on a large scale.
Despite its outstanding performance in various tasks, there are still many unresolved issues. We will focus on introducing and discussing the latest technologies, open issues, challenges, and models in the field of pre-training, as well as technologies and applications in the pre-training field. Topics of interest include but are not limited to: advanced model architectures for language models; advanced algorithms for improving performance on diverse tasks; model transfer and compression techniques for LLMs; prompt Learning for LLMs; creative applications of LLMs in various domains, e.g., medical care, smart agriculture, education, and financial systems; natural language understanding and content generation by pre-trained language models, etc.
Key words: Natural Language Processing, pre-trained language model, large language model, content generation.
Chair：Assoc. Juan Wen, China Agricultural University
Juan Wen received her B.E.degree in information engineering and Ph.D.degree in signal and information processing from Beijing University of Posts and Telecommunications. She was a visiting scholar at the University of Florida in 2019 and 2020. She is now an associate professor in the College of Information and Electrical Engineering, China Agricultural University. Her research interests include artificial intelligence, machine learning, natural language processing, and information security.
Summary:
Visual analysis and machine learning are two important techniques in most academic, industrial, business, and medical applications. Visual analysis including image and video processing systems is closely related to various fields, such as internet of things, 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 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. Please name the title of the submission email with “paper title_workshop title”.
Key words: machine learning, deep learning, image processing, computer vision, pattern recognition, artificial neural network.
Chair：Assoc. Prof. Lei Chen, Shandong University
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, CSAI2022 and MLCCIM2022 as Technical Chair or Publicity Chair.
Summary:
Machine vision is a rapidly developing field that encompasses a wide range of technologies aimed at enabling computers to extract meaningful information from images and videos. With advances in image processing, pattern recognition, computer vision, and artificial intelligence, machine vision techniques have shown tremendous potential in various application domains, including industry, healthcare, and agriculture etc. The effective use of machine vision technologies can lead to improved efficiency, accuracy, and reliability in these areas, as well as facilitate the development of innovative and intelligent solutions.
In the industrial sector, machine vision techniques play a crucial role in automating processes such as inspection, quality control, material property prediction, new material discovery and robot guidance. In healthcare, machine vision has been employed for medical image analysis, diagnosis, and treatment planning, as well as patient monitoring and care. In agriculture, machine vision can be used for crop monitoring, phenotype, and precision farming.
Despite the remarkable progress in machine vision research and applications, several challenges remain to be addressed. These include developing robust and efficient algorithms, handling noisy and incomplete data, dealing with complex and diverse environments, and ensuring the scalability and adaptability of machine vision solutions.
This workshop aims to bring together researchers and practitioners from academia and industry to discuss the latest advancements and challenges in machine vision and its intelligent applications in industry, healthcare, and agriculture etc. Topics of interest include, but are not limited to: image processing, pattern recognition, object detection, object tracking, image segmentation, 3D vision, deep learning for computer vision, industrial inspection, quality control, material discovery, robot guidance, medical image analysis, patient monitoring, crop monitoring, phenotype, precision farming, and other intelligent applications, intelligent systems. We encourage prospective authors to submit original research papers on the subject of machine vision and its intelligent applications in industry, healthcare, and agriculture etc.
Key words: Machine vision, image processing, pattern recognition, object detection, object tracking, image segmentation, 3D vision, deep learning, industrial inspection, quality control, material discovery, robot guidance, medical image analysis, patient monitoring, crop monitoring, crop phenotype, disease detection, precision farming, intelligent system
Chair 1：Prof. Taohong Zhang, University of Science and Technology Beijing
Taohong Zhang, Professor of University of Science and Technology Beijing, Deputy Director of the Women's Science and Technology Workers' Committee of the Beijing Graphics and Imaging Society, Committee member of the Smart Medical Special Committee of the Chinese Artificial Intelligence Society; She is reviewer of more than five top journals, and guest editor of Applied Science journal special issue. She has hold and participated in multiple scientific research projects of the Study Abroad Return Fund, the National Key R&D Program, the National Science and Technology Support Program, the National Natural Science Foundation of China, and industry research projects. Published more than 60 search papers, authorized 13 national invention patents which got converted 1.12 million yuan. Received the honorable title of the most beautiful scientific and technological worker of the Beijing Society of Image Graphics in 2022, and the Excellent Paper Award of the Smart Medical Conference of the Chinese Artificial Intelligence Society in 2022.
Chair 2：Assoc. Prof. Xi Guo, University of Science and Technology, Beijing
Beijing Key Laboratory of Knowledge Engineering for Materials Science
Xi Guo has been engaged in scientific research in the field of database technology and knowledge engineering for a long time, conducting research in areas such as spatiotemporal data query optimization, trajectory data mining and vehicle scheduling, fine-grained spatiotemporal knowledge graphs, fairness in machine learning algorithms, automatic generation of standards and machine-readable standards.
She has led national, provincial, and university-level longitudinal projects, including the National Natural Science Foundation of China for Young Scholars, the Fundamental Research Funds for the Central Universities Additionally, she has participated in over ten collaborative projects with enterprises. Research achievements have been published in well-known journals such as "The VLDB Journal" (CCF-A), "World Wide Web Journal" (CCF-B), as well as reputable international conferences like APWeb. Students under her guidance have received the "Sa Shixuan Outstanding Student Paper Award" at the 37th CCF China National Database Conference (NDBC 2020).
She serves as the Beijing University of Technology representative of the China Computer Federation (CCF), a member of the CCF Communication Work Committee (awarded the title of Outstanding membor in 2021), and the CCF Database Committee. She also served as the Co-Chair for the organization of academic workshops in the field of big data and cloud computing, such as the "International Workshop on Intelligent Information Mining and Management." Furthermore, she is a reviewer for journals including the Journal of Software, Journal of Computer Science and Technology, and WWW Journal.
Summary:
Artificial Intelligence (AI) has ushered in a transformative era within the healthcare domain, introducing advancements in diagnostics, treatment planning, and operational efficiency. Concurrently, Extended Reality (XR) technologies, encompassing Virtual Reality (VR) and Augmented Reality (AR), have revolutionized medical education by offering immersive, risk-free environments for skill enhancement and training. Moreover, the amalgamation of AI and XR has paved the way for groundbreaking innovations in telemedicine, personalized medicine, and the cultivation of patient-centric care.
The convergence of AI and XR has ushered in patient-centric healthcare approaches, with AI tailoring treatment plans through patient data analysis and XR enhancing patient engagement and comprehension. This workshop aims to gather cutting-edge research that explores the dynamic interplay between these transformative technologies, reshaping the healthcare landscape. Topics include examining AI's multifaceted applications in healthcare, from diagnostics to administrative streamlining, delving into the evolution of medical education through XR-driven surgical simulations and skill enhancement, investigating the role of AI and XR in telemedicine, emphasizing their impact on remote consultations, monitoring, and diagnostics, and finally, exploring AI-driven personalized medicine and XR-enabled patient experiences, which emphasize elevated patient engagement and personalized care plans.
In essence, this workshop embarks on an exploration of the burgeoning frontier where AI and XR technologies converge to reinvent healthcare delivery, patient care, and medical training. It is a unique opportunity to immerse oneself in insightful discussions, share knowledge, and network with leaders in the field. We invite you to join us in shaping the future of healthcare by harnessing the limitless potential that AI and XR offer. Together, we can chart a transformative course for the healthcare industry, enriching the lives of patients and healthcare professionals alike.
Key words: AI in Healthcare, XR, VR, AR, Medical Education and Training, Patient Engagement, Remote Monitoring, Healthcare Innovation, Surgical Simulations, Digital Twins, Metaverse, Diagnostics Advancements
Chair：Assoc. Prof. LEE BOON GIIN， University of Nottingham Ningbo, China
Lee Boon Giin (Bryan) holds the position of Associate Professor at the School of Computer Science, University of Nottingham Ningbo China. He serves as the Head of the Human-Computer Interaction Lab at UNNC and as the Head of the Human-Centric Multi-Sensing Lab within the Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute (CBI). Notably, he achieved recognition in 2022 by being listed among the top 2% of scientists by Stanford University. He is also an IEEE Senior Member and assumes the role of guest editor for Sensors. Bryan actively contributes as a reviewer to several influential journals, including IEEE IoT, IEEE Sensors, IEEE ITS, and IEEE HMS. His involvement in top conferences as an invited speaker, session chair, and TPC member highlights his significant contributions to the academic community. Over the past five years, he has engaged in numerous research projects, including a municipal key major program and more than five national, provincial, and municipal grants. He has over 70 co-authored papers, six patents, multiple software copyrights, and the receipt of six international best paper awards.
Summary:
Artificial Intelligence (AI) has ushered in a transformative era within the healthcare
Emotion is an important part of Human-Computer-Interaction, which has attracted the attention of many scholars. The external manifestations of emotion include speech fundamental frequency mode (pitch), speech content (text), facial muscle coding, electroencephalogram, heart rate, skin electricity and so on. The internal principle of emotion involves psychology and neurophysiology. These external manifestations of emotion often reflect some mental disorder or disease of the subject, such as obsessive-compulsive disorder (OCD), autism, depression, autism and so on.
Most of the existing researches use information modeling techniques such as Artificial Neural Network to model the external manifestations of emotion, and some researches involve multi-modal data. The research on the mechanism of emotion cognition and expression is also one of the hotspots, including the relationship between the occurrence of various neurological diseases and the pathological changes in the cortex of emotion perception. In addition, the technology of emotional human-computer-interaction has been developed greatly, such as emotion speech synthesis, automatic expression generation, etc. . However, the ability of AI to perceive and express emotions is not yet comparable to that of humans. On the one hand, because of the complexity of emotion, it is very difficult to obtain a large and high-quality data set of emotional external performance, on the other hand, the mechanism of emotional perception in the brain is still unclear, how to explain emotional expression is still a problem.
This Research Topic aims to study the neurophysiological principle of emotion and the coding of its external manifestations, Including but not limited to the following directions:
1. High-quality database of emotion external manifestations, such as voice, facial expression, EEG, ECG, skin electricity, body temperature, etc.
2. Advanced emotion recognition model, such as artificial neural network, trancformer, etc.
3. Emotion generation model for emotional human-computer interaction,
4. Emotion perception principle of brain,
5. Emotion-related psychopathy principle, including obsessive-compulsive disorder (OCD), autism, depression, autism, etc.
Key words:
Emotion perception, Emotion manifestations, Emotion recognition, Emotion synthesis, Emotion diseases
Chair 1：Assoc. Prof. Lijiang Chen，Beihang University， China
Lijiang Chen is an associate professor at Beihang University, Beijing, China. He received his Ph.D. degree in School of Electronic and Information Engineering, Beihang University, Beijing, China, in 2012. He was a Hong Kong Scholar in the City University of Hong Kong from 2015-2017. He won the second prize of technological invention of the Ministry of Education of China. He is a member of IEEE, China Society of Image and Graphics, Chinese Association of Sutomation. He presided or participated in more than 10 fund projects, including National Natural Science Foundation, Postdoctoral Fund, Top Talents Program of Beihang University, Pre-research Project of the 13th Five-Year Plan, etc. His current research interests include Affective Computing, Pattern Recognition, Sentiment Computing, and Human Computer Interaction. He has published more than 70 papers in academic journals and international conferences, of which 53 have been indexed by SCI on journals. His papers have been cited 1150 times, the H-index in Scopus database is 15.
Chair 2：Assoc. Prof. Jizheng Yi, Central South University of Forestry and Technology, China
Jizheng Yi got his Ph.D. from Beihang University and worked as a visiting scholar at the University of Pennsylvania. Now he is an associate professor of Central South University of Forestry and Technology (CSUFT) and holds various positions within esteemed organizations, such as the Executive Committee Member of Computer Applications Technical Committee of China Computer Federation, the Standing Committee Member of Education Technical Committee of Hunan Association for Artificial Intelligence, the leader of Talent Training and Teaching Team for computer majors at CSUFT, the director of the Department of Computer Science and Technology (National First-Class Undergraduate Major Construction Point), and also the head of the Department of Artificial Intelligence.
Doctor Yi’s research focuses on a range of cutting-edge topics, including emotional computing, image processing, pattern recognition, deep learning, sustainable ecology, and financial public opinion analysis. He has led or participated in over 10 national, provincial, and ministerial research projects. He has published more than 50 research papers and solely authored one monograph. H-index 9.
Summary:
With the rapid development of artificial intelligence, intelligent robots have attracted increasing interest from the theoretical researches and practical applications. When complex tasks in the unstructured environment put forward higher demand for the intelligence of robots, adopting intelligent methods and technologies can effectively improve the robustness and generalization of these tasks. The aim of this workshop is to bring together the latest researches and innovations on sensing, decision-making and control for intelligent robotic systems from both the technology and functionality perspectives.
Key words:
robotic system, sensing, decision-making, control
Chair 1：Assoc. Prof. Chao Ma, University of Science and Technology Beijing, China
Chao Ma is an associate professor of School of Mechanical Engineering, University of Science and Technology Beijing (USTB). He is a senior member of the Chinese Mechanical Engineering Society, a senior member of the Chinese Institute of Command and Control, a member of the IEEE and ACM. He obtained a doctor's degree in control science and engineering from Harbin Institute of Technology. His main research fields are in the hybrid intelligent systems, intelligent robot systems, human-computer interaction systems, etc. He has published more than 50 SCI/EI research papers, and published a Springer academic book and served as the conference committee in many international conferences.
Chair 2：Assoc. Prof. Wei Wu Institute of Automation, Chinese Academy of Sciences, China
Wei Wu is an associate professor with the State Key Laboratory of Multimodal Artificial-Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing. He received the B.Sc. degree in physics and M.Sc. degree in theoretical physics from Beijing Normal University, Beijing, China, in 2001 and 2004, respectively, and the Ph.D. degree in computational neuroscience from Johann Wolfgang Goethe University, Frankfurt, Germany, in 2008. His current research interests include artificial intelligence and intelligent systems.
Chair 3：Assis. Prof. Yiheng Han Beijing University Of Technology, China
Yiheng Han is an assistant professor with the department of artificial intelligence and automation, Beijing University of Technology. He received his B.Eng degree from Jilin University, China, in 2018, and received the PhD degree from Tsinghua University, China, in 2023. His research interests include robot active vision, motion planning and robotic vision, 6D pose estimation. His research was mainly published in T-PAMI, ICRA, RAL and IROS. He win the nomination award for Excellent Doctoral paper of BSIG in 2023.
Summary:
This workshop is an multidisciplinary crossing of researchers at the intersection of computer science, artificial intelligence, machine learning, statistics, and related areas. It also aims to increase public understanding of artificial intelligence, improve the teaching and training of AI practitioners, and provide guidance for research planners and funders concerning the importance and potential of current AI developments and future directions. This workshop also gives attendees an opportunity to share experiences and lessons learned in applying AI theories and techniques to real-life projects in practice.
Key words:
Artificial Intelligence, Machine learning, Deep learning
Chair 1：Prof. Xinrong Hu, Wuhan Textile University, China
Xinrong Hu earned her Ph.D. at the Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology in 2008. Now she is a professor and dean in the School of Computer Science and Artificial Intelligence, at Wuhan Textile University. Her research interests include image processing, virtual reality technology, and computer vision. She has published more than 100 articles in peer-reviewed international journals, conference proceedings, and books.
Chair 2：Dr. Bangchao Wang, Wuhan Textile University, China
Bangchao Wang is a Master Supervisor in the School of Computer Science and Artificial Intelligence at Wuhan Textile University, Wuhan, China. He received the Ph.D. degree in Computer Science andTechnology from Wuhan University. His research interests mainly include but are not limited to software engineering, requirements engineering, and knowledge engineering. He has published nearly30 articles in peer-reviewed international journals and conference proceedings.
Summary:
Recently, deep learningmodelsand algorithmshave become hot topics and could effectively deal with a wide range of real applications, such as image processing and computer vision.We believe this trend will continue in the future.Thus, this workshop aims to promote discussions among researchers investigating innovative deep learningtechnologies from perspectives of fundamentalmodelsand algorithmsin image processing and computer vision. Furthermore, researchers from multiple disciplines including artificial intelligenceand mathematics fields are encouraged to join the workshop to discuss the challenging problems and future research directions.
Key words:
Machine learning,deep learning, multispectral/hyperspectral images, model-driven and data-driven algorithms, videos and medical images
Chair 1：Prof. Jinshan Zeng, Jiangxi Normal University, China
Jinshan Zeng received the Ph.D. degree in mathematics from Xian Jiaotong University, Xi'an, China,in 2015.He is currently a Distinguished Professor withthe School of Computer and Information Engineering,,and serves as the associated dean of this school. He has authoredmore than 50 papers in high-impact journals andconferences such as IEEE TPAMI, JMLR, IEEE TSP\TKDE,ICML,and AAAI. He hascoauthored two papers with collaborators that received the International Consortium of Chinese Mathematicians (ICCM) Best Paper Award in 2018 and2020). His current research interests include machinelearning (in particular deep learning), computer vision, and remote sensing.
Chair 2：Assoc. Prof. Yong Chen, Jiangxi Normal University, China
Yong Chen obtained his doctoral degree in 2020 from School ofMathematical Sciences of University of Electronic and Technology of China. When pursuing the doctoral degree, hereceived full sponsorship for a oneyear study tour to RIKEN AIP. In March 2021, Hejoined theSchool of Computer Information Engineering of Jiangxi NormalUniversity. So far, Hehas published 27papers on journals and conferences, where 23are on SCI-indexed journals including IEEE TIP, IEEE TCYB, IEEE TNNLS, ISPRS P&RR, IEEE TGRS, IEEE TCI and PR, with twoESI highlycited papers. The total citations of his papers reached nearly 800 on Google Scholar. Hehas chaired one project funded by the National Natural Science Foundation, and twofunded by the Natural Science Foundation of Jiangxi. Now, heis a reviewer for several SCI-indexed journals like IEEE TIP, IEEE TNNLS, IEEE TGRS, IEEE JSTSP, and IEEE JSTARS. His current research interests include image processing, low-rank matrix/tensor representation, and model-drivendeep learning.
Summary:
The concepts of the Internet of Things (IoT) are providing services across different sectors including agriculture, healthcare, manufacturing, smart cities, smart supply chains, industrial internet and automobile. However, computing intelligence has become a major concern in the IoT environment, which is important to address before widely deploying the IoT services. Edge Computing is a capable technology that enhances the quality and performance of IoT services and brings computing intelligent paradigms. The edge computing technology perfectly fits the architecture and features of IoT systems. However, edge computing is still a novel concept and faces many challenges specifically related to integration and universal adoption, availability, energy consumption, accuracy and efficiency. The given challenges motivate us to explore various possible solutions for the intelligent IoT environment. Machine Learning and Optimization come into play as the leading solution strategies recently. This workshop is concerned with the Machine Learning and Optimization techniques addressing various tasks in edge computing based IoT.
Key words:
Edge computing internet of things computing intelligence Machine Learning
Chair 1：Prof. Shuai Zhao, Beijing University of Posts and Telecommunications, China
Shuai Zhao received the Ph.D. degree in computer science and technology from the Beijing University of Posts and Telecommunications (supervisor: Prof. Junliang Chen) in June 2014. He is a Professor with the State Key Laboratory of Networking and Switching Technology at Beijing University of Posts and Telecommunications. His current research interests include Internet of Things technology and service computing.
Chair 2：Shengjie Li, Beijing University of Posts and Telecommunications, China
Shengjie Li received the Ph.D. degree in information and communication engineering from the Beijing University of Posts and Telecommunications (supervisor: Prof. Junliang Chen) in 2020. He is currently a Lecturer with the State Key Laboratory of Networking and Switching Technology at Beijing University of Posts and Telecommunications. His current research interests include Internet of Things technology and visual object tracking.
Summary:
Evolutionary computation technique has been widely used for addressing various challenging problems due to its powerful global search ability. Meanwhile, there are many complex optimisation tasks in the fields of deep learning such as neural architecture search, weight optimisation, hyper-parameter search, feature selection, feature construction, etc. Combining evolutionary computation and deep learning, especially employing evolutionary computation technique for optimization problems in deep learning, is becoming a popular topic in both evolutionary computation community and deep learning community. However, the most prominent problem is that it is very time-consuming to evolve a population of deep neural networks which involve the training processes. Efficient techniques, such as surrogate models for ranking, need to be developed to solve the problem. This workshop aims to collect original papers that develop efficient methods for evolutionary deep learning.
Key words:
Evolutionary deep learning, evolutionary computation, neural architecture search, surrogate model, neuroevolution
Chair 1：Prof. Yu Xue , Nanjing University of Information Science and Technology, China
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 the School of 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.
Chair 2：Prof. Bing Xue, Victoria University of Wellington, New Zealand
Bing Xue is currently a Professor of 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 Optimisation, 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.
Chair 3：Prof. Yong Zhang, China University of Mining and Technology, China
Yong Zhang received 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 optimisation and data mining.
Chair 4：Prof. Ferrante Neri, University of Surrey, UK
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 Optimisation 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. In 2019, Ferrante Neri moved to the University of Nottingham, United Kingdom and in 2022 to the School of Computer Science and Electronic Engineering, University of Surrey, United Kingdom, where he is currently Professor of Machine Learning and Artificial Intelligence and Head of the Nature Inspired Computing and Engineering (NICE) research group. His research interests include algorithms, hybrid heuristic-exact optimisation, memetic computing, differential evolution, and membrane computing. Prof Neri published over 200 items including two editions of the textbook “Linear Algebra for Computational Sciences and Engineering” and is Associate Editor of multiple journals including Information Sciences and Integrated Computing Engineering.
Chair 5：Prof. Adam Slowik, Koszalin University of Technology, Poland
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 optimisation algorithms and their applications. He is an Associate Editor for the IEEE Transactions on Industrial Informatics.
Summary:
Perceptual representation is a fundamental processing step for image, video, speech, and audio recognition, which mathematically is also considered as a complex transformation function from input to output to extract and characterize the essential features of a signal. At present, there are two main methods for functional modeling: data-driven fitting and first-principles modeling. In recent years, the proposal of data-driven deep network fitting methods has brought breakthrough progress to classic pattern recognition applications. However, due to excessive reliance on a large number of labeled samples and neglecting the inherent correlation relationships of data, deep learning models have limitations in such as interpretability, robustness, and adaptability.
In order to solve these problems, this article proposes a perceptual mapping model from any shape to differential geometry space using the modeling idea of first principles. Firstly, based on the principle of non-singularity, we used algebraic and calculus mathematical methods to prove the existence of a bijective function that maps algebraic geometric shapes with shifts, scales, biases, gains, and noise changes to a low dimensional manifold in a high-dimensional background space, thereby overcoming the curse of dimensionality and inaccurate differential calculations in modeling complex problems. Then, based on the multi-scale characteristics of perceptual representation, we proposed a multi-scale perceptual model for encoding the intrinsic characteristics of signals. Finally, we designed a neural network model for image classification with multi-scale perception models, and conducted classifier learning and classification experiments on datasets such as MINIST, EMINIST, and CIFAR. Experiments show that the classification accuracy reaches 99.63%, 89.991%, and 95.75% on MINIST, EMINIST, and CIFAR datasets, respectively, which is better than the existing representative methods. Unlike deep learning algorithms, we use principal component analysis and orthogonal transformation to solve the parameters of deep neural networks for feature selection and recognition through the first principles of visual recognition.
This study not only explains that perception is essentially the extraction of intrinsic geometric features from data, but also the proposed perceptual model does not require training samples, resulting in good generalization to different classification tasks. Our study provides a new mathematical analysis theory and technical approach to overcome catastrophic forgetting phenomenon and improve the robustness and adaptability of low-shot learning for complex changing targets.
Key words:
Visual perception; Featureextraction; Geometric manifold; Neural network interpretability
Chair：Prof. Guoguo Wang , Hangzhou University of Science and Technology, China
Wang Guoguo is a professor at the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, and the National Key Laboratory of Multispectral Information Intelligent Processing Technology. He is an expert in the Overall Missile Technology Professional Group and Intelligent Application Equipment Professional Group, a committee member of the China Information Fusion Society, and an executive director of the Hubei Aerospace Society. He mainly engages in the research and development of computer vision theory, matching and recognition guidance technology, and intelligent systems, published over 140 academic papers, and received four items of Science and Technology Awards, including the Second Prize in Natural Science of Hubei Province, the First Prize and Second Prize in Science and Technology Progress of the Ministry of Education, and the Second Prize in National Defense Science and Technology.
Summary:
This workshop will provide a condensed yet highly focused exploration of the intersection of AI and food, medicine, and biochemistry domains. Topics includes, but not limited to food quality assurance and quality control, food safety and risk assessment, precision farming, drug discovery, diagnostic support systems, as well as other AI's role in biochemistry. Over the course of a dynamic and engaging session, participants delved into the cutting-edge applications and transformative potential of various machine learning and AI techniques in revolutionizing food production and safety, AI-powered healthcare and medicine, biochemistry and drug discovery, etc. This workshop will offer a concise yet comprehensive exploration of the frontiers of AI and machine learning’s transformative potential. Participants will exchange ideas about the latest advancements, ethical considerations, and opportunities for innovation, shaping the future of food production, healthcare, and biochemistry, reinforcing the idea that technology has the power to create a healthier and more sustainable world.
Key words:
Artificial Intelligence，Deep learning，Food analysis，QSAR
Chair 1：Assoc. Prof. Weiying Lu, Shanghai Jiao Tong University, China
Dr. Lu is an associate professor in the Department of Food Science and Technology, at Shanghai Jiao Tong University. He earned his Ph.D. degree in analytical chemistry from Ohio University. His main research interest focused on food quality and safety using the state-of-art fingerprinting and big-data analysis techniques such as metabolomics and proteomics. He has studied analytical techniques such as ultra-high-performance liquid chromatography-time-of flight mass spectrometry, UV-Vis and FTIR spectroscopy, gas chromatography, and bioactivity evaluation, combined with chemometrics, to assess the bioactive components in common foods such as olive oil, butter, chrysanthemum tea, and milk, as well as functional foods such as gouqi fruits and plantago seeds. He has been acted as principal investigator for various government- and industry sponsored projects, published over 30 peer reviewed papers and book chapters in esteemed academic journals, and have been granted patents and software copyrights.
Chair 2：Assist Prof. Yanping Chen, Shanghai Jiao Tong University, China
Dr. Yanping Chen is an Assistant Professor in the Department of Food Science and Technology, at Shanghai Jiao Tong University. Her research interests included food flavor chemistry, sensory evaluation, and flavor perception. She got a Ph.D. degree from the Chinese University of Hong Kong in 2016 and obtained master’s and bachelor’s degrees from Jiangnan University in 2013 and 2010. She has published 37 academic papers, including 2 highly cited papers. She was involved in more than 20 research projects funded by the Chinese national natural science foundation, and the food industry as principal investigator or co-investigator. She is a member of the Youth Working Committee of Shanghai Food Society, a member of the China Animal Products Processing Research Association, a member of the American Chemical Society. She has served as guest editor for the Journal of Food Biochemistry, Biosensors, Foods, and other journals.
Summary:
For the robots with model uncertainty and output constraints, an adaptive neural network impedance control method based on an asymmetric integral barrier Lyapunov function (AIBLF) is proposed. The control structure consists of an impedance control outer loop and a tracking control inner loop. In the outer loop, to prevent inappropriate interactive behavior from exceeding the constraints, an asymmetric soft saturation function is designed to reshape the desired trajectory generated by the impedance model. In the inner loop, to solve the constraint tracking control problem, an adaptive state feedback controller based on AIBLF is designed. The controller strictly guarantees that the robot end effector does not exceed the constraint boundary. Additionally, a radial basis function neural network (RBFNN) is used to compensate uncertainties in robot dynamics and improve tracking performance. Finally, by the Lyapunov stability theorem, it is proved that all error signals of the closed-loop system are bounded.
Key words: Adaptive control, Human-computer interaction
Chair： Prof. Lin-lin Ou, Zhejiang University of Technology, China
Lin-Lin Ou received the B.Eng. degree and Ph.D. degrees from Shanghai Jiao Tong University, China in 2001 and 2006, respectively. She was with the College of Information Engineering, Zhejiang University of Technology, China, as a lecturer from 2006 to 2007 and later as an associate professor from 2008 to 2012. She is currently a professor since 2013. She has published nearly 50 academic papers in IEEE Transactions on Automatic Control and other journals and conferences, and also has authorized over 20 invention patents. She was a recipient of the China Machinery Industry Science and Technology.
Her research interests include stabilization and control of time delay systems, intelligent learning and robot system, multi-robot collaborative control, and human-robot integration.
Summary: Artificial Intelligence exists in industries broadly and promotes the efficiency and yields of intelligent production greatly. The development of AI can increase prediction accuracy and measurement accuracy, handle uncertainties in industrial process, and so on. Artificial Intelligence in industries should present the concerns as below.
1.AI techniques for intelligent sensing in industrial process.
2.AI techniques for industrial data modelling in industrial process.
3.AI techniques for industrial big data analysis and data mining.
4.AI techniques for cooperative control, autonomous control, operation optimization, and so on.
5.AI techniques for abnormal remote monitoring, performance monitoring and assessment, fault diagnosis and prediction, automatic fault recovery, life prediction, and so on.
6.AI techniques for automatic parameter measurement.
AI techniques for intelligent decision-making.
Keywords: Intelligent sensing, data modelling, data mining, cooperative control, monitoring, decision-making
Chair: Prof. Zhenyan Ji, Beijing Jiaotong University, China
Zhenyan Ji, Professor of Beijing Jiaotong Univeristy. She received her Ph.D. degree from Institute of Software, Chinese Academy of Sciences in 1999. She had worked for Norwegian University of Science and Technology from November 1999 to June 2000, and Mid Sweden University from July 2000 to September 2008. Her main research areas: artificial intelligence, software engineering, and distributed systems. She has published more than 60 academic papers and authored 6 books in these areas.
Chair: Assoc. Prof. Li Li, Beijing University of Posts and Telecommunications， China
Li Li, Ph.D, associate professor of Beijing University of Posts and Telecommunications(BUPT), member of Chinese Association for Artificial Intelligence, and visit scholar of Georgia Institute of Technology.
She has been engaged in the field of artificial intelligence and communication for many years, published over 30 SCI/EI papers and obtained over 20 patent authorizations.
She has been in charge of several national as well as enterprise cooperation projects, including National Natural Science Foundation project, sub-project of National Science and Technology Major Project of the Ministry of Science and Technology of China, Special Program for Youth Research and Innovation of the Ministry of Education of China, Huawei Innovation Program, and so on.
She led a team to research on performance improvement of machine leaning algorithms, neural network model compression as well as applications in several scenarios for several years. They developed a Chinese herbal medicine recognition system, a violence monitoring system based on video understanding, and a human behavior recognition system. They also solved resource management problems in communication networks as well as EEG signal processing problems by utilizing machine learning algorithms.
In 2021, they won the "Best Potential Award" in the first Western Digital Education Application Industry Innovation and Entrepreneurship Competition
Summary: With the development of computer and artificial intelligence technology, wearable sensors play an important role in people's daily life and have a broad commercial application prospect. Wearable sensors classified by sensing type include A-type ultrasound, plantar pressure insoles, inertial sensors, myoelectricity, EEG, etc., which are capable of acquiring human body-related motion and physiological signals, and through a large number of datasets and machine learning methods are able to construct mathematical models containing human body motions, and through the mathematical models, realize the recognition of users' intentions. Wearable sensors have good prospects for use in behavior recognition, medical rehabilitation, and virtual reality due to their low cost, high flexibility, and good portability. In recent years, researchers have used A-type ultrasound, data gloves, pressure smart shoes, and inertial sensors to realize human gesture and gait recognition. The EEG and EMG signals have assisted doctors in the diagnosis of Parkinson's patients' disease diagnosis and the rehabilitation assessment of stroke patients, and have been integrated into smart prosthetics to help amputee patients achieve object grasping and stable walking. Virtual reality interaction was realized through wearable VR devices and inertial sensors.
This workshop aims to provide a communication platform for wearable sensors for human behavior recognition and health monitoring, involving but not limited to myoelectricity, ultrasound, pressure sensors, inertial sensors, EEG technology, etc. We welcome you to discuss the current state of research and application prospects of wearable sensors.
This workshop aims to provide a communication platform for wearable sensors for human behavior recognition and health monitoring, involving but not limited to myoelectricity, ultrasound, pressure sensors, inertial sensors, EEG technology, etc. We welcome you to discuss the current state of research and application prospects of wearable sensors.
Keywords: Wearable Sensors, Human Behavior Recognition, Human-Machine Interaction, Pattern Recognition, Machine Learning Application
Chair: Assoc. Prof. Zongxing Lu, Fuzhou University, China
Lu Zongxing is currently an associate professor at the School of Mechanical Engineering and Automation at Fuzhou University. He graduated from Beijing Institute of Technology in 2016 with a PhD. He is currently a Category C high-level talent in Fujian Province, winner of the IEEE Andrew P. Sage Best Transactions Paper Award, and a director of the Mechanical Engineering Society of Fujian Province. He has long been engaged in research in the fields of wheel-footed composite robots, multi-modal human behavior sensing technology, rehabilitation robots and muscle assessment technology, and biomechatronics. He has published more than 30 academic papers, including more than 20 SCI indexed, and has authorized more than 10 Chinese invention patents. In 2017, he participated in the formulation of national standards. He has presided over a number of national, provincial and ministerial level scientific research projects, and completed a number of university-enterprise joint technology research and development projects focusing on the modeling and application of robotic arms.
Summary: The development of industrial process modeling, fault diagnosis and safety control technology has made many exciting achievements. With the vigorous development of artificial intelligence and machine learning technologies, data-driven modeling, diagnosis and security control technologies face many new opportunities, such as the rapid progress of learning methods, the enhancement of hardware computing power, the rise of industrial metaverse and big data concepts. Some new application scenarios and complex systems and environments also bring many challenges to the research and application of industrial process modeling, diagnosis and safety control technology. In view of this, we initiated the "Intelligent Modeling, Diagnosis and Safety Control of Complex Systems" seminar, with the theme of "Artificial Intelligence Helps Industrial process Modeling, Diagnosis and safety Control", to provide a platform for scholars at home and abroad to exchange new ideas and new technologies.
Keywords: artificial intelligence，abnormal detection, complex systems, machine learning
Chair 1: Assoc. Prof. Kaixun He, Shandong University of Science and Technology, China
Kaixun He received the Ph.D. degree in control science and engineering from the School of Information Science and Engineering from East China University of Science and Technology, Shanghai, China, in 2016. In September 2016, he joined the Shandong University of Science and Technology, Qingdao, China, where he is currently an Associate Professor
in automation with the College of Electrical Engineering and Automation. His current research interests include industrial process monitoring and fault diagnosis, artificial intelligent, and machine learning.
Chair 2: Assoc. Prof. Ting Xue, Shanghai Maritime University, China
Ting Xue received the M.S. degree in instrumentation science and technology from Beihang University, Beijing, China, in 2016, and the Ph.D. degree in electrical engineering and information technology from the University of Duisburg-Essen, Duisburg, Germany, in 2020.
From Dec. 2020 to Apr. 2023, she worked in Shandong University of Science and Technology as a postdoctoral fellow, Qingdao, China. She is currently an Associate Professor in Shanghai Maritime University, Shanghai, China. Her research interests include model-based and data-driven fault diagnosis and their applications.
Chair 3: Prof. Xin Peng, East China University of Science and Technology, China
Xin Peng is currently an assistant professor with the East China University of Science and Technology and research fellow with State Key Laboratory of Industrial Control Technology/ Key Laboratory of Smart Manufacturing in Energy Chemical Process of Ministry of Education. His current research interests include intelligent modeling, control and optimization of industrial processes, and machine learning, intelligent optimization methods and their industrial applications. Dr. Peng received his Ph.D degree from the Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, in 2017.,From 2017 to 2019, he worked as a Post-Doctoral Researcher at the University of Duisburg-Essen, Duisburg, Germany. He has published over 70 papers in IEEE TCYB, IEEE TNNLS, IEEE TIE, IEEE TII, CES, Info. Sci., and other journals and conferences. He has hosted a research subject of National Key Research and Development Program of China, a General Program of National Natural Science Foundation of China and other national/ provincial research projects. Dr. Peng has served as Conference/Technical/ Special Session Chair of many international conferences including IEEE ONCON, RICAI, IARCE, MLCCIM. He is one of the receivers of second-class prize of Shanghai Natural Science Award of 2022.