The goal of this invited session is to bring together researchers interesting in intelligent systems. Researchers from these areas are encouraged to submit proposals to present their work related to intelligent systems. Submissions will be evaluated on the basis of their innovation, relevance, scientific contribution, and presentation.

• Neural Networks and Support Vector Machines
• Image Processing
• Intelligent Information Systems
• Intelligent Agent
• Inductive Learning
• Intelligent Control
• Sample and Feature Selection
• Evolutionary Computation
• Data Mining
• Automated Reasoning
• Knowledge-Based Systems
• Information Retrieval and Integration
• Machine Learning
• Pattern Recognition
• Robotics
• Speech Recognition and Synthesis
• Support Vector Machines
• Mobile Intelligence
• Web Intelligence
• AI Applications
• Computer Vision
• Image Processing
• Intelligent E-Learning/Tutoring
• Semantic Web
• RFID Applications
• Intelligent Internet
• Big Data
• Computer and Communication Networks
• Genetic Algorithms
• Other Related Topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (smchen@mail.ntust.edu.tw) before May 15, 2023

Prof. Shyi-Ming Chen
Department of Computer Science and Information Engineering,
National Taiwan University of Science and Technology,
43, Section 4, Keelung Road, Taipei, Taiwan
smchen@mail.ntust.edu.tw

The goal of this invited session is to bring together researchers interesting in fuzzy systems. Researchers from these areas are encouraged to submit proposals to present their work related to fuzzy systems. Submissions will be evaluated on the basis of their innovation, relevance, scientific contribution, and presentation.

• Fuzzy Reasoning
• Fuzzy Control and Robotics
• Fuzzy Image, Speech and Signal Processing
• Vision and Multimedia, and Pattern Recognition
• Fuzzy Data Mining
• Fuzzy Database
• Fuzzy Forecasting
• Fuzzy Expert Systems
• Fuzzy Neural Networks
• Fuzzy Information Systems
• Fuzzy Decision-Making
• Computing with Words
• Granular Computing
• Rough Sets
• Grey Systems
• Fuzzy Data Analysis
• Industrial, Financial, and Medical Applications
• Applications of Fuzzy Systems
• Soft Computing
• Computational Intelligence
• Other Related Topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (smchen@mail.ntust.edu.tw) before May 15, 2023

Prof. Shyi-Ming Chen
Department of Computer Science and Information Engineering,
National Taiwan University of Science and Technology,
43, Section 4, Keelung Road, Taipei, Taiwan
smchen@mail.ntust.edu.tw

With a number of breakthroughs in intelligent system and its related technology over the past decade, practical use of machine learning has become fiercer than ever. This session aims to highlight the evolution of topics, frontline research and multiple applications, in the domain of artificial Intelligence from the mainstream foundations to novel investigations and applications.

• Intelligent Systems
• Big data
• Computer Vision and Image Processing
• Control System
• Cryptography
• Signal Processing
• Data Mining
• Multisensory processing
• Human-Robot Interactions
• Affective Computing Models
• Other Related Topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (shenhongrui1987@163.com) before May 15, 2023

Prof. Xiao-Hui Hu
South China Normal University
huxh@scnu.edu.cn

Prof. Hong-Rui Shen
Neusoft Institute Guangdong
shenhongrui1987@163.com

This special session focuses on the topological clustering and continual learning algorithms emerging from the adaptation, learning, and cognitive development through interaction with people and dynamic environments from the conceptual, theoretical, methodological, and/or technical points of view. More specifically, we aim to discuss topological clustering and continual learning for extracting, storing, and exploiting multidimensional information from environmental data with multiple modalities. This session welcomes fundamental research on information extraction techniques and knowledge base relation learning approaches. In addition, the session also welcomes research on applied topics relating to exploiting knowledge with intelligent applications/robots.

• Unsupervised Learning
• Topological Clustering
• Clustering
• Knowledge Extraction
• Intelligent Robotics
• Continual Learning
• Other related topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (ytoda@okayama-u.ac.jp) before May 15, 2023

Dr. Yuichiro Toda
Okayama University
ytoda@okayama-u.ac.jp

Dr. Naoki Masuyama
Osaka Metropolitan University
masuyama@omu.ac.jp

Prof. Naoyuki Kubota
Tokyo Metropolitan University
kubota@tmu.ac.jp

This session aims at exploring intelligent ways of processing in depth unstructured data in terms of feature extraction, feature selection and classification. In the context of machine learning, unstructured data normally needs to be transformed into structured data through feature extraction prior to training of classifiers. In the setting of representation learning, it is essential to learn a feature extractor that can be well generalized to unseen data, i.e. features extracted from training data need to be well applicable to test data and features that well describe test data should be present from training data. Also, feature extraction from unstructured data generally leads to high dimensionality of feature vectors. From the above points of view, it is necessary to adopt feature selection techniques to not only reduce the dimensionality but also increase the correlation between the feature space and the label space. On the other hand, in order to increase the depth of learning, it is necessary to ensure that a layer-by-layer processing of data is involved and the feature space is also updated iteratively during the learning process. Furthermore, sample representativeness is another issue that could not only result in overfitting of classifiers on training data but also increase the chance to cause insufficient generalizability of a feature extractor, i.e., if a sample set does not represent a full population of instances in a domain, it would be likely to train a classifier that overfits the sample set and to extract features that are incompatible with features that well describe unseen data. This session welcomes submissions of papers related to unstructured data processing and papers that address the above issues are particularly encouraged. All submitted papers will be evaluated on the basis of their relevance, technical merit and quality of writing.

• Natural Language Processing
• Knowledge Graph
• Feature Extraction
• Feature Selection
• Feature Transformation
• Feature Fusion
• Deep Learning
• Ensemble Learning
• Representation Learning
• Meta Learning
• Embedding Learning
• Multi-Modal Learning
• Text Mining
• Image Processing
• Signal Processing
• Computer Vision
• Computer Graphics
• Medical Imaging
• Covid Diagnosis
• Sentiment Analysis
• Affective Computing
• Emotion Detection
• Topic Detection
• Cyberbullying Detection
• Cyberhate Detection
• Social Media Analysis
• 3D Reconstruction
• Object Recognition
• Activities Recognition
• Emotion Cause Analysis
• Question Answering Systems
• Machine Translation
• Other Related Topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (han.liu@szu.edu.cn) before May 15, 2023

Dr. Han Liu
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
han.liu@szu.edu.cn

Dr. Li Zhang
Department of Computer Science, Royal Holloway, University of London, Egham, UK
li.zhang@rhul.ac.uk

This special session focuses on discussing topics from the viewpoint of community-centric systems. The community-centric system aims to support a whole community that organically collaborates with each user who performs their role and task. Therefore, in terms of community, discussing human understanding methods and novel support systems as one of the essential components is important. By utilising machine learning techniques, a better extraction and understanding of community-based behaviour and planning can be achieved, facilitating advanced community-centric systems. And the improvement will be reflected in better autonomy, intelligence, and efficiency. In this session, we will discuss community-centric systems from various aspects widely including topics on human-related behaviour classification, cognitive computing, and their applications in robotics, healthcare, and daily activity support.

• Activity recognition
• Affective computing/li>
• Behaviour recognition
• Cognitive development
• Community-based healthcare
• Human sensing
• Recommender system
• Rehabilitation intelligence
• Community robotics
• Other related topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (dalin.zhou@port.ac.uk) before May 15, 2023

Dr. Dalin Zhou
University of Portsmouth, UK
dalin.zhou@port.ac.uk

Dr. Kurnianingsih
Politeknik Negeri Semarang, Indonesia
kurnianingsih@polines.ac.id

Dr. Eri Sato-Shimokawara
Tokyo Metropolitan University, Japan
eri@tmu.ac.jp

This session aims to bridge the gap between fast-developing machine intelligence and automatic systems. In the past decades machine learning such as deep learning has massively advanced intelligence theory, seeking application carriers to maximize its role and impact; on the other hand, recent technology such as advanced electronics has offered an opportunity to revolutionize conventional systems with accumulating datasets and robots. Intelligence theory with machine learning join forces to push the boundaries of the research frontiers in automation for applications, e.g. industrial robots, self-driving vehicles, and aerial vehicles. This special session brings together experts in machine learning, computer vision, robotic behaviour to foster a fruitful and multi-disciplinary discussion. This session will present the latest results and emerging learning and algorithmic techniques for practical applications, which allows top researchers from different communities to share their work. We aim to inspire cross-discipline collaboration and motivate the use of more integrated research approaches, especially to real-world applications.

• Learning for vision understanding
• Automated robots
• Scene interpretation
• Machine intelligence
• Sensing
• Other related topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (sy@ieee.org) before May 15, 2023

Prof. Shengyong Chen
Tianjin University of Technology
sy@ieee.org

Prof. Gu Fang
Western Sydney University
g.fang@westernsydney.edu.au

Prof. Naoyuki Kubota
Tokyo Metropolitan University
kubota@tmu.ac.jp

Dr. Yu He
Tsinghua University
hooyeeevan2511@gmail.com

Prof. Honghai Liu
HIT Shenzhen
honghai.liu@icloud.com

With the advancement in technology, practical applications of artificial intelligence have been developed and deployed intensively. Data science and brain-inspired methods have gained most attractiveness than ever, as they serve as the cores of novel intelligent systems. The integration of advanced sensing, data processing, and innovative brain-inspired technology rapidly extend its practical use in real-life problems, enables the related techniques to be the most attractive means for novel system design. This session aims to highlight the frontline research and applications, in the domain of data science and brain-inspired Intelligence, from the mainstream foundations to novel investigations and applications. Submissions in any relevant discipline are highly encouraged, including but not limited to the application of Brain Informatics, Machine Learning or alternative novel techniques to Intelligent Systems, Signal Processing, Data Mining, Multisensory processing, Human-Robot Interactions, Natural Language Processing, Big Data, and Image Processing. We particularly welcome submissions with an interdisciplinary character. Normal standards of academic excellence apply.

• Brain Informatics
• Data Mining
• Big Data
• Natural Language Processing
• Human Machine Interaction
• Metaverse
• Other related topics

Authors must submit an electronic copy (in word or pdf) of their complete manuscript directly to the Session Organizer (xueyun@m.scnu.edu.cn) before May 15, 2023

Prof. Yun Xue
South China Normal University
xueyun@m.scnu.edu.cn

Prof. Haolan Zhang
NIT, Zhejiang University
haolan.zhang@nit.zju.edu.cn