Plenary Speaker - ICAI 2023

ICAI 2023 Plenary Speakers

Vasu Alagar
Vladimir Filaretov
De-Shuang Huang

	Vasu Alagar PhD. Professor Emeritus Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada H3G 1M8
	Vladimir Filaretov PhD & Professor Academicians of Russian Engineering Academy and Russian Science Academy Vice-president of Russian Engineering Academy, Vladivostok, Russia
	De-Shuang Huang Prof. & Ph.D, IEEE Fellow, IAPR Fellow & AAIA Fellow Institute of Machine Learning and Systems Biology, Eastern Institute of Technology, Ningbo, China

Contextual Reasoning

Vasu Alagar PhD. Professor Emeritus
Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada H3G 1M8
Email:vangalur.alagar@concordia.ca,alagar@cse.concordia.ca

Abstract: Contextual knowledge representation, contextual reasoning, and learning are the foundations on which AI evolves. Intelligent problem solving in any domain requires the selection of data relevant to achieve the goal, the representation of knowledge (semantic content), the context in which data originated and the context in which analysis of data will be done. So, understanding and analyzing content without context are meaningless, and every context that exists at different problem-solving stages will have some content that may or may not be useful to achieve the goal. However, in the current AI and applications on context-aware frameworks, the distinction between knowledge and context are blurred and not formally integrated. As a result, adaptation behaviors based on contextual reasoning cannot be formally derived and reasoned about. In many smart systems such as automated manufacturing, decision making, and healthcare informatics it is essential for context-awareness units to synchronize with contextual reasoning modules to derive new knowledge in order to adapt, alert, and predict. A rigorous formalism is therefore essential to represent contextual domain knowledge as well as application rules, and precisely and efficiently reason to derive the closure of contextual conclusions. This talk will first introduce a formal context representation and a context calculus used to build a formal context model for applications in a domain. Any application in that domain that requires this contextual cover can import the context toolkit of this context model and link it for context-aware applications and formal reasoning of its properties. The formal framework for contextual reasoning is provided by Contelog, which is a conservative extension of the syntax and semantics of Datalog. In Contelog framework design, contextual knowledge and contextual reasoning are loosely coupled. The significance of this design is that by fixing contextual knowledge, rules of inference may be changed and hence multiple reasonings are possible. The talk will show several case studies chosen from the Book of Examples and refer to the Doctoral Thesis of Ammar Alsaig for an in-depth study on the expressive power of its theory and a variety of implemented examples to showcase a proof of concept for the generality, expressiveness, and the rigor of Contelog.

Bio-Sketch: Vasu Alagar is an Emeritus Professor in the Department of Computer Science and Software Engineering at Concordia University, Montreal, Canada. His academic career, spawning over five decades, has been rich and varied that includes Algorithm Development and Complexity Analysis, Formal Methods, and Rigorous Development of Large Complex Systems. His recent research centers around Formal Component-based Software Development, Context-aware Systems, and in particular the embedding of context in programming languages and Big Data discovery and Analytic. He has written and edited several books and conference proceedings. He has graduated more than 150 masters and PhD students, and his research results are widely published in many journals and conferences.

Development of control systems for underwater and industrial robots with elements of artificial intelligence

Vladimir Filaretov
Academicians of Russian Engineering Academy and Russian Science Academy
Vice-president of Russian Engineering Academy, Vladivostok, Russia
Head of Robotics Laboratory at Institute of Automation and Control Processes Far Eastern
Branch of Russian Academy of Science
Head of the Department of robotics and Automation at Far Eastern Federal University
Member of Presidium of the Highest Engineering Council of Russia
Email: filaretov@inbox.ru

Abstract: The talk is dedicated to creation technologies of intelligent control systems of various robots which can automatically perform complex technological operations in non-deterministic operating environment. These systems are constructed based on information processing, obtained from different vision systems, and provide automatically generation and correction of robot's motion trajectory in a priori unknown and changeable environment. For realization of these systems, a different method of recognition and processing of information obtained from vision systems (optical and laser) will be presented. Here I will talk about method of fast combination of three-dimensional models of deformed parts obtained from laser scanners with their reference CAD-models. Based on this combination it is possible to make trajectory planning of robots in real time for exact processing of the parts. For underwater robots I will present new algorithm for combining images into a one whole raster photo map from a sequence of individual images or video frames using tile graphics and simple transformations of input images. The use of tiles allows to present the generated map in a convenient form both for a person and for the on-board control system of the robot.

Brief Bio-data: Vladimir Filaretov was born in 1948. In 1973 graduated from Moscow State Technical University named after Bauman with honors with the specialty “Automatic systems”. In 1976 Mr. Filaretov was awarded the degree of candidate of sciences (engineering) and in 1990 he was awarded the degree of Doctor of Sciences in the field of automatic control. In 1992 Mr. Filaretov was confirmed in professor’s degree. In 1995 he was elected the member of an Russian and in 1996 the member of an International Engineering Academy. At present he is head of Department of Robotics and Automation at Far Eastern Federal University and Head of Robotic Laboratory of the Institute of Automatics and Control Process of Russian Academy of Sciences, President of Far Eastern Branch Russian Engineering Academy and Vice-president of Russian Engineering Academy. Professor Vladimir Filaretov is a specialist in the field of adaptive and optimal control devices of complicated nonlinear systems of automatic control with unknown and variable parameters, and also in the field of mathematical description of complicated multi-connected mechanisms dynamics. His researches are mainly directed at creation both industrial and underwater robots and manipulators and also other dynamic systems, allowing to automate technical devices and technological processes. Professor V. Filaretov has more than 740 scientific publications, 10 monographs and 350 patents (inventions) for developed technical systems and devices.

Graph-Data Learning and Bioinformatics Applications

De-Shuang Huang, Prof. & Ph.D,
IEEE Fellow, IAPR Fellow & AAIA Fellow
Institute of Machine Learning and Systems Biology, Eastern Institute of Technology, Ningbo, China
Email: dshuang@eitech.edu.cn

Abstract: Graph Neural Networks (GNNs) have achieved advanced performance in many fields such as traffic prediction, recommendation systems, and computer vision. Recently there are majorities of methods on GNN focusing on graph convolution, and less work about pooling. To address the problems of information loss and low feature representation capability during graph pooling operations. In this report, we explore higher efficient graph-level representation learning methods and their application to bioinformatics. Firstly, to address the problem of information loss in the pooling operation, we propose a hierarchical graph-level representation learning method with self-adaptive cluster aggregation. Secondly, to address the fact that all existing graph pooling models based on mutual information maximization need to construct negative samples and usually only consider local neighborhood information, we propose a mutual information graph pooling method based on simple Siamese network. Finally, we present an application of our proposed graph-level representation learning method to healthy aging prediction by using scRNA-seq data.

Bio-Sketch: De-Shuang Huang is a Professor in Institute of Machine Learning and Systems Biology, Eastern Institute of Technology, Ningbo, China. He is currently the Fellow of the IEEE (IEEE Fellow), the Fellow of the International Association of Pattern Recognition (IAPR Fellow), the Fellow of the Asia-Pacific Artificial Intelligence Association (AAIA), and associated editors of IEEE/ACM Transactions on Computational Biology & Bioinformatics and IEEE Transactions on Cognitive and Developmental Systems, etc. He founded the International Conference on Intelligent Computing (ICIC) in 2005. ICIC has since been successfully held annually with him serving as General or Steering Committee Chair. He also served as the 2015 International Joint Conference on Neural Networks (IJCNN2015) General Chair, July12-17, 2015, Killarney, Ireland, the 2014 11th IEEE Computational Intelligence in Bioinformatics and Computational Biology Conference (IEEE-CIBCBC) Program Committee Chair, May 21-24, 2014, Honolulu, USA. He has published over 480 papers in international journals, international conferences proceedings, and book chapters. Particularly, he has published over 260 SCI indexed papers. His Google Scholar citation number is over 23410 times and H index 80. His main research interest includes neural networks, pattern recognition and bioinformatics. His main research interest includes neural networks, pattern recognition and bioinformatics.