Invited Speakers


Dr. Mohammed Chadli, Professor

Dr. Mohammed Chadli, Professor

University of Paris-Saclay, IBISC Lab., France
Speech Title: Multi-Objective Fault Detection Filter Synthesis for a Class of Nonlinear Systems: Some Results and Perspectives

Abstract: This presentation proposes some methods of fault detection filter synthesis for a class of nonlinear systems. Observer-based LMI synthesis methods for T-S systems subjected to unknown inputs are presented. Subsequently, multi-objective synthesis problem is discussed in FDI framework. When we are interested in these problems in finite frequency domains (FFD), i.e. in frequency ranges of the fault and unknown perturbations known in advance and belonging to finite frequency bands, these classic techniques (in infinite frequency domains) become quite restrictive. Indeed, the problem of multiobjective synthesis in the finite frequency domain is addressed. In a fault diagnosis context, the generated residue must be as sensitive as possible to faults and as robust as possible against unknown perturbations by means of two finite frequency performance indices such as the H_ and H∞ indexes. Based on the Kalman-Yakubovich-Popov generalized lemma (GKYP) and the Lyapunov method, sufficient design conditions have been proposed in recent years. Despite these recent developments, and the use of polyquadratic Lyapunov functions, the multiobjective LMI synthesis conditions are only sufficient. Still open perspectives will be discussed.



 Dr. Simon James Fong, Associate Professor

Dr. Simon James Fong, Associate Professor

Computer and Information Science Department, University of Macau, China
Speech Title: Optimized Machine Learning for Critical Industrial Applications

Abstract: With the rapid development of industrial technology and intelligent information technology, the processing of big data by artificial intelligence (AI) enables industrial production to reach a higher level of automation. This is because AI has the ability of learning and identifying manufacturing defects using machine learning. It can control, monitor, and predict the state of the manufacturing equipment through the production data it has obtained, and it can achieve self-learning by establishing a neural network. On this basis, industrial production can rely on AI to achieve advanced intelligent requirements. As a branch of computer science and technology, the buzzword AI is actually rebranded from traditional machine learning techniques. But in industrial applications, especially for critical applications, the demand for precision and performance of AI is extremely high. Any mistake made by the AI means life and death.
Machine Learning (ML) has been around for decades, empowering many AI applications from computer vision to bioinformatics. Recently Deep Learning gained a remarkable popularity as a branch of ML, by its power to progressively extract higher-level features from the raw input through multiple "deep" layers. Convolutional Neural Network (CNN) is such a flagship model of DL that has unprecedented influential innovations in the field of computer vision and object recognition. While CNN has shown its power in many real-life case studies and successful deployment, recently much attentions of computer scientists are focused on how to build a best CNN for a given task with the best performance [1]. In this talk, I will describe holistic methodology called Optimized Learning (OL) which is designed to uplift the performance of DL, from augmenting the input data, to the CNN optimization and corrective output learning. The context of optimization in OL here is different from traditional optimization algorithms. ML usually acts indirectly in terms of enhancing the prediction performance. It is supposed that optimization in OL needs to be done at several levels and at different places of a ML model. This endeavor aims at leveraging a better ML/DL model for better outcomes, especially in critical applications where the best possible accuracy matters. Some prior works have already been done and applied in industries [2]. Some demos in real commercial AI projects will be shown, with a highlight of the importance of researching for enhanced ML/DL algorithms to better solve industrial problems.

References:
[1] Latest Journal Papers about artificial intelligence in industrial applications:
https://www.sciencedirect.com/journal/computers-and-electrical-engineering/special-issue/10H6P2R11TZ
[2] Examples of AI in actions as industrial solutions
https://www.opencv.ai/#solutions



 Dr. Dmitry G. Korzun, Adjunct Professor

Dr. Dmitry G. Korzun, Adjunct Professor

Department of Computer Science, Institute of Mathematics and Information Technology, Petrozavodsk State University (PetrSU), Russia;
Leading Research Scientist, Head of Data Mining Lab, Deputy Director for Research of Artificial Intelligence Center
Speech Title: Edge Analytics for Bearing Fault Detection based on Convolution Neural Network

Abstract: Advanced technologies of Sensorics and Internet of Things enable realtime data analytics based on multiple sensors covering the target industrial production system and its manufacturing processes. The rolling bearings fault detection problem is one of the most urgent and could be solved using convolution neural networks and edge artificial intelligence (edge AI) devices. The limitations of the hardware platform must be taken into account to achieve maximum performance. In this paper, we analyze efficient CNN architecture for bearings fault detection that is able to process data in real-time on edge AI devices. We observe that the accuracy of CNN is unsatisfactory for practical use, and better accuracy is possible with increasing the number of bearings in the training dataset. The invited speech is prepared together with PhD students Valentin, Perminov and Vladislav Ermakov from PetrSU. The reported study was funded from Russian Fund for Basic Research according to Research Project No. 19-07-01027.



Dr. Xuanhua Xu, Professor, Doctoral Supervisor

Dr. Xuanhua Xu, Professor, Doctoral Supervisor

Director of Research Center for Big Data and Intelligent Decision, Department of Management Science and Information Management, Central South University of China
Speech Title: A Large-Scale Group Risk Emergency Decision Method Based on the Entropy of Fuzzy and Conflict

Abstract: Based on the decision risk caused by both the ambiguity of emergency decision information and the large group preference conflict, a large group risk emergency decision method based on the Entropy of Fuzzy and Conflict is proposed. The first, the decision group is clustered by preferences to form aggregation preference matrix. Second, the interval-valued intuitionistic fuzzy (IVIF) distance is proposed in the form of intuitionistic fuzzy (IF) number in order to reduce the loss of preference information. And generalized IVIF number is also defined. Combining with prospect theory, the IF prospect matrix of different cluster is obtained by conversion. Then, large group emergency decision model of fuzzy conflict entropy is constructed, the goal is to minimize the risk in the process of emergency decision. According to the optimization model, the weight of every attribute can be got, and then prospect matrix and attribute’s weight are aggregated to figure out the comprehensive prospect values which decide the ranking of alternatives. Finally, a case analysis and comparison are used to illustrate the rationality and effectiveness of above method.
Keywords: Large-scale group; Emergency decision; entropy of fuzzy and conflict entropy; Risk decision



Dr. Huiyu Zhou, Professor

Dr. Huiyu Zhou, Professor

School of Informatics, University of Leicester, UK
Speech Title: Artificial Intelligence in Health Care

Abstract: Artificial intelligence has significantly influenced the health sector for years by delivering novel assistive technologies from robotic surgery and hospital management systems to versatile biosensors that enable remote diagnosis and efficient treatment. While the COVID-19 pandemic is devastating, the uses of AI in the healthcare sector are dramatically increasing and it is a critical time to look at its impact and possible limitations in different aspects. In this talk, I will introduce the concept of artificial intelligence (AI) and its uses. Then, I discuss the current public opinion on AI and its hype. I also present the regulation of AI in the community, followed by the discussion on challenges in the field. Finally, I predict the future work in AI using a few examples.
Keywords: Artificial intelligence; health care; hype; regulation; challenges.



Dr. Feng Feng, Professor

Dr. Feng Feng, Professor

Xi'an University of Posts and Telecommunications, China
Speech Title: An Order-theoretic Framework for Multiple Attribute Decision Making Based on Weighted Intuitionistic Fuzzy Soft Sets

Abstract: Decision making is a ubiquitous activity in the real world, which can be seen as a process of ranking a collection of alternatives or selecting the optimal one(s) from them based on the available information. Multiple attribute decision making (MADM) refers to the decision making process in which alternatives are evaluated by virtue of several attributes, reflecting the performance of alternatives from independent perspectives. The notion of intuitionistic fuzzy soft sets provides an elegant framework for addressing MADM problems in an intuitionistic fuzzy setting. In this talk, we first introduce the history and recent progress of intuitionistic fuzzy multiple attribute decision making. Then some rudiments regarding intuitionistic fuzzy soft sets, order relations and preference structures are recalled. Moreover, we establish an order-theoretic framework for MADM based on weighted intuitionistic fuzzy soft sets. In the proposed scheme, the essence of intuitionistic fuzzy multiple attribute decision making is described as the process of aggregating the initial information expressed as a weighted intuitionistic fuzzy soft set and deriving a preference structure on the universe of alternatives. Illustrative examples are presented to demonstrate the validity and generality of the proposed framework.



 Dr. Lanyong Zhang, Associate Professor

Dr. Lanyong Zhang, Associate Professor

College of Automation, Harbin Engineering University (HEU), China
Speech Title: Edge Intelligent Epidemic Control System Based on Visual Internet of Things

Abstract: The research goal of this paper is a big data intelligent epidemic management and control system in public places based on computer vision technology, innovatively introducing age as the basis for fever discrimination, comprehensively using computer vision technology to make up for the shortcomings of manual detection and traditional detection, and it is more suitable for application public places in a big data environment. Introduced the use of PyCharm, camera, infrared camera sensor, Newland edge computing NLE-AI800 development board, touch screen, the software and hardware of the intelligent epidemic management system in public places, the construction of cloud platform, and the edge-side task scheduling based on K-means clustering the design of the model. The comprehensive application of various technologies enables the accuracy of mask recognition of the intelligent epidemic management system in public places to reach 87.5%.



V. Padmavathi, Professor

V. Padmavathi, Professor

Department of Computer Science and Engineering, Anurag University, India
Speech Title: Block Chain Technologies and Quantum Computing

Abstract: Blockchain technology secures data from modification as it is a distributed ledger which is secured cryptographically. Most of the recent applications are implemented through blockchain and distributed ledger. Among the prevailing technology, cryptocurrency has taken over the finance sector. Though blockchain is ruling the present generation of technology, it is vulnerable to the attacks by quantum computer. The base to implement these technologies is hashing and digital signatures which are susceptible to threats and attacks. The principles of quantum mechanics are applied to build the blocks to enhance security. These principles are the concepts of quantum computing which uses qubits for communication. These encrypted data blocks rely on the laws of physics. As a result this leads to quantum challenge i.e. superposition of quantum states. The computations are performed through photons or qubits which are produced by means of photon’s polarization. These photons are the quantized features used to for encoding the information. Cryptography in quantum computing can be carried out by the principle of uncertainty which is the one of the principle of quantum mechanics. This quantum cryptography through quantum mechanics can be enhanced as quantum key distribution (QKD) in which distantly apart communicators share a common secret key. The QKD implements sharing of common secret key which is then used to implement blocks.



Dr. Peide Liu, Professor

Dr. Peide Liu, Professor

School of Management Science and Engineering, Shandong University of Finance and Economics, China
Speech Title: A consistency- and consensus-based method for group decision-making with incomplete probabilistic linguistic preference relations

Abstract: The use of incomplete probabilistic linguistic term sets (InPLTSs) can enrich the flexibility of qualitative decision-making information expression, especially in decision-making situations with high time pressure and insufficient knowledge. In this study, a method for group decision-making (GDM) with incomplete probabilistic linguistic preference relations (InPLPRs), considering consistency and consensus simultaneously, is developed. First, to fully explore the ability of InPLTSs to express uncertain information, InPLTSs are specifically classified. Then, an expected multiplicative consistency of InPLPRs is introduced, which is conductive to estimating the missing information more accurately and effectively. Subsequently, considering the consensus of GDM problems, a consensus index, which considers the principle of majority and minority, is developed to measure the agreement degree among multiple individuals. Because individual InPLPRs may not all meet acceptable consistency after reaching consensus, a consistency- and consensus-improving mathematical programing model considering information distortion is presented. Then, to aggregate all individual preference relationships into a collective one, a reliability induced ordered weighted geometric operator is introduced, whose induced variable reliability is determined by the confidence degree and consistency index of individual preference relationships. Furthermore, a multi-phase algorithm with InPLPRs is developed to solve GDM problems. Finally, a numerical example is presented to illustrate the applicability of the proposed method, and some detailed validity test and comparative analysis are conducted to highlight the advantages of the proposed method.



Sayan Kaennakham, Associate Professor

Sayan Kaennakham, Associate Professor

School of Mathematics, Suranaree University of Technology, Thailand
Speech Title: Generalized-Multiquadric Radial Basis Function Neural Networks (RBFNs) with Variable Shape Parameters for Function Recovery

Abstract: After being introduced to approximate two-dimensional geographical surfaces in 1971, the multivariate radial basis functions (RBFs) have been receiving a great amount of attention from scientists and engineers. In 1987 the idea was extended into the construction of neural networks corresponding to the beginning of the era of artificial intelligence, forming what is now called ‘Radial Basis Function Neural Networks (RBFNs)’. Ever since, RBFNs have been developed and applied to a wide variety of problems; approximation, interpolation, classification, prediction, in nowadays science, engineering, and medicine. This also includes numerically solving partial differential equations (PDEs), another essential branch of RBFNs under the name of the ‘Meshfree/Meshless’ method. Amongst many, the so-called ‘Multiquadric (MQ)’ is known as one of the mostly-used forms of RBFs and yet only a couple of its versions have been extensively studied. This study aims to extend the idea toward more general forms of MQ. At the same time, the key factor playing a very crucial role for MQ called ‘shape parameter’ (where selecting a reliable one remains an open problem until now) is also under investigation. The scheme was applied to tackle the problem of function recovery as well as an approximation of its derivatives using six forms of MQ with two choices of the variable shape parameter. The numerical results obtained in this study shall provide useful information on selecting both a suitable form of MQ and a reliable choice of MQ-shape for further applications in general.