Speakers

SPEAKERS

Prof. Pingyi Fan

Tsinghua University, China

Dr. Pingyi Fan is a professor of the Department of Electronic Engineering of Tsinghua University. He received Ph.D. degree at the Department of Electronic Engineering of Tsinghua University in 1994. From 1997 to 1999, he visited the Hong Kong University of Science and Technology and the University of Delaware in the United States. He also visited many universities and research institutes in the United States, Europe, Japan, Hong Kong and Singapore. He has obtained many research grants, including national 973 Project, 863 Project, mobile special project and the key R&D program, national natural funds and international cooperation projects. He has published more than 190 SCI papers (more than 130 IEEE journals), and 4 academic books. He also applied for more than 30 national invention patents, 5 international patents and. He won seven best paper awards of international conferences, including IEEE ICC2020 and Globecom 2014, and received the best paper award of IEEE TAOS Technical Committee in 2020, the excellent editor award of IEEE TWC (2009), etc. He has served as the editorial board member of several Journals, including IEEE and MDPI. He is currently the editorial board member of Open Journal of Mathematical Sciences, the deputy director of China Information Theory society, the co-chair of China's 6G-ANA TG4, and the chairman of Network and Communication Technology Committee of IEEE ChinaSIP. His current research interests are in 6G wireless communication network and machine learning, semantic information theory and generalized information theory, big data processing theory, intelligent network and system detection, etc.

Title: 

Identifying Machines with Sounds：Anomaly Detection with  GAN-based Approaches

Abstract: 

Digital Twins and Industry 4.0 are becoming the most promising trends in the near future for modern industrial manufacturing and production managements.  Anomaly detection is the critical issue for them.  There are two different ways to do it. One is based on the images or videos observed by using sensors with camera;  Another is based on the sensors of audios.  In fact, the techniques with images or video can only check the abnormal statuses of the machine or equipment  appearing in the surfaces. But the sounds from the machine or equipment can be used to check their inner anomaly statuses.  Machine Sounds have been considered as one important feature in future digital twins and industry 4.0. In this talk, we first review the developments of the anomalies identification problem by machine sounding and then present a new generative adversarial network (GAN) which combines GAN with autoencoder, refered to as AEGAN, where anomalies are detected from two complementary perspectives: error reconstruction measured by the generator and embedding features extracted from the discriminator. The experimental results will show that AEGAN reaches the state-of-the-art performance over two DCASE datasets among unsupervised methods, which indicates that the AEGAN performs well on widely-used working scenarios. Later on, we also introduce the MIM-GAN theory and its application in Anomaly detection. Finally, some conclusions and future research directions are given.

Prof. Yulin Wang

Yulin Wang is a full professor in the School of Computer Science, Wuhan University, China. His research interests include image and video processing, digital rights management, information security, intelligent system, e-commerce, IoT, code clone and so on.

He got his PhD degree from University of London, UK. He got his master and bachelor degree from Huazhong University of Science and Technology（HUST）and Xi-Dian University respectively, both in China.

Before joining the Wuhan University, he has worked in Hi-tech IT industry, including HUAWEI© and national research institute, for more than ten years. He has involved more than 15 national and international research projects. In recently 10 years, Prof. Wang has published 1 book, and 50+ journal and conference papers, including in IEEE TIP. He holds 10 authorized patents.

Prof. Wang served as EiC of 2 international journals and reviewer of top IEEE and ACM journals. He also served as reviewer of Innovative talents projects and national  research funds, including National High Technology Research and Development Program of China. Prof. Wang was the external PhD advisor of Dublin City University, Ireland during 2008-2010.

In recently 10 years, Prof. Wang served as chairman of more than 10 international conferences, and keynote speakers in more than 20 international conferences. Besides UK, he visited US, France,Italy, Portugal,Croatia, Australia, Germany, korea, Ireland,Singapore, Malaysia, Japan, and Hong Kong. In addition, Prof. Wang has been appointed as the deputy director of Hubei provincial science and technology commission (CAPD) since 2014.

Title: Image Authentication and Tamper Localization

Abstract: 

Image authentication can be used in many fields, including e-government, e-commerce, national security, news pictures, court evidence, medical image, engineering design, and so on. Since some content-preserving manipulations, such as JPEG compression, contrast enhancement, and brightness adjustment, are often acceptable—or even desired—in practical application, an authentication method needs to be able to distinguish them from malicious tampering, such as removal, addition, and modification of objects. Therefore, the traditional hash-based authentication is not suitable for the application. As for the semi-fragile watermarking technique, it meets the requirements of the above application at the expense of severely damaging image fidelity. In this talk, we propose a hybrid authentication technique based on what we call fragile hash value. The hash value is derived from the relative difference between each pair of the selected DCT coefficient in a central block and its counterpart which is estimated by the DC values of the center block and its adjacent blocks. In order to achieve blind authentication, we hide the hash value in the specified boundary of the image. The technique can blindly detect and localize malicious tampering, while maintaining reasonable tolerance to conventional content-preserving manipulations. Finally, we point out the direction using deep leaning technique for image authentication.

Prof. Jixin Ma

Dr Jixin Ma is a Full Professor in the School of Computing and Mathematical Sciences, University of Greenwich, United Kingdom. He has been the Director of the Centre for Computer and Computational Science, and the Director of School’s PhD/MPhil Programme. He is also a Visiting Professor of Beijing Normal University, Auhui University, Zhengzhou Light Industrial University, and City University of Macau.

Professor Ma obtained his BSc and MSc of Mathematics in 1982 and 1988, respectively, and PhD of Computer Sciences in 1994. His main research areas include Data Science, Artificial Intelligence and Information Systems, with special interests in Temporal Logic, Temporal Databases, Reasoning about Action and Change, Case-Based Reasoning, Pattern Recognition, Graph Matching and Information Security. He has been a member of British Computer Society, American Association of Artificial Intelligence, ICIS/IEEE, and Special Group of Artificial Intelligence of BCS. Professor Ma has been the Editor of several international journals and international conference proceedings, and Program Chair/Invited Keynote Speakers of many international conferences. He has published more than 200 research papers in peer-reviewed international journals and conferences.

Title: The Notion of Time in Computer Science

Abstract: 

The notion of time plays an important role in modelling natural phenomena and human activities concerning the dynamic aspect of the real world. Virtually most information in the universe of discourse is time-dependent and suitable methodologies are needed to deal with the rich temporal issues in computer-based systems. Particularly, many Data Science and Artificial Intelligence applications need to deal with the temporal dimension of data, the change of information over time and the knowledge about how it changes. The purpose of this talk is to: (a) motivate and explain a topic of emerging importance in Computer Science and Artificial Intelligence; (b) provide an overview on some fundamental issues with respects to temporal ontology; (c) present a brief introduction to temporal representation and reasoning in Computer Science and Artificial Intelligence in terms of some illustrating examples.

Prof. Yajun Liu

Prof. Yajun Liu was born on September 20, 1974 in Jiangxi, China. Native speaker of Chinese, fluent in English. His Education and Academic Research Experiences is as follows:

December, 2016- Now Professor in South China University of Technology School of Mechanical and Automotive Engineering.

December, 2009- December, 2010. Visiting Professor in Fluid Power Research Center (FPRC) Purdue University at West Lafayette, USA.

Feb, 2005 – July, 2016. Post-doctoral Research Fellow, Tokheim JV company in China.

June, 2002 Ph. D. in Mechanical Engineering. South China University of Technology, Guangzhou,China.

His research interests include Digital signal processing technology and its application in mechanical systems (such as hydraulic System for Energy Saving.); Intelligence control and Manufacturing

Engineering. Moreover, Prof. Yajun Liu has published more than 270 papers in Journals and proceedings of international conferences. 40+ patents on Mechanical System design and manufacturing.