Prof. Ram Bilas Pachori
Indian Institute of Technology Indore, India
Title：Multivariate brain signal processing
Recently, our research group has developed multivariate empirical wavelet transform and multivariate iterative filtering for multi-channel signal processing. These developed methods have been studied for automated EEG signal classification for epilepsy and schizophrenia diagnosis. In this keynote speech, these above mentioned methods together with experimental results will be explained.
Ram Bilas Pachori received the B.E. degree with honours in Electronics and Communication Engineering from Rajiv Gandhi Technological University, Bhopal, India in 2001, the M.Tech. and Ph.D. degrees in Electrical Engineering from Indian Institute of Technology Kanpur, India in 2003 and 2008, respectively.
He worked as a Post-Doctoral Fellow at Charles Delaunay Institute, University of Technology of Troyes, France during 2007-2008. He served as an Assistant Professor at Communication Research Center, International Institute of Information Technology, Hyderabad, India during 2008-2009. He served as an Assistant Professor at Department of Electrical Engineering, Indian Institute of Technology Indore, India during 2009-2013. He worked as an Associate Professor at Department of Electrical Engineering, Indian Institute of Technology Indore during 2013-2017 where presently he has been working as a Professor since 2017. Currently, he is also associated with Center for Advanced Electronics at Indian Institute of Technology Indore. He was a Visiting Professor at Neural Dynamics of Visual Cognition Lab, Free University of Berlin, Germany during July-September, 2022. He has served as a Visiting Professor at School of Medicine, Faculty of Health and Medical Sciences, Taylor’s University, Malaysia during 2018-2019. Previously, he has worked as a Visiting Scholar at Intelligent Systems Research Center, Ulster University, Londonderry, UK during December 2014.
His research interests are in the areas of Signal and Image Processing, Biomedical Signal Processing, Nonstationary Signal Processing, Speech Signal Processing, Brain-Computer Interfacing, Machine Learning, and Artificial Intelligence & Internet of Things in Healthcare.
He is an Associate Editor of Electronics Letters, IEEE Transactions on Neural Systems and Rehabilitation
Engineering, Biomedical Signal Processing and Control and an Editor of IETE Technical Review journal. He is a
senior member of IEEE and a Fellow of IETE, IEI, and IET. He has served as member of
review boards for more than 100 scientific journals. He has also served in the scientific committees of various national and international conferences. He has delivered more than 250 talks and lectures in conferences, workshops, short term courses, and academic events organized by various institutes. He has been ranked #21 in India among top scientists for 2022 in the field of Computer Science by Research.com website (March, 2022). He has been listed in the world's top 2 % scientists in the study carried out at Stanford University, USA (October, 2020, October, 2021, and October, 2022). He has received several awards including Achievement Award (IICAI conference, 2011), Best Paper Award (ICHIT conference, 2012), Excellent Grade in the Review of Sponsored Project (DST, 2014), Best Research Paper Awards (IIT Indore, 2015 & 2016), Premium Awards for Best Papers (IET Science, Measurement & Technology journal, 2019 & 2020), IETE Prof. SVC Aiya Memorial Award (2021), and Best Paper Award (DSPA Conference, 2022).
He has supervised 14 Ph.D., 23 M.Tech., and 42 B.Tech. students for their theses and projects (15 Ph.D., 03 M.Tech., 01 M.S. (by Research), and 07 B.Tech. under progress). He has 266 publications which include journal papers (164), conference papers (72), books (08), and book chapters (22). He has also three patents: 01 Australian patent (granted) and 02 Indian patents (filed). His publications have been cited approximately 12,000 times with h-index of 57 according to Google Scholar. He has worked on various research projects with funding support from SERB, DST, DBT, CSIR, and ICMR.
Prof. Gang Wang
School of Automation, Beijing Institute of Technology, China
Title： Why Heuristics Work? Three Examples in Machine Learning
Heuristics are widely used in machine learning and data science, from high-resolution imaging, to deep and reinforcement learning (RL). Despite the challenges such as the highly nonconvex landscape in training deep neural networks, simple heuristics are often surprisingly effective in finding high-quality solutions. To gain a deeper understanding of why and how heuristics work well, this talk will discuss three concrete problems. The first is a century-old problem known as phase retrieval that emerges in diverse scientific and engineering applications such as X-ray crystallography, where we are given magnitude-only measurements about an image with its phase information completely missing, and we wish to recover the image. The second is the problem of training a two-layer nonlinear (ReLU) neural network over separable data, in which both the “trainability” as well as the generalization issues will be investigated. The third is about temporal-difference (TD) learning, one of the most key concepts in reinforcement learning, whose non-asymptotic analysis has proved challenging. We describe three simple solutions, and present some theory explaining how and why they work well, as well as some numerical examples and applications.
Dr. Gang Wang received a B.Eng. degree in Automatic Control in 2011, and a Ph.D. degree in Control Science and Engineering in 2018, both from the Beijing Institute of Technology, Beijing, China. He also received a Ph.D. degree in Electrical and Computer Engineering from the University of Minnesota, Minneapolis, USA, in 2018, where he stayed as a postdoctoral researcher until July 2020. Since August 2020, he has been a professor with the School of Automation at the Beijing Institute of Technology.
His research interests focus on the areas of signal processing, control, and reinforcement learning with applications to cyber-physical systems and multi-agent systems. He was the recipient of the Best Paper Award from the Frontiers of Information Technology & Electronic Engineering (FITEE) in 2021, the Excellent Doctoral Dissertation Award from the Chinese Association of Automation in 2019, the Best Conference Paper at the 2019 IEEE Power & Energy Society General Meeting, and the Best Student Paper Award from the 2017 European Signal Processing Conference. He is currently on the editorial boards of Signal Processing, Actuators, and IEEE Transactions on Signal and Information Processing over Networks.
Prof. Xiaofeng Ding
Huazhong University of Science and Technology
Title：Privacy Preserving Problems in Deep Learning
Deep learning is increasingly popular, partly due to its widespread application potential, such as in civilian, government and military domains. Given the exacting computational requirements, cloud computing has been utilized to host user data and model. However, such an approach has potential privacy implications. Therefore, we introduce a method to protect user’s privacy in the inference phase of deep learning workflow. Specifically, we use an intermediate layer to separate the entire neural network into two parts, which are respectively deployed on the user device and the cloud server.
I am currently a Professor and Pd.D Supervisor in the School of Computer Science and Technology at Huazhong University of Science and Technology (HUST). I received my Ph.D degree in Computer Science from HUST in 2009. I also worked as Research Fellow at the National University of Singapore and the University of South Australia during 2010-2013. My research interests mainly include data privacy and query processing, data encryption, graph databases and deep learning. Most of my works are published in reputable jounrals or conferences like IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Information Forensics and Security, International Conference on Very Large Data Bases (VLDB), IEEE International Conference on Data Engineering (ICDE), ACM Conference on Information and Knowledge Management (CIKM) and etc.
Prof. Liang Hu
Tongji University, China
Title：Federated Learning: Basic Concepts, Models and Applications
In recent years, more and more countries have been paying increasing attention to data security and personal privacy, which has direct impact on the socioeconomic development. Federated learning, as a promising AI research area, enables machine learning models to obtain the knowledge from different datasets located in different devices or sites without sharing training data. This allows personal data to remain in local devices or sites, reducing possibility of privacy breaches. In this talk, the speaker will introduce the basic concepts of federated learning and the classification of various federated learning models. After that, two real applications that demand high-level privacy will be introduced, where the federated learning methods are employed to guarantee the data and personal privacy. Firstly, the speaker will present the federated learning on crowdsourced HD mapping. Secondly, the speaker will present the potential application of federated learning on person re-identification.
Dr Liang Hu is a full professor with Tongji University and also the Chief AI Scientist with DeepBlue Academy of Science, China. His research interests include recommender systems, machine learning, data science and general intelligence. He has published a number of papers in top-rank international conferences and journals, including WWW, IJCAI, AAAI, ICDM, ICWS, TOIS, IEEE-IS. He has been invited as the program committee of more than 30 top-rank AI international conferences, including AAAI, IJCAI, ICDM, CIKM, and KDD. He also serves as the reviewer of more than ten AI and data science-related international journals, including ACM CSUR, IEEE TKDE, ACM TOIS, IEEE TPAMI, etc. In addition, he has presented eight tutorials on recommender systems and machine learning at top-rank AI conferences including IJCAI, AAAI, SIGIR, and ICDM.
Prof. Longyu Jiang
Southeast University, China
Active Mask-Box Scoring R-CNN for Sonar Image Instance Segmentation
Instance segmentation task for sonar images is an effective way for underwater target recognition. However, the current instance segmentation models often confront a problem that the positioning accuracy is not well correlated with classification confidence which damages the positioning accuracy. Besides, annotating sonar images is a costly work in terms of time and professional knowledge. To tackle these problems, in this paper, we study the instance segmentation algorithm and propose a novel instance segmentation method called Mask-Box Scoring R-CNN(M-B Scoring R-CNN), and apply it in active learning process. M-B Scoring R-CNN uses a boxIoU head to predict the quality of the bounding boxes. It revises the confidence scores of the NMS step during inference to preserve highquality bounding boxes. To deal with the annotating problem, we propose a triplets-based active learning method with balancedsampling. The triplets-based active learning method evaluates the amount of information of unlabeled samples from the aspects of classification confidence, positioning accuracy and mask quality.
The balanced-sampling method selects hard samples from data set to train model to improve the performance to the greatest extent. The experiments results show that M-B Scoring R-CNN has a noticeable improvement on the instance segmentation performance of sonar images by generating more accurate bounding boxes, and the active learning method can reach a satisfying performance with less labeled samples.
Longyu Jiang received her B.Sc, M.Sc, and Ph.D degrees from Wuhan University, China, Southeast University, China, and Grenoble Alpes University, France respectively. She is currently a professor and doctoral supervisor at the School of Computer Science and Engineering, Southeast University, China. Her main research interests include underwater acoustic signal and sonar image processing, artificial intelligence and big data.
In recent years, she has hosted or participated in a number of scientific research projects, such as the French National Scientific Research Agency Fund, the Pre-research Fund of the Equipment Development Department of the Military Commission, the National Natural Science Foundation of China, the Natural Science Foundation of Jiangsu Province, and the Fund for Returned Overseas Chinese Scholars of the Ministry of Education and so on. She has published more than 30 scientific articles in international authoritative journals and conferences, such as IEEE Journal of Oceanic Engineering, The Journal of the Acoustical Society of America, IEEE Transactions on Circuits and Systems I: Regular Paper and so on.
She has been awarded the China Ocean Engineering Science and Technology Award (ranked first), the first prize of National Teaching Achievement Award, the first prize of Teaching Achievement Award in Jiangsu Province, the Teaching Competition Award for young teachers in Southeast University, the first and second prizes of Teaching Achievement awards in Southeast University, and the China-Thailand grant.
Her main social part-time jobs include the evaluation expert of the China Scholarship Council for overseas projects, the member of the Visual Sensing Commission of the China Graphics and Image Association, the member of the Underwater Communication Committee of the Jiangsu Communication Association, and the communication evaluation of the National Natural Science Foundation of China.
Prof. Kehua Guo
Central South University
Title：Multimodal weak sample learning
With the development of machine learning, especially deep learning, the lack of data labels leads to difficulties in traditional machine learning methods. This report introduces research from Dr. Kehua Guo's team about developing machine learning methods to analyze weak sample analysis for multimodal data, and its applications i.e., small sample data enhancement, modal imbalance semantic fusion and weak sample federated learning.
Dr. Kehua Guo is a Professor at the School of Computer Science and Engineering at Central South University. He was selected as The National Youth Talent Support Program, Hunan Furong scholar and got the Hunan Outstanding Youth Fund. Dr. Guo received his Ph.D. in Computer Application Technology from Nanjing University of Science and Technology in 2008. He has been selected as the Chairman of computer education special committee of Hunan Higher Education Society and Secretary General of Hunan Computer Education Instruction Committee. He has long been engaged in research on artificial intelligence, big data, intelligent computing, etc. He has published more than 100 research papers in international journals or conferences. He owns 16 patents for the invention of the country. Some of his research findings have been successfully applied in industry. He is a member of the procedure Committee of many international conferences and serves as guest editors in many well-known SCI journals.
Prof. Ljiljana Trajkovic
Simon Fraser University, Canada
Title: “Machine Learning for Detecting Internet Traffic Anomalies”
Border Gateway Protocol (BGP) enables the Internet data routing. BGP anomalies may affect the Internet connectivity and cause routing disconnections, route flaps, and oscillations. Hence, detection of anomalous BGP routing dynamics is a topic of great interest in cybersecurity. Various anomaly and intrusion detection approaches based on machine learning have been employed to analyze BGP update messages collected from RIPE and Route Views collection sites. Survey of supervised and semi-supervised machine learning algorithms for detecting BGP anomalies and intrusions is presented. Deep learning, broad learning, and gradient boosting decision tree algorithms are evaluated by creating models using collected datasets that contain Internet worms, power outages, and ransomware events.
Ljiljana Trajkovic received the Dipl. Ing. degree from University of Pristina, Yugoslavia, the M.Sc. degrees in electrical engineering and computer engineering from Syracuse University, Syracuse, NY, and the Ph.D. degree in electrical engineering from University of California at Los Angeles. She is currently a professor in the School of Engineering Science, Simon Fraser University, Burnaby, British Columbia, Canada. Her research interests include communication networks and dynamical systems. She served as IEEE Division X Delegate/Director, President of the IEEE Systems, Man, and Cybernetics Society, and President of the IEEE Circuits and Systems Society. Dr. Trajkovic serves as Editor-in-Chief of the IEEE Transactions on Human-Machine Systems and Associate Editor-in-Chief of the IEEE Open Journal of Systems Engineering. She is a Distinguished Lecturer of the IEEE Circuits and System Society, a Distinguished Lecturer of the IEEE Systems, Man, and Cybernetics Society, and a Fellow of the IEEE.