Keynote Speakers
Prof. Ram Bilas Pachori
Indian Institute of Technology Indore, India
>>>Personal Website: Click
Brief Introduction
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 (IIT) Kanpur, Kanpur, India in 2003 and 2008, respectively. He worked as a Postdoctoral Fellow at Charles Delaunay Institute, University of Technology of Troyes, 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, IIT Indore, Indore, India during 2009-2013. He worked as an Associate Professor at Department of Electrical Engineering, IIT Indore, Indore, India 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 IIT Indore. He has served as a Visiting Professor at School of Medicine, Faculty of Health and Medical Sciences, Taylorˊs University, Subang Jaya, Malaysia during 2018- 2019. Previously, he has worked as a Visiting Scholar at Intelligent Systems Research Center, Ulster University, Northern Ireland, 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 and Internet of Things (IoT) 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 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 210 talks and lectures in conferences, workshops, short term courses, and academic events organized by various institutes. He has been listed in the top h-index scientists in the area of Computer Science and Electronics by Research.com website (April, 2020). He has been listed in the world's top 2 % scientists in the study carried out at Stanford University, USA (October, 2020 and October, 2021). 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), and IETE Prof. SVC Aiya Memorial Award (2021). He has supervised 14 Ph.D., 20 M.Tech., and 41 B.Tech. students for their theses and projects. He has 243 publications which include journal papers (150), conference papers (67), books (06), and book chapters (20). He has also two patents: 01 Australian patent (granted) and 01 Indian patent (filed). His publications have been cited more than 10,000 times with h-index of 53 according to Google Scholar. He has worked on various research projects with funding support from SERB, DST, DBT, CSIR, and ICMR.
Speech Title:
Multivariate signal processing with biomedical applications
Abstract:
The multivariate extension of empirical wavelet transform and iterative filtering based non-stationary signal decomposition techniques will be presented. The applications for automated diagnosis of epileptic seizures and schizophrenia from EEG signals will be demonstrated. The experimental results will be explained for the above-mentioned methods and applications.
Prof. Gang Wang
School of Automation, Beijing Institute of Technology, China
>>>Personal Website: Click
Brief Introduction
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.
Speech Title:
“Why Heuristics Work? Three Recent Examples in Machine Learning”
Abstract:
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 fundamental ideas 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.
Prof. Haoji Hu
College of Information Science and Electronic Engineering, Zhejiang University, China
>>>Personal Website: Click
Brief Introduction
Haoji Hu received the B.Sc. degree in electrical engineering from Tsinghua University, China in 2002, and the Ph.D. degree in Electronic and Computer Science from University of Southampton, U.K., in 2007. From 2007 to 2009, he was a Postdoctoral Researcher of digital watermarking with the Communications and Remote Sensing Laboratory, Université Catholique de Louvain, Belgium. In 2009, he joined the College of Information Science and Electronic Engineering, Zhejiang University, China, as an Assistant Professor. He has been promoted to an Associate Professorship since 2013. His research interests mainly focus on deep learning theory and applications, which include deep model compression and acceleration, medical image analysis and image segmentation. He has published more than 50 research papers in international conference and journals, which include Pattern Recognition, IEEE Transactions on Image Processing, Journal of Selected Areas of Signal Processing, AAAI, and CVPR. Dr. Hu is the holder of eleven Chinese patents and one US patent.
Speech Title:
Deep Neural Network Model Compression and Acceleration
Abstract:
Modern deep neural networks (DNNs) usually lead to massive computation and storage consumption, hindering their deployment on mobile and embedded devices. To reduce computation cost, many research works focus on the model compression and acceleration of DNNs .
In this talk, we will first review existing works and future trends in the area of deep neural network compression and acceleration. Then, we will present several of our research works, which include: (1) convolutional neural network pruning; (2) Compression of task-specific neural networks, e.g., face recognition networks, action recognition networks, style transfer networks and makeup transfer networks; (3) Compression of large-scale Transformer networks, which is one of the recent directions of DNN compression.
Finally, we will discuss challenges and future directions in the area of deep neural network compression and acceleration.
Prof. Lamei Zhang
Harbin Institute of Technology, China
>>>Personal Website: Click
Brief Introduction
Lamei Zhang received a Bachelor's degree, Master's Degree and Ph.D. degree in Information and Communication Engineering from Harbin Institute of Technology, Harbin, China in 2004, 2006 and 2010, respectively.
Lamei Zhang is currently an associate professor and ph.D supervisor of the Department of Information Engineering, Harbin Institute of Technology. She is an IEEE senior member and currently serves as the Secretary of IEEE GRSS Harbin Chapter, and a very active Review for many international journals.
Her research interests are in the field of information extraction and interpretation of SAR and polarimetric SAR images, artificial intelligence algorithms and their application in remote sensing. She has published more than 120 academic papers, of which more than 40 have been indexed by SCI.
Speech Title:
Advanced Polarimetric Target Decomposition Techniques and its Applications
Abstract:
Polarimetric SAR (Synthetic Aperture Radar) is an all-day and all-weather active remote sensing radar and it can obtain more detailed information and characteristics of the target by transmitting electromagnetic waves with different polarization modes. Therefore, polarimetric SAR attracts more attention and has been widely used in the fields of environmental monitoring and ground object classification. Polarimetric target decomposition is a typical feature extraction method for polarimetric SAR data. It can decompose the scattering energy into the combination of various basic scattering mechanism to accurately analyze the polarimetric scattering characteristics of targets. In this report, the principles of different polarimetric decomposition methods are introduced and compared. Accordingly, some typical application and results are also introduces.
Assis. Prof. Ahmed Alkhateeb
Arizona State University, USA
>>>Personal Website: Click
Brief Introduction
Ahmed Alkhateeb received his B.S. and M.S. degrees in Electrical Engineering from Cairo University, Egypt, in 2008 and 2012, and his Ph.D. degree in Electrical Engineering from The University of Texas at Austin, USA, in 2016. After the Ph.D., he spent some time as a Wireless Communications Researcher at the Connectivity Lab, Facebook, before joining Arizona State University (ASU) in Spring 2018, where he is currently an Assistant Professor in the School of Electrical, Computer, and Energy Engineering. His research interests are in the broad areas of wireless communications, signal processing, machine learning, and applied math. Dr. Alkhateeb is the recipient of the 2012 MCD Fellowship from The University of Texas at Austin, the 2016 IEEE Signal Processing Society Young Author Best Paper Award for his work on hybrid precoding and channel estimation in millimeter-wave communication systems, and the NSF CAREER Award 2021 to support his research on leveraging machine learning for large-scale MIMO systems.
Speech Title:
Multi-Modal Sensing Aided Communications and the Role of Machine Learning
Abstract:
Wireless communication systems are moving to higher frequency bands (mmWave in 5G and above 100GHz in 6G and beyond) and deploying large antenna arrays at the infrastructure and mobile users (massive MIMO, mmWave/terahertz MIMO, reconfigurable intelligent surfaces, etc.). While using large antenna arrays and migrating to higher frequency bands enable satisfying the increasing demand in data rate, they also introduce new challenges that make it hard for these systems to support mobility and maintain high reliability and low latency. In this talk, I will first motivate the use of sensory data and machine learning to address these challenges. Then, I will present DeepSense 6G, the world's first large-scale real-world multi-modal sensing and communication dataset that enables the research in a wide range of integrated sensing and communication applications. After that, I will go over a few machine learning tasks enabled by the dataset such as radar, LiDAR, camera, and position aided beam and blockage prediction. Finally, I will discuss some future research directions in the interplay of communications, sensing, and positioning.
