Keynote Speakers

Prof. Nitin Vaidya

Georgetown University

 

Title of the talk: Fault-Tolerant Distributed Optimization and Learning 

Speaker’s Bio:-

Nitin Vaidya is the Robert L. McDevitt, K.S.G., K.C.H.S. and Catherine H. McDevitt L.C.H.S. Chair Professor Computer Science at Georgetown University, where he served as the Department Chair during 2018-24. His current research interests are in the area of distributed algorithms, and previously he has worked on wireless networks. He received a Ph.D. from the University of Massachusetts at Amherst. He previously served as a Professor and Associate Head in Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. He has co-authored papers that received awards at several conferences, including SSS, ACM MobiHoc and ACM MobiCom. He is a fellow of the IEEE. He has served as the Chair of the Steering Committee for the ACM PODC conference, as the Editor-in-Chief for the IEEE Transactions on Mobile Computing, and as the Editor-in-Chief for ACM SIGMOBILE publication MC2R. 

Abstract of the talk

Abstract:  Consider a network of agents wherein each agent has a private cost function. In the context of distributed machine learning, the private cost function of an agent may represent the “loss function” corresponding to the agent’s local data. The objective here is to identify parameters that minimize the total cost over all the agents. In machine learning for classification, the cost function is designed such that minimizing the cost function should result in model parameters that achieve higher accuracy of classification. Similar problems arise in the context of other applications as well. Our work addresses privacy and security (or fault-tolerance) of distributed optimization with applications to machine learning. In privacy-preserving machine learning, the goal is to optimize the model parameters correctly while preserving the privacy of each agent’s local data. In fault-tolerance, the goal is to identify the model parameters correctly while tolerating adversarial agents that may be supplying incorrect information. When a large number of agents participate in distributed optimization, security compromise of some of the agents becomes increasingly likely. We constructively show that privacy-preserving and secure algorithms for distributed optimization exist. The talk will provide intuition behind these algorithms, with a focus on fault-tolerant algorithms. 

Prof. Shambhu J. Upadhyaya

University at Buffalo

The State University of New York

Title of the talk: Detecting Ransomware with Machine Learning and Natural Language Processing Models

Speaker’s Bio:-

Prof. Shambhu J. Upadhyaya is a faculty member in the Department of Computer Science and Engineering at the State University of New York at Buffalo, where he directs the Center of Excellence in Information Systems Assurance Research and Education (CEISARE), a designation by the National Security Agency (NSA). He earned his BE and ME degrees from the Indian Institute of Science in 1979 and 1982, respectively, and his PhD from the University of Newcastle, Australia, in 1986. His research focuses on information assurance, computer security, fault-tolerant computing, and reliable distributed systems. He has authored over 300 publications in peer-reviewed journals and conferences. His work has been funded by the National Science Foundation, U.S. Air Force Research Laboratory, DARPA, the National Security Agency, IBM, Intel Corporation, Harris Corporation, and Cisco. Prof. Upadhyaya has held visiting research faculty positions at the University of Illinois at Urbana-Champaign, Intel Corporation, the U.S. Air Force Research Laboratory, and the U.S. Naval Research Laboratory. He has been awarded the IBM Faculty Partner Fellowship, the National Research Council Faculty Fellowship, the Lilly Endowment Teaching Fellowship, and the Tan Chin Tuan Exchange Fellowship of Singapore. Additionally, he has served on the editorial boards of several academic journals and has organized numerous international conferences and workshops. Prof. Upadhyaya is a Fellow of IEEE.

Abstract of the talk

Abstract: Ransomware is a malicious software that encrypts a system's critical data and demands a ransom for its release. If the ransom is paid, access is typically restored; otherwise, the data remains inaccessible to the victim. However, the threat landscape is evolving, with recent attacks demonstrating greater sophistication, including stealth tactics and contingency strategies. Modern ransomware variants fall under the category of advanced persistent threats (APT) and are often carried out by nation-state actors with vast resources at their disposal. Traditional security measures are largely ineffective against the constantly evolving nature of APT-type ransomware, emphasizing the urgent need for an intelligent and robust intrusion detection system (IDS). In this talk, we will begin by examining APT malware and reviewing recent ransomware attacks that have severely impacted critical national infrastructure. We will then highlight key research challenges and explore existing solutions for ransomware mitigation. Finally, we will present our latest research on ransomware detection using machine learning and natural language processing models, discussing the results, trade-offs, and implications for designing an effective IDS.

 

Prof. Ram Bilas Pachori

IIT Indore

Title of the talk: Multichannel signal processing enabled machine learning methods for medical applications

Speaker’s Bio:-

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 IIT Kanpur, India, in 2003 and 2008, respectively. Before joining the IIT Indore, India, he was a Post-Doctoral Fellow at the Charles Delaunay Institute, University of Technology of Troyes, France (2007-2008) and an Assistant Professor at the Communication Research Center, International Institute of Information Technology, Hyderabad, India (2008-2009). He was an Assistant Professor (2009-2013), an Associate Professor (2013-2017), and a Professor (2017-2023) at the Department of Electrical Engineering, IIT Indore, where he has been a Professor (HAG) since 2023. He was a Visiting Professor at the Department of Computer Engineering, Modeling, Electronics and Systems Engineering, University of Calabria, Rende, Italy, in July 2023; Faculty of Information & Communication Technology, University of Malta, Malta, from June 2023 to July 2023; Neural Dynamics of Visual Cognition Lab, Free University of Berlin, Germany, from July 2022 to September 2022; School of Medicine, Faculty of Health and Medical Sciences, Taylor’s University, Malaysia, from 2018 to 2019. Previously, he was a Visiting Scholar at the Intelligent Systems Research Center, Ulster University, Londonderry, UK, in December 2014. His research interests include signal and image processing, biomedical signal processing, non-stationary signal processing, speech signal processing, brain-computer interface, machine learning, and artificial intelligence and internet of things in healthcare. He was an Associate Editor of IEEE Transactions on Neural Systems and Rehabilitation Engineering (2021-2024). Currently, he is an Associate Editor of Electronics Letters, IEEE Open Journal of Engineering in Medicine and Biology, Computers and Electrical Engineering, and Biomedical Signal Processing and Control. He is also serving as a Handling Editor of Signal Processing and an Editor of IETE Technical Review journal. He is a Fellow of Institute of Electrical and Electronics Engineers (IEEE), Institution of Engineering and Technology (IET), Institution of Electronics and Telecommunication Engineers (IETE), and Institution of Engineers (India) (IEI). He has authored the textbook titled “Time-Frequency Analysis Techniques and their Applications” (CRC Press, 2023). He has 362 publications, which include journal articles (225), conference papers (96), books (11), and book chapters (30). He has also eight patents, including two granted (Australian patent and Indian patent) and six published (Indian patents). His publications have been cited approximately 18500 times with h-index of 74 according to Google Scholar. 

Abstract of the talk

Abstract: In the last one or two decades, adaptive signal decomposition techniques have gained popularity for their broad applicability to almost all fields of science and technology. Empirical mode decomposition has been proposed to decompose the signal into amplitude-frequency modulated components (basis functions). Several methods have been proposed, followed by empirical mode decomposition for adaptive decomposition and to obtain improved signal representation. Empirical wavelet transform (EWT), Fourier-Bessel series expansion-based EWT (FBSE-EWT), iterative filtering, variational mode decomposition are a few popular techniques among adaptive decomposition techniques. Recent advancements in sensor technology make it easier to acquire signals from multiple sources simultaneously, which demands multivariate/multi-channel signal decomposition methods. The univariate iterative filtering has been extended for processing multichannel signals, which will be discussed in this talk. Also, developed intelligent systems based on multivariate iterative filtering and machine learning (ML) for brain-computer interface (BCI) and schizophrenia detection from multichannel electroencephalogram (EEG) signals will be presented. The obtained results show the effectiveness of the discussed multivariate/multi-channel adaptive signal decomposition techniques. 

Prof. Srinjoy Mitra

University of Edinburgh, UK

Title of the talk: Electronics for Healthcare and Neuroscience

Speaker’s Bio:-

Srinjoy Mitra is an Associate Professor (Reader) at the University of Edinburgh, UK. He received his B.S. degree in physics and electronics from Calcutta, India and his M.Tech. in microelectronics from the Indian Institute of Technology, Bombay, India. After spending a short time in the electronics industry (in India and Japan), he received his Ph.D. from the Institute of Neuroinformatics, ETH Zurich, in 2004. Between 2008 and 2010, he worked as a post-doctoral researcher at Johns Hopkins University, USA.

He then joined the medical electronics team at IMEC, Belgium, as a senior scientist and took up leadership roles in various projects related to bio-potential recording. Electro-encephalography (EEG) measurement ICs and high-density neural recording probes developed by his team have been successfully validated in a clinical environment and are now commercialized. Dr. Mitra has been with the Integrated Micro and Nano Systems, University of Edinburgh, since 2017. His research interests are low-power sensor interfaces, medical/neural electronics, neuromorphic systems, and engineering education. He is the Program Director for the MSc in Sensors and Imaging System and the convenor of the Curriculum Decolonisation at the College of Science and Engineering.

Abstract of the talk

Abstract: Driven by the consumer electronics industry, silicon integrated circuits have followed Moore’s law to deliver generations of powerful, smaller, cheaper computer processors. However, in contrast to conventional Moore’s law, a More-than-Moore axis exists in the industry roadmap. Not limited by the bottlenecks of Moore’s law, this axis has proven to be extremely important in bringing richness and diversification in modern silicon circuits and systems. Recent advances in medical and neural-electronics are a result of such activities. I will first discuss my work on ambulatory healthcare devices and present the advances in neuro-technologies developed by our group in the recent past. Next, I will discuss some ongoing work on point-of-care medical devices like capsule endoscopy, smart garments and other ambulatory sensors. Finally, I will introduce some RFID-based remote sensing systems we are currently working on.

Copyright © 2023 Parala Maharaja Engineering College. All Rights Reserved.

Designed & Developed By SDGI TECHNOSYSTEMS PRIVATE LIMITED