Detailed Schedule
4th January 2025
IIT Hyderabad
4th January 2025
IIT Hyderabad
Time: 08:00 AM – 09:00 AM
Registration
Time: 9:00 AM – 10:00 AM
Technical Session I (Invited Talk):
Speaker: Prof. Nirmalya Roy (University of Maryland, Baltimore County )
Speaker Website: https://mpsc.umbc.edu/
Lecture Title: Designing Camera-based Physiological Health Parameter Sensing on the Edge
Session Chair: Dr. Jaydeep Howladar, NIT Durgapur
Prof. Nirmalya Roy
Dr. Nirmalya Roy is a Professor in the Information Systems Department at the University of Maryland, Baltimore County (UMBC), where he leads the Mobile, Pervasive, and Sensor Computing (MPSC) Lab. He also serves as the Director of the Center for Research in Use-Inspired Cyber-Physical Systems (CYPRESS) and the Associate Director of the Center for Real-time Distributed Sensing and Autonomy (CARDS) at UMBC. His current research interests include applied AI/ML with applications in smart health, cyber-physical systems, IoT, robotics, and autonomy. Dr. Roy has received numerous accolades, including best paper awards at IEEE/ACM DCOSS 2023, SmartComp 2023 and 2022, SPIE 2022, CHASE 2021, IGSC 2020, Elsevier PMC 2020, QShine 2009, and PerCom 2006. Dr. Roy is a co-PI on the ArtIAMAS (AI and Autonomy for Multi-Agent Systems) cooperative research agreement with the Army Research Lab (ARL), a collaboration with the University of Maryland, College Park, running from 2021 to 2026. He has secured funding from various prestigious sources, including the DoD, ARL, ONR, NSF (EAGER, CPS, US-India Collaborative Research, REU Site, CAREER, and GCTC), Alzheimer’s Association, Constellation E2: Energy to Educate, and UMB-UMBC Research and Innovation Partnership. More information about his research, students, and projects can be found on the following websites: MPSC Lab || REU SCC || CYPRESS || CARDS
Title of the Talk: Designing Camera-based Physiological Health Parameter Sensing on the Edge
Abstract: Contactless physiological health parameter sensing using video cameras provides a low-cost, ubiquitous, and easy-to-deploy solution for continuous health monitoring and assessment. Remote photoplethysmography (rPPG) and respiration rate estimation, for instance, enable measurement of two key human vital signs: heart rate (HR) and respiratory rate (RR). These vital signs can be extracted from facial and respiration-induced chest movement videos using regular camera sensors. However, traditional signal processing methods for deriving these vital signs from videos often rely on heuristics and fail to harness the power of data-driven deep learning (DL) models. In this talk, I will articulate the challenges in developing robust data-driven models for rPPG estimation, particularly the inherent aleatoric (irreducible) uncertainty in ground truth data annotation. This uncertainty arises due to factors such as synchronization issues between source (camera) and target (ground truth) data streams, sensor placement and heterogeneities, and inter-subject variations. These challenges hinder the development of traditional end-to-end DL models, potentially leading to overfitting on irrelevant noise in the absence of clean labels. To address these uncertainties and build robust DL models for rPPG estimation, I will discuss three novel approaches: (a) Multi-task Learning: A method that separates individual targets while learning shared embeddings across noisy ground truth data to identify core rPPG features, (b) Self-Supervised Learning: An approach that leverages unlabeled rPPG data to learn intrinsic rPPG properties and enhance feature representation and signal reconstruction by incorporating prior domain knowledge (e.g., HR frequency, phase, and temporal coherence), (c) Generative Adversarial Learning: A framework that enables fine-grained rPPG feature learning without direct supervision, leveraging large-scale rPPG datasets. I will also present validations of these approaches on our in-house MPSC-rPPG dataset as well as multiple public datasets, with open-source code for further exploration. Additionally, I will demonstrate RhythmEdge, a real-time heart rate estimation system built using a low-cost camera sensor and discuss rPPG-specific pruning techniques to optimize model size for efficient edge deployment. The talk will conclude with future research directions and insights into our ongoing work on respiratory rate estimation using a particle-video-based approach.
Time: 10:00 AM – 11:00 AM (IST) : Paper Presentations
Session Chair: Dr. Bishakh Ghosh, Founder, Startup Pinggy
1. Grouping nodes based PBFT for Preventing Fake Educational Certificates Verification
Amritesh Kumar (IIT Jodhpur), Nitin Bhatia (IIT Jodhpur) and Debasis Das (IIT Jodhpur)
2. A Scalable Framework for Multi-cloud IoT Data Synchronization
Arnab Mallick (CMERI Durgapur) and Rajesh P. Barnwal(CMERI Durgapur)
3. Secure and Expressive Authorized Keyword Search in Cloud-Assisted Cyber-Physical Systems
Kasturi Routray (IIT Bhubaneswar) and Padmalochan Bera (IIT Bhubaneswar)
Time: 11:00 AM – 11:30 AM (IST) : Tea Break
Time: 11:30 AM – 12:30 PM
Technical Session II (Invited Talk):
Speaker: Dr. Soumyajit Chatterjee
Research scientist at the Pervasive Systems Department of Nokia Bell Labs, Cambridge
Speaker Website: https://sites.google.com/view/sjitiit.
Lecture Title: Efficient Machine Learning for the Edge: Resolving Challenges of Labeling, Collecting, and Collaborating Information Across Devices
Session Chair: Dr. Sujoy Saha, NIT Durgapur
Dr. Soumyajit Chatterjee
Dr. Soumyajit Chatterjee is a research scientist at the Pervasive Systems Department of Nokia Bell Labs, Cambridge, UK, where he focuses on efficient machine learning and pervasive computing. His works focus on human activity recognition, human-computer interaction, and behavioral sensing through wearables and smartphones. During his doctoral research at IIT Kharagpur, he was supervised by Dr. Sandip Chakraborty and Dr. Bivas Mitra; Soumyajit published several papers in reputed conferences such as IEEE PerCom, IEEE INFOCOM, ACM ICMI, IEEE DCOSS-IoT, and journals like IEEE TMC, ACM TIoT, ACM TIST, IEEE TNSM. Soumyajit has also been a part of several program committees and has received the Outstanding Contribution Award from the COMSNETS Association. He also holds an M.Tech from IIT (ISM) Dhanbad, where he was awarded the ISM Silver Medal, and has prior software industry experience. The link to his personal webpage can be found here: https://sites.google.com/view/sjitiit.
Title of the Talk: Efficient Machine Learning for the Edge: Resolving Challenges of Labeling, Collecting, and Collaborating Information Across Devices
Efficiency is one of the key design aspects for bringing machine learning (ML) to the edge, where resource constraints and scalability challenges prevail. This talk explores efficiency from three key perspectives: labeling efficiency, minimizing data collection efforts, and fostering collaborative learning across devices. First, I will present an innovative approach leveraging state-of-the-art large language models (LLMs) to automate annotation tasks in sensor data, significantly reducing the human effort that is usually required to label any dataset. Next, I will try to introduce an idea for uncovering hidden classes within audio datasets, demonstrating how to make the most out of existing datasets, thus reducing the efforts to perform new data collections for every new application. Finally, I will introduce a robust framework for deploying federated learning across resource-constrained devices, enabling collaborative model training across multiple edge devices while preserving privacy and reducing communication overhead. Together, these contributions highlight the importance of interdisciplinary methodologies in driving efficiency and scalability in machine learning systems, paving the way for broader accessibility and practical deployment.
Time: 12:30 PM – 1:00 PM : Sponsored Key Note
1:00 PM-2:00 PM : LUNCH
Time: 2:00 PM – 3:30 PM : Joint Keynotes for all workshops (Dilip Krishnaswamy, Kiran Kuchi)
Time :3:30 PM – 4:30 PM: Paper Presentation (3 Papers)
Session Chair: Dr. Suoy Saha, NIT Durgapur
4. Non-Fungible Tokens (NFTs): A Systematic Study of Trust Criteria
Rangin Lahiri (UEM Kolkata), Saikat Chakrabarti (UEM Kolkata) and Subrata Saha (UEM Kolkata)
5. Faster Convergence of Adaptive Data Rate in Dynamic LoRa-based IoT Network Applications
Alekhya Gorrela (BITS Pilanai Hyderabad) and Nikumani Choudhury (BITS Pilanai Hyderabad)
6. Optimizing Autonomous Intersection Control Using Single Agent Reinforcement Learning
Yash Ganar (RGIPT Amethi), Vinay Kumar (RGIPT Amethi), Shraddha Dulera (IITRAM Gujrat) and Ram Narayan Yadav (IITRAM Gujrat)
Time: 4:30 PM : Best Paper Award