UbiNet: Ubiquitous Networked Systems Lab

16/05/2026

🎉 Sayantan Kuila presented our paper "𝐆𝐫𝐚𝐝𝐢𝐞𝐧𝐭 𝐀𝐧𝐠𝐥𝐞𝐬 𝐟𝐨𝐫 𝐑𝐮𝐧𝐭𝐢𝐦𝐞 𝐃𝐞𝐭𝐞𝐜𝐭𝐢𝐨𝐧 𝐨𝐟 𝐁𝐨𝐝𝐲-𝐏𝐨𝐬𝐢𝐭𝐢𝐨𝐧 𝐒𝐡𝐢𝐟𝐭 𝐢𝐧 𝐇𝐮𝐦𝐚𝐧 𝐀𝐜𝐭𝐢𝐯𝐢𝐭𝐲 𝐑𝐞𝐜𝐨𝐠𝐧𝐢𝐭𝐢𝐨𝐧" at the FMSys Workshop @ IEEE/ACM CPS-IoT week 2026! 🚀

A wonderful collaboration with Soumyajit Chatterjee (Brave Software / University of Cambridge) and our team at the Department of Computer Science and Engineering, IIT Kharagpur.

📱 𝐓𝐡𝐞 𝐩𝐫𝐨𝐛𝐥𝐞𝐦: Wearable devices rarely stay in one place -- a smartphone might be in your pocket, on your arm, or in your hand. This body-position heterogeneity silently breaks on-device Human Activity Recognition (HAR), and the issue persists even with the new wave of wearable foundation models.

💡 𝐎𝐮𝐫 𝐚𝐧𝐠𝐥𝐞 (𝐥𝐢𝐭𝐞𝐫𝐚𝐥𝐥𝐲): Instead of asking "how do we adapt?", we ask "do we even need to adapt right now?" -- because continuous test-time adaptation is simply too expensive for resource-constrained wearables.

🔍 𝐖𝐡𝐚𝐭 𝐰𝐞 𝐟𝐨𝐮𝐧𝐝: ▪️ Body-position shifts cause sharp, activity-dependent performance drops (walking generalizes well across positions; sitting does not) ▪️ A lightweight gradient-angle analysis captures directional mismatch between reference and runtime gradients -- a far more meaningful signal than gradient magnitude alone ▪️ Last-layer gradients offer roughly an order-of-magnitude sharper separation between same-position and cross-position cases, while being memory-efficient enough for on-device monitoring

📈 𝐖𝐡𝐲 𝐢𝐭 𝐦𝐚𝐭𝐭𝐞𝐫𝐬: Gradient angles enable alignment-gated adaptation and angle-aware federated aggregation, moving beyond blind continuous adaptation toward smarter, runtime-aware policies for wearable AI.

Grateful to the FMSys Workshop organizers and the IEEE/ACM CPS-IoT week 2026 community for the engaging discussions! 🙏

🔗 https://fmsys-org.github.io/2026/index.html

13/05/2026

🎤 Sandip Chakraborty presented our paper "𝐌𝐈𝐑𝐎: 𝐌𝐮𝐥𝐭𝐢-𝐑𝐚𝐝𝐚𝐫 𝐈𝐝𝐞𝐧𝐭𝐢𝐭𝐲 𝐚𝐧𝐝 𝐑𝐚𝐧𝐠𝐢𝐧𝐠 𝐟𝐨𝐫 𝐎𝐜𝐜𝐮𝐩𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐒𝐚𝐟𝐞𝐭𝐲" at 𝐀𝐂𝐌/𝐈𝐄𝐄𝐄 𝐒𝐞𝐧𝐒𝐲𝐬 𝟐𝟎𝟐𝟔! 🎉

Sharing a few moments from the presentation. 📸

Workers in hazardous environments like stone-cutting yards face serious exposure to particulate matter every day, yet monitoring pollution exposure at the individual level remains an open challenge, especially without compromising worker privacy through camera-based surveillance.

𝐌𝐈𝐑𝐎 tackles this with a privacy-preserving framework that pairs continuous PM sensing with a multi-radar mmWave re-identification backbone, tracking and re-associating workers across overlapping radar views -- no cameras involved. A GAN-based view adaptation model corrects azimuth-related distortions in range-Doppler signatures to keep identities consistent across radars, achieving a 90.4% re-ID F1-score, validated through field deployments in real industrial workspaces.

A big thank you to the wonderful SenSys community for the engaging discussions and thoughtful feedback during and after the talk.

Team behind MIRO: 👏 Tirthankar Halder (IIT Kharagpur) 👏 Argha Sen (IIT Kharagpur) 👏 Swadhin Pradhan (Cisco Systems) 👏 Rijurekha Sen (IIT Delhi) 👏 Sandip Chakraborty (IIT Kharagpur)

We gratefully acknowledge the support of the Department of Science and Technology (DST), Government of India, the National Science Foundation (NSF), and Google Research (Google's Society-Centered AI research funding) for making this work possible.

🎬 Teaser video: https://youtu.be/nTJj0PruMGk?si=Dcg_y5HLCcMeIJhg

🌐 Project page: https://ubinet-iitkgp.github.io/ubinet/pages/miro.html

🔗 Paper: https://dl.acm.org/doi/10.1145/3774906.3802761

23/04/2026

Our paper "𝐌𝐈𝐑𝐎: 𝐌𝐮𝐥𝐭𝐢-𝐫𝐚𝐝𝐚𝐫 𝐈𝐝𝐞𝐧𝐭𝐢𝐭𝐲 𝐚𝐧𝐝 𝐑𝐚𝐧𝐠𝐢𝐧𝐠 𝐟𝐨𝐫 𝐎𝐜𝐜𝐮𝐩𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐒𝐚𝐟𝐞𝐭𝐲" has been accepted at 𝐀𝐂𝐌/𝐈𝐄𝐄𝐄 𝐒𝐞𝐧𝐒𝐲𝐬 𝟐𝟎𝟐𝟔!

Workers in hazardous environments such as stone-cutting yards face significant exposure to particulate matter, yet monitoring individual-level pollution exposure remains a challenge. MIRO addresses this through a privacy-preserving framework that combines continuous PM sensing with a multi-radar mmWave re-identification backbone -- tracking and re-associating workers across overlapping radar views without the use of cameras. A GAN-based view adaptation model corrects azimuth-related distortions in range-Doppler signatures to maintain identity consistency across radars, achieving a 90.4% re-ID F1-score validated through field deployments in real industrial workspaces.

Congratulations to the team: 𝐓𝐢𝐫𝐭𝐡𝐚𝐧𝐤𝐚𝐫 𝐇𝐚𝐥𝐝𝐞𝐫 (IIT Kharagpur), 𝐀𝐫𝐠𝐡𝐚 𝐒𝐞𝐧 (IIT Kharagpur), 𝐒𝐰𝐚𝐝𝐡𝐢𝐧 𝐏𝐫𝐚𝐝𝐡𝐚𝐧 (Cisco Systems), 𝐑𝐢𝐣𝐮𝐫𝐞𝐤𝐡𝐚 𝐒𝐞𝐧 (IIT Delhi), and 𝐒𝐚𝐧𝐝𝐢𝐩 𝐂𝐡𝐚𝐤𝐫𝐚𝐛𝐨𝐫𝐭𝐲 (IIT Kharagpur).

We gratefully acknowledge the support of the Department of Science and Technology (DST), Government of India, the National Science Foundation (NSF), and Google Research (Google' Society Centered AI research funding) for supporting this work.

🔗 Project page: https://ubinet-iitkgp.github.io/ubinet/pages/miro.html

🎬 Teaser video: https://youtu.be/nTJj0PruMGk?si=4jItmefizDbNErx9

Occupational exposure to airborne particulate matter (PM) is a major health risk in open industrial settings like stonecutting yards. Conventional solutions ...

22/04/2026

UbiNet is proud to announce that 𝐔𝐭𝐤𝐚𝐥𝐢𝐤𝐚 𝐒𝐚𝐭𝐚𝐩𝐚𝐭𝐡𝐲 has successfully defended her PhD thesis! Congratulations, 𝐃𝐫. 𝐒𝐚𝐭𝐚𝐩𝐚𝐭𝐡𝐲!

Her doctoral research focused on 𝐏𝐫𝐨𝐯𝐞𝐧𝐚𝐧𝐜𝐞 𝐚𝐧𝐝 𝐎𝐛𝐬𝐞𝐫𝐯𝐚𝐛𝐢𝐥𝐢𝐭𝐲 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤𝐬 𝐟𝐨𝐫 𝐃𝐢𝐬𝐭𝐫𝐢𝐛𝐮𝐭𝐞𝐝 𝐌𝐢𝐜𝐫𝐨𝐬𝐞𝐫𝐯𝐢𝐜𝐞𝐬, supervised by Dr. Sandip Chakraborty. Her work has been published at premier venues including IEEE INFOCOM, COMSNETS, and IEEE Transactions on Services Computing, and received the 𝐁𝐞𝐬𝐭 𝐏𝐚𝐩𝐞𝐫 𝐇𝐨𝐧𝐨𝐮𝐫𝐚𝐛𝐥𝐞 𝐌𝐞𝐧𝐭𝐢𝐨𝐧 𝐀𝐰𝐚𝐫𝐝 at COMSNETS 2025.

We thank Prof. Venkatesh Tamarapalli from IIT Guwahati for serving as the external examiner for her PhD Viva Voce.

Beyond her research contributions, Dr. Satapathy has been instrumental in advancing systems research within UbiNet and played a key role in establishing industry collaborations with IBM Research and Ericsson Research -- partnerships that have enriched the lab's research direction and impact.

We wish Dr. Satapathy the very best as she embarks on the next phase of her career. UbiNet is proud to count her among its alumni.

20/04/2026

Our paper "𝐅𝐫𝐨𝐦 𝐈𝐧𝐯𝐢𝐬𝐢𝐛𝐥𝐞 𝐭𝐨 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞: 𝐀𝐮𝐠𝐦𝐞𝐧𝐭𝐞𝐝 𝐑𝐞𝐚𝐥𝐢𝐭𝐲 𝐈𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐨𝐧𝐬 𝐰𝐢𝐭𝐡 𝐈𝐧𝐝𝐨𝐨𝐫 𝐂𝐎𝟐" was presented at 𝐀𝐂𝐌 𝐂𝐇𝐈 𝟐𝟎𝟐𝟔 by Prasenjit Karmakar.

Indoor CO2, despite being invisible, has a significant impact on health, cognition, and productivity. This work investigates how Augmented Reality can make this hidden environmental data perceivable and actionable for everyday occupants.

Congratulations to the team:
Prasenjit Karmakar (IIT Kharagpur), Manjeet Yadav (IIT Jodhpur), Swayanshu Rout (RGIPT), Swadhin Pradhan (Cisco Systems), and Sandip Chakraborty (IIT Kharagpur).

🔗 Project page: https://ubinet-iitkgp.github.io/ubinet/pages/CoWear.html
🎬 Teaser video: https://youtu.be/F1LfQBEomHc?si=WczCsmPfMPKcxVsK

09/04/2026

We are hiring at UbiNet Lab, IIT Kharagpur — 2 Junior Research Fellow (JRF) positions!

𝗣𝗿𝗼𝗷𝗲𝗰𝘁: 𝗔𝗱𝘃𝗲𝗿𝘀𝗮𝗿𝗶𝗮𝗹𝗹𝘆 𝗥𝗼𝗯𝘂𝘀𝘁 𝗮𝗻𝗱 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 𝗣𝗿𝗲𝘀𝗲𝗿𝘃𝗶𝗻𝗴 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 𝗳𝗼𝗿 𝗠𝘂𝗹𝘁𝗶-𝗦𝗲𝗻𝘀𝗼𝗿 𝗘𝗱𝗴𝗲 𝗔𝗜 𝗶𝗻 𝗣𝘂𝗯𝗹𝗶𝗰 𝗦𝗮𝗳𝗲𝘁𝘆 𝗮𝗻𝗱 𝗛𝗲𝗮𝗹𝘁𝗵

Sponsored by: Anusandhan National Research Foundation (ANRF)

This project explores the intersection of foundation models, adversarial robustness, privacy preservation, and edge deployment for multi-sensor AI systems in public safety and health, which is a challenging and exciting space with real-world impact. The selected candidates will be supervised by Dr. Sandip Chakraborty and Prof. Shamik Sural.

𝗣𝗼𝘀𝗶𝘁𝗶𝗼𝗻 𝗱𝗲𝘁𝗮𝗶𝗹𝘀:

🔹 Compensation: Up to ₹37,000/month (depending on qualification & experience)

🔹 Tenure: 36 months or project duration, whichever is earlier

🔹 Age limit: 28 years

🔹 Application fee: NIL

🔹 Deadline: 23 April 2026

🎓 Selected candidates can participate in the MS/PhD selection process of the Department of Computer Science and Engineering, IIT Kharagpur.

Eligibility: Post Graduate Degree in CSE (or equivalent) OR Graduate Degree in CSE (or equivalent) along with a valid GATE score. Candidates should have more than 75% marks or 8.0 CGPA throughout academic degrees.

Apply here: https://erp.iitkgp.ac.in/SricWeb/temporaryJobs.htm

Ref No.: IIT/SRIC/R/PPM/2026/101

Please feel free to share with anyone who might be interested. Happy to answer questions about the project.

04/04/2026

We were delighted to host 𝐏𝐫𝐨𝐟. 𝐒𝐚𝐥𝐢𝐥 𝐊𝐚𝐧𝐡𝐞𝐫𝐞 𝐟𝐫𝐨𝐦 𝐭𝐡𝐞 𝐔𝐧𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 𝐨𝐟 𝐍𝐞𝐰 𝐒𝐨𝐮𝐭𝐡 𝐖𝐚𝐥𝐞𝐬 (𝐔𝐍𝐒𝐖), Sydney, at the UbINet Lab, Department of Computer Science and Engineering, IIT Kharagpur, as part of the ongoing SPARC collaboration with Dr. Sandip Chakraborty (IIT Kharagpur) and Dr. Sourav Kanti Addya, Ph.D. Addya (NIT Surathkal).

It was a truly enriching experience for our lab members to interact with Prof. Kanhere and exchange ideas on cutting-edge research problems.

Prof. Kanhere also delivered an open research seminar at the department titled "Cracking the Code: Detecting the Next Generation of Social Bots," where he presented two compelling lines of work -- BotSSCL, a self-supervised contrastive learning framework for detecting human-like social bots, and TBTrackerX, a measurement-driven study uncovering coordinated trigger-based bot campaigns on social media. The talk highlighted the growing sophistication of bot operations and the pressing need for adaptive and trustworthy detection strategies.

Thank you, Prof. Kanhere, for the insightful visit and stimulating discussions. We look forward to continued collaboration! Thanks to SPARC (https://sparc.iitkgp.ac.in/) for supporting this project.

01/03/2026

Team UbiNet actively participated in the Research Scholar Day and Research Promotion Workshop organized by the Department of Computer Science & Engineering IIT Kharagpur. Our members presented a diverse set of posters, showcasing ongoing research across multiple cutting-edge domains — from leveraging mmWave sensing for indoor mapping and water quality assessment (Sagnik Ghosh, Arup Sau, Pranjal Chatterjee, Nishant Kumar Das, Tamanna Nasrin), to exploring WiFi sensing for personalized free-hand exercise recommendations (Debjit chatterjee), utilizing distributed ledgers for efficient cab sharing (Shailesh Kumar Sharma), and developing active learning frameworks for physical data annotation using large language models (Aritra Hota).

Prof. Sandip Chakraborty delivered a faculty talk highlighting the wide spectrum of research directions currently being pursued at UbiNet, reflecting the group’s commitment to impactful, interdisciplinary work.

It was particularly enriching to interact with Prof. Parimal Pal Choudhury, whose academic lineage and legacy continue to inspire and guide the UbiNet team.

A day filled with learning, collaboration, and meaningful academic exchange!

18/01/2026

Our paper “𝐅𝐫𝐨𝐦 𝐈𝐧𝐯𝐢𝐬𝐢𝐛𝐥𝐞 𝐭𝐨 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞: 𝐀𝐮𝐠𝐦𝐞𝐧𝐭𝐞𝐝 𝐑𝐞𝐚𝐥𝐢𝐭𝐲 𝐈𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐨𝐧𝐬 𝐰𝐢𝐭𝐡 𝐈𝐧𝐝𝐨𝐨𝐫 𝐂𝐎₂,” has been accepted at , the premier A* conference in Human–Computer Interaction. This year’s CHI was exceptionally competitive, with 6,730 complete submissions, the highest in its history, and an overall acceptance rate of just 25.3%. Congratulations to all the authors Prasenjit Karmakar, Manjeet Yadav, Swayanshu Rout, Swadhin Pradhan, Sandip Chakraborty.

Thanks to for supporting Prasenjit's research, and Google Research and IIT Kharagpur AI4ICPS I Hub Foundation for supporting our works on developing systems and applications for tackling air pollution.

Our paper addresses a critical but often overlooked challenge: indoor air pollution. While CO₂ can significantly impact health and cognitive performance, it remains invisible, odorless, and poorly understood by occupants. Through extensive user studies, we found that although people recognize CO₂ as harmful, they lack awareness of safe thresholds and effective ventilation strategies.

To bridge this gap, we present 𝐂𝐨𝐖𝐞𝐚𝐫, 𝐚 𝐰𝐫𝐢𝐬𝐭-𝐰𝐨𝐫𝐧 𝐂𝐎₂ 𝐬𝐞𝐧𝐬𝐢𝐧𝐠 𝐬𝐲𝐬𝐭𝐞𝐦 𝐢𝐧𝐭𝐞𝐠𝐫𝐚𝐭𝐞𝐝 𝐰𝐢𝐭𝐡 𝐚 𝐬𝐦𝐚𝐫𝐭𝐩𝐡𝐨𝐧𝐞-𝐛𝐚𝐬𝐞𝐝 𝐚𝐮𝐠𝐦𝐞𝐧𝐭𝐞𝐝 𝐫𝐞𝐚𝐥𝐢𝐭𝐲 𝐞𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞. The system visualizes localized CO₂ accumulation as dynamic, color-coded AR “bubbles” anchored in real indoor spaces. By making invisible pollution perceptible and interactive, users are encouraged not only to understand where CO₂ accumulates, but also to take immediate, informed actions, such as directing airflow or opening windows, and observe the impact in real time. A user study with 35 participants across controlled and in-the-wild environments demonstrates that AR-based interaction leads to significantly better CO₂ reduction, higher engagement, and improved understanding compared to traditional 2D visualizations, while achieving strong usability scores.

The work highlights how augmented reality can move beyond awareness toward situated actionability, opening new possibilities for everyday health, sustainability, and human–environment interaction.

🎬 Teaser Video: https://youtu.be/F1LfQBEomHc?si=sXnBYoFs82DsIjhq

We look forward to presenting this work at ACM CHI 2026 and engaging with the global HCI community.

Indoor carbon dioxide (CO2) can rapidly accumulate to form invisible pollution hotspots, posing significant health risks due to its odorless and colorless na...

02/01/2026

As we bid farewell to 2025, the UbiNet Lab at the Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, wishes everyone a Happy New Year 2026!

To mark the transition into the new year, we are excited to share a short video capturing some of the key research milestones and impactful work carried out at the lab over the past year. The video also expresses our sincere gratitude for the continued support from our funding agencies, including Anusandhan National Research Foundation (ANRF), Department of Science and Technology (DST), and National Science Foundation (NSF), as well as our industry collaborators Google Research, Ericsson Research, and Tata Consultancy Services Research. We are equally thankful to all our academic and industrial collaborators, the Department of Computer Science and Engineering, IIT Kharagpur, Sponsored Research and Industrial Consultancy (SRIC), and the entire administration of Indian Institute of Technology, Kharagpur for their constant encouragement and support.

The video highlights our work spanning mmWave-based human and environmental sensing, personalized pollution sensing, smart edge systems for transportation and driving behavior monitoring, and system provenance for large-scale distributed environments, reflecting UbiNet’s commitment to impactful, real-world research.

🎬 Teaser Video:
👉 https://youtu.be/Sq70n6ZQa5A?si=T6eZqAoBvHOyzefi

We look forward to building on this momentum in 2026 with new ideas, collaborations, and societal impact.

At the UbiNet Lab at IIT Kharagpur, we continually strive to push the boundaries of sensing and systems research. Come along if you share the same ambition.