About Me
Hi, I am a 5th year Ph.D. student in Societal Computing (S3D) at Carnegie Mellon University. I love to build (hardware and software) systems. I am interested in how we can enhance utility of smart environments and promote human-AI collaboration towards user health and wellness, while alleviating privacy concerns. I am fortunate to be advised by Dr. Yuvraj Agarwal, and to get an opportunity to work closely with Dr. Mayank Goel, Dr. Amy Ogan and Dr. John Zimmerman.
I am actively engaged with Edusense classroom sensing project, and Autonomous project for supporting people with Dementia. Before grad school, I worked with Bidgely UtilityAI on promoting energy efficiency using smart meter disaggregation, and completed my undergraduate (B.Tech) in Computer Science from IIT Delhi .
News and Updates
Presented ClassID paper at Ubicomp/ISWC, 2024
5 months agoHad an awesome time at MSR, Redmond for last three months.. Will miss my time here. Excited to continue this collaboration…
7 months agoEdulyze paper published in the Journal for Learning Analytics' Volume 11, Issue 2. Congratulations to Edusense team!!
7 months ago**Won CyLab Presidential Fellowship for the 2024-25 academic year. Very honored!
8 months agoStarted summer internship at Microsoft Research, Redmond. Looking forward to my time on west coast. :)
10 months agoClassID paper is published in IMWUT Volume 8 Issue 2. Congratulations to the team!!
10 months agoClassID accepted with minor revisions at Ubicomp/ISWC 2024
12 months agoPresented two guest lectures on "Sensing and ML in real world " in User Focused Sensing Systems Class.
1 years ago**Won CMLH translational Fellowship for 2024. Very Excited about the project. More details soon!
1 years agoPresented VAX and TAO at Ubicomp/ISWC 2024, very excited to get feedback on our work
1 years agoVAX and TAO paper is published in IMWUT Volume 7 Issue 3. First paper(s) at Ubicomp/ISWC, very excited!!
1 years ago
Research Highlights
ClassID: Enabling Student Behavior Attribution from Ambient Classroom Sensing Systems
A data attribution method for within a class session and across multiple sessions of a course without individual instrumentation.
Prasoon Patidar, Tricia J Ngoon, John Zimmerman, Amy Ogan, Yuvraj Agarwal
Edulyze: Learning Analytics for Real-World Classrooms at Scale
Edulyze is an analytics engine that processes complex, multi-modal sensing data and translates them into a unified schema that is agnostic to the underlying sensing system or classroom configuration.
Prasoon Patidar, Tricia Ngoon, Neeharika Vogety, Nikhil Behari, Chris Harrison, John Zimmerman, Amy Ogan, Yuvraj Agarwal
VAX: Using Existing Video and Audio-based Activity Recognition Models to Bootstrap Privacy-Sensitive Sensors
We created a novel system, VAX (Video Audio to 'X'), where training labels acquired from existing A/V models are used to train ML models for a range of privacy-sensitive sensors.
Prasoon Patidar, Mayank Goel, Yuvraj Agarwal
TAO: Context Detection from Daily Activity Patterns Using Temporal Analysis and Ontology
TAO is a hybrid system that leverages OWL-based ontologies and temporal clustering approaches to detect high-level contexts from human activities.
Sudershan Boovaraghavan, Prasoon Patidar, Yuvraj Agarwal
Self-Serviced IoT: Practical and Private IoT Computation Offloading with Full User Control
We propose a system that allows users to offload computation from their IoT devices to the cloud while maintaining privacy and control over their data.
Dohyun Kim, Prasoon Patidar, Han Zhang, Abhijith Anilkumar, Yuvraj Agarwal
Multi-purchase behavior: Modeling, estimation, and optimization
We study the problem of modeling purchase of multiple products and using it to display optimized recommendations for online retailers and e-commerce platforms.
Theja Tulabandhula, Deeksha Sinha, Saketh Reddy Karra, Prasoon Patidar
Network flow Optimization through Monte Carlo Simulation
We study the problem of network flow optimization using Monte Carlo simulation and propose a novel algorithm to solve it.
Sayaji Hande, Prasoon Patidar, Sachin Meena, Saurabh Banerjee
Optimizing Adaptation of Smart Traffic Lights with Resource Constraints
We explore the idea of efficiently deploying smart intersections within given budget constraints in a city using a generic simulation-based framework.
Prasoon Patidar, Geoffrey B Dobson, Kathleen M Carley, Yuvraj Agarwal
Publications
Edulyze: Learning Analytics for Real-World Classrooms at Scale
Prasoon Patidar, Tricia Ngoon, Neeharika Vogety, Nikhil Behari, Chris Harrison, John Zimmerman, Amy Ogan, Yuvraj Agarwal
Journal of Learning Analytics, 2024
Classroom sensing systems can capture data on teacher-student behaviours and interactions at a scale far greater than human observers can. These data, translated to multi-modal analytics, can provide ...
ClassID: Enabling Student Behavior Attribution from Ambient Classroom Sensing Systems
Prasoon Patidar, Tricia J Ngoon, John Zimmerman, Amy Ogan, Yuvraj Agarwal
Ubicomp/ISWC, 2024
Ambient classroom sensing systems offer a scalable and non-intrusive way to find connections between instructor actions and student behaviors, creating data that can improve teaching and learning. Whi...
Multi-purchase behavior: Modeling, estimation, and optimization
Theja Tulabandhula, Deeksha Sinha, Saketh Reddy Karra, Prasoon Patidar
MSOM (Manufacturing & Service Operations Management), 2023
We study the problem of modeling purchase of multiple products and using it to display optimized recommendations for online retailers and e-commerce platforms. Rich modeling of users and fast computat...
VAX: Using Existing Video and Audio-based Activity Recognition Models to Bootstrap Privacy-Sensitive Sensors
Prasoon Patidar, Mayank Goel, Yuvraj Agarwal
Ubicomp/ISWC, 2023
The use of audio and video modalities for Human Activity Recognition (HAR) is common, given the richness of the data and the availability of pre-trained ML models using a large corpus of labeled train...
TAO: Context Detection from Daily Activity Patterns Using Temporal Analysis and Ontology
Sudershan Boovaraghavan, Prasoon Patidar, Yuvraj Agarwal
Ubicomp/ISWC, 2023
Translating fine-grained activity detection (e.g., phone ring, talking interspersed with silence and walking) into semantically meaningful and richer contextual information (e.g., on a phone call for ...
An Instructor is [already] able to keep track of 30 students: Students’ Perceptions of Smart Classrooms for Improving Teaching & Their Emergent Understandings of Teaching …
Tricia J Ngoon, David Kovalev, Prasoon Patidar, Chris Harrison, Yuvraj Agarwal, John Zimmerman, Amy Ogan
ACM designing interactive systems (DIS) conference, 2023
Multi-modal classroom sensing systems can collect complex behaviors in the classroom at a scale and precision far greater than human observers to capture learning insights and provide personalized tea...
Self-serviced iot: Practical and private iot computation offloading with full user control
Dohyun Kim, Prasoon Patidar, Han Zhang, Abhijith Anilkumar, Yuvraj Agarwal
arXiv, 2022
The rapid increase in the adoption of Internet-of-Things (IoT) devices raises critical privacy concerns as these devices can access a variety of sensitive data. The current status quo of relying on ma...
Professional Informatics: Personalized, Data-Driven Professional Development
Tricia J Ngoon, Prasoon Patidar, Amy Ogan, Chris Harrison, Yuvraj Agarwal
CHI, 2022
We argue to reframe PI as Pro-I (Professional Informatics). Through this lens, we explore whether self-sensing technology in support of behavior change would work effectively if applied to professiona...
Optimizing Adaptation of Smart Traffic Lights with Resource Constraints
Prasoon Patidar, Geoffrey B Dobson, Kathleen M Carley, Yuvraj Agarwal
IEEE 7th World Forum on Internet of Things (WF-IoT), 2021
Large cities worldwide are facing many challenges, such as a growing population, which leads to an increase in traffic congestion. In many places, city road infrastructure does not cope well with grow...
Privacy-preserving Incentive Mechanisms for Resource Sharing in IoT Markets
Prasoon Patidar, Jinding Xing
, 2021
we model the trading between IoT devices and computation resource providers as a multi-leader and multi-follower Stackelberg game with consideration of market competition and privacy preservation. In ...
Dope-ml: Designing Operational Policies for ML Environments
Prasoon Patidar, Sudershan Boovaraghavan, Balamurugan Marimuthu
, 2022
The field of Machine Learning Operations (MLOps) has grown with time due to increasing number of ML application deployed worldwide. Over the years, people have developed many MLOps platforms (both ope...
Multi-purchase behavior: Modeling and optimization
Theja Tulabandhula, Deeksha Sinha, Prasoon Patidar
SSRN 3626788, 2020
We study the problem of modeling purchase of multiple items and utilizing it to display optimized recommendations, which is a central problem for online e-commerce platforms. Rich personalized modelin...
Network flow Optimization through Monte Carlo Simulation
Sayaji Hande, Prasoon Patidar, Sachin Meena, Saurabh Banerjee
Fifth International Conference on Parallel, Distributed and Grid Computing (PDGC), 2018
We encounter network flows in day to day life. They are the backbone of logistics, city planning, processes etc. In order to study these networks, domain specific connectivity graphs along with their ...
Contact
Email: prasoonpatidar@cmu.edu
Office: Office 347, TCS Hall (4665 Forbes Ave), CMU
Address: Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA (USA)