Prahalathan Sundaramoorthy

Prahalathan Sundaramoorthy

Master's student at the University of Southern California. Specializing in machine learning and big data

Publications

ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition

Published in The 3rd International Workshop on Deep Learning for Mobile Systems and Applications, ACM MobiSys, 2019

This paper is about integrating active learning techniques in Convolutional Neural Networks to efficiently learn from unlabeled data.

Recommended citation: Gautham Krishna Gudur, **Prahalathan Sundaramoorthy**, Venkatesh Umaashankar, "ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition", ACM MobiSys 2019, 3rd International Workshop on Embedded and Mobile Deep Learning, Seoul, South Korea. http://prahalath.github.io/files/activeharnet.pdf

HARNet: Towards On-Device Incremental Learning using Deep Ensembles on Constrained Devices

Published in Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning, ACM MobiSys, 2018

This paper is about designing an efficient deep learning architecture capable to run on smartphones. The data from sensor is used to perform Human Activity Recognition.

Recommended citation: Prahalathan Sundaramoorthy, Gautham Krishna Gudur, Manav Rajiv Moorthy, R Nidhi Bhandari, Vineeth Vijayaraghavan, "HARNet: Towards On-Device Incremental Learning using Deep Ensembles on Constrained Devices", ACM MobiSys 2018, 2nd International Workshop on Embedded and Mobile Deep Learning, Munich, Germany. http://prahalath.github.io/files/harnet.pdf

Current peak based Device Classification in NILM on a low-cost embedded platform using Extra-trees

Published in 2017 IEEE MIT Undergraduate Research Technology Conference (URTC), Massachusetts Institute of Technology, Cambridge, MA, 2017, 2017

Efficient classification model for low-cost Non-Intrusive Load Monitoring

Recommended citation: A. K. Jain, S. S. Ahmed, P. Sundaramoorthy, R. Thiruvengadam, V. Vijayaraghavan, "Current peak based Device Classification in NILM on a low-cost embedded platform using Extra-trees," 2017 IEEE MIT Undergraduate Research Technology Conference (URTC), Massachusetts Institute of Technology, Cambridge, MA, 2017. http://prahalath.github.io/files/nilm.pdf