M
Mohit Agarwal
Researcher at Georgia Institute of Technology
Publications - 16
Citations - 135
Mohit Agarwal is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Reinforcement learning & Wearable computer. The author has an hindex of 5, co-authored 16 publications receiving 64 citations. Previous affiliations of Mohit Agarwal include Indian Institute of Technology Kanpur.
Papers
More filters
Proceedings ArticleDOI
Blink: A Fully Automated Unsupervised Algorithm for Eye-Blink Detection in EEG Signals
TL;DR: This work proposes a fully automated and unsupervised eyeblink detection algorithm, Blink that self-learns user-specific brainwave profiles for eye-blinks, and does away with any user training or manual inspection requirements.
Proceedings ArticleDOI
Cerebro: A Wearable Solution to Detect and Track User Preferences using Brainwaves
TL;DR: A machine learning algorithm Cerebro is presented, which can learn the specific nuances of the user's brainwaves for preferences to accurately rank the objects.
Journal ArticleDOI
Accelerating Reinforcement Learning using EEG-based implicit human feedback
TL;DR: This work proposes and experimentally validate the zero-shot learning of ErrPs, proposes a novel RL framework for integrating implicit human feedbacks via ErrPs with RL agent, improving the label efficiency and robustness to human mistakes, and scales the application of ErrP to reasonably complex environments.
Posted Content
Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback
TL;DR: This work proposes and experimentally validate the zero-shot learning of ErrPs, and proposes a novel RL framework for integrating implicit human feedbacks via ErrPs with RL agent, improving the label efficiency and robustness to human mistakes, and scale the application of ErrP to reasonably complex environments.
Proceedings ArticleDOI
Blink to Get In: Biometric Authentication for Mobile Devices using EEG Signals
TL;DR: This work focuses on the EEG signal corresponding to the human eye-blink to create an authentication system that could be used to distinguish between multiple users accurately and efficiently while also being burden-less and convenient to the users.