Research

Graduate Research Assistant (HMI | ML | Graduate Thesis)

The motivation behind my research is professional gaming, which is being grown exponentially in recent years and the growth of this industry boomed in this COVID-19 era. Gamers buy expansive hardware for competitive gaming just to keep communication delay from hardware to the operating system as low as possible. They don't attend the contest or make a purchase when this response delay is more than 7 to 10 ms.
Supervised under Prof. Ning Jiang, my graduate thesis is focused on the development of low latency device for professional gamers using Human-Machine Interfacing (HMI) and Artificial Intelligence (AI). Electromyography (EMG) is one of the techniques that is used oftentimes in HMI. We are using surface electromyography (sEMG) which used to capture the muscle activity at the skin surface. The whole setup consists of 2 to 4 electrodes on the back of your palm, along with ADC connected to the system. After one training session followed by biomedical signal processing and machine learning, the user is not only able to reduce the delay but in fact started getting lead of 40ms on average up to 100ms. Please see the video below to see the real-time play of the system.

Supervised under Prof. Mark Crowley, worked on a novel algorithm in multiagent Re-enforcement learning (RL) domain, which involves learning tasks from trajectories and experts.
Developed Deep Learning (DL) models for Deep Q-learning from Demonstrations (DQfD), Continuous control with deep reinforcement learning (DDPG), and Reinforcement Learning from Imperfect Demonstrations (NAC), for Pommerman, predator-prey, and soccer as testbeds.

Chopra, Tushar, and Vikash Kumar Sharma. "Droid Guard: An Approach to Make Android Secure." International Journal of Computer Applications 117.8 (2015): 42-46.