Research
AccessWear: Making Smartphone Applications Accessible to Blind Users
AccessWear is a system that improves the accessibility of smartphone touchscreen interactions for blind users using smartwatch gestures.
AccessWear is the first real-time smartwatch-based gesture recognition system for blind users that works without any training data from the users. We develop a novel input virtualization mechanism that eliminates the need for each app to integrate alternate gestures.
MuteIt: Jaw Motion Based Unvoiced Command Recognition Using Earable
MuteIt is an ear-worn system for recognizing unvoiced human commands. It is an intuitive alternative to voice-based interactions that can be unreliable in noisy environments. MuteIt proposes a twin-IMU set-up to track the user’s jaw motion and cancel motion artifacts caused by head and body movements.
Rather than employing machine learning to train a word classifier, we reconstruct each word as a sequence of phonemes using a bi-directional particle filter, enabling the system to be easily scaled to a large set of words.
JawSense: Recognizing Unvoiced Sound using a Low-cost Ear-worn System
JawSense is a wearable system that enables a novel form of human-computer interaction based on unvoiced jaw movement tracking. JawSense allows its user to interact with computing machines just by moving their jaw.
Naqaab: Health Sensing and Persuasion via Masks
With high levels of air pollution the COVID'19 pandemic, masks have become ubiquitous. We envision to make these masks as a reflection of lung activity at different pollution levels by retrofitting them with a sensing system.
This project was advised by Prof. Nipun Batra
Staging System for Multiple Myeloma
For predicting the stage of Multiple Myeloma (a type of cancer) generally expensive lab tests are required. To address this we proposed a staging system based on simple blood test reports for the Indian cohort patients.
This project was advised by Dr. Anubha Gupta
Air Cognizer: Predicting Air Quality levels from Mobile Camera Images
Air Cognizer is an android application that predicts air quality with mobile camera photos. It allows users to upload an image of the sky horizon to predict the AQI levels.
This project was advised by Dr. Aakanksha Chowdhery (Google AI) and Dr. Brejesh Lall (IIT Delhi).
Upper Extremity Prosthetics
This involves the development of low-powered Electronic Circuit Board and software for the prosthetic hand. The hand is controlled by Myo Electrodes which are placed on the amputee's limb and EMG signal is processed further to control opening, closing and various other grip patterns of the hand .
This project is developed for Endolite India Ltd.