Activity recognition can play a significant role in providing feedback for a healthy life style as well as assisting the sick and the disabled. There are a variety of devices in the market that help users collect and analyze their activities (ie. Fitbit, Misfit). However, most of these data are not available for public usages and hinder the researchers to gain some insightful information from these data. This project involves building a platform that enables the users to collect data from the sensor of their Pebble Watches, analyzing it using a mobile phone, and applying a machine learning algorithm to the data for activity recognition.

Last semester, I worked with the MIT Media lab to build an android application that lets users document their DYI project. In addition, during my internship at State Farm insurance, I built a small prototype of a similar project using android to label human activity and used WEKA to generate a machine-learning model for activity prediction. I have worked at a couple of big corporates including HP Vertica, Amazon, Groupon, which prepare me with a wide variety of aspects in software development.