Mining Semantic Trajectories using Phone Sensors

There is a lot of research on mobility behavior analysis of moving objects. Such research has traditionally focused on moving objects such as vehicles, ships etc. With the advent of people-sensing, the focus has shifted on sensing using the mobile phone. People-sensing is an active area of research today. The primary objective is to use the sensors on the phone and sense different aspects of the environment, effectively bringing people in the sensing loop.

In this project, we will explore algorithms for efficient extraction of knowledge from a stream of sensor data obtained from mobile phones of users (e.g. GPS, accelerometer). The goal is to extract a high-level semantic view of such people trajectories (e.g., sequence of activities, semantic locations visited).

The students will benefit from experience in learning about machine learning algorithms (supervised, unsupervised), spatial data processing techniques as well as experience in programming techniques to handle large data.

Interested students are kindly asked to contact Zhixian Yan.

Requirements: C, Java, SQL      Desirable: Matlab, Machine learning tools (e.g. libsvm, weka)