UROP Openings

Have a UROP opening you would like to submit?

Please fill out the form.

Submit your UROP opening

Driving Behaviour Analysis from CAN-BUS and SmartPhone Data


Term:

Fall

Department:

11: Urban Studies and Planning

Faculty Supervisor:

Carlo Ratti

Faculty email:

ratti@mit.edu

Apply by:

09/21/2020

Contact:

Punit Rathore, prathore@mit.edu

Project Description

The purpose of this project is to analyse and classify the driving behaviour of drivers by leveraging the CAN-BUS and Smartphone data, that includes GPS coordinates, speed, accelerometer, and gyroscope data. The primary objectives of this project are to: (I) pre-process the raw data from CAN-BUS (e.g. filtering, trip segmentation etc.) (ii) pre-process the smartphone data e.g., noisy removal, handle smartphone movements using virtual re-orientation strategies etc.) (iii) exploratory data analysis on raw and pre-processed data to obtain useful insights (iv) classify driving behaviours (e.g. safe, harsh etc.) using unsupervised approaches. Applicants can only work fully remotely.

Pre-requisites

(1) Experience with Python or MATLAB or R is required (2) Basic knowledge and some experience with data science, exploratory data analysis, and signal processing is required (3) Availability to start as soon as possible. If you don't have the background, but you are highly motivated to participate in the project, please apply.