Leveraging smartphones to incentivize city-wide, energy ecient transportation

Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. === This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. === Cataloged from student-s...

Full description

Bibliographic Details
Main Author: Srinivasan, Arjun, M. Eng. Massachusetts Institute of Technology
Other Authors: Moshe E. Ben-Akiva.
Format: Others
Language:English
Published: Massachusetts Institute of Technology 2018
Subjects:
Online Access:http://hdl.handle.net/1721.1/113106
Description
Summary:Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. === This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. === Cataloged from student-submitted PDF version of thesis. === Includes bibliographical references (pages 51-53). === Transportation is a major source of energy consumption in developed countries [4]. Unfortunately, people have little incentive to change their habits, relying on inefficient transportation sources. The "Sustainable Travel Incentives with Prediction, Optimization and Personalization" (Tripod) project seeks to incentivize people to improve their transportation-related behavior through redeemable tokens. These tokens are rewarded through city-wide, energy-optimized transportation decisions decided in real-time. As part of this initiative, I have developed an initial prototype Android application named FMS Advisor that allows users to interact with the larger Tripod system before, during, and after their journey. Working off an initial design, I designed a trip planner interface that uses optimized route planning information to display a personalized trip menu. I also developed trip validation algorithms such as vehicle occupancy detection and driving-style detection using dynamic time warping (DTW) and threshold-based methods. These methods were then evaluated through group user sessions and controlled trip experiments. This resulted in a functional end-to-end user experience, though trip validation methods require additional data to have properly tuned detection. In the future, token redemption will be possible through an integrated marketplace for rewards that can be accessed at the end of a trip. === by Arjun Srinivasan. === M. Eng.