GPS for high resolution positioning

• Main Author: Ng, Kah Pooi
• Other Authors: Lee Yee Hui
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering::Wireless communication systems
• Online Access: https://hdl.handle.net/10356/139138
• Institution: Nanyang Technological University

With the advent of a wide-ranging suite of applications and online services utilizing data from the Global Positioning Systems (GPS), map-matching, which is the problem of aligning noisy observed coordinates to road networks, on a given map, is now an increasingly important problem. In this project, a Fast Hidden-Markov Model (HMM) is proposed and implemented in Python, deriving the most likely trajectory undertaken by a traveler based on observed trajectories emitted from his/her GPS. Our experiment results indicate that our model performs with a relatively high degree of accuracy on the base case and remains so even as the GPS sampling frequency is significantly reduced. Although the processing time of our algorithm is significant, it also has better performance as compared to other major open source implemented algorithms that can be found.