Publication Date

2020

Document Type

Thesis

Committee Members

Derek Doran, Ph.D. (Advisor); Adam Nolan, Ph.D. (Committee Member); Michael Raymer, Ph.D. (Committee Member)

Degree Name

Master of Science in Computer Engineering (MSCE)

Abstract

Recent advances in location acquisition services have resulted in vast amounts of trajectory data; providing valuable insight into human mobility. The field of trajectory data mining has exploded as a result, with literature detailing algorithms for (pre)processing, map matching, pattern mining, and the like. Unfortunately, obtaining trajectory data for the design and evaluation of such algorithms is problematic due to privacy, ethical, dataset size, researcher access, and sampling frequency concerns. Synthetic trajectories provide a solution to such a problem as they are cheap to produce and are derived from a fully controllable generation procedure. Citing deficiencies in modern synthetic trajectory procedures, we propose a data-driven, seasonally-aware and simulation-based procedure that incorporates macro- and micro-level patterns from reference trajectories. The procedure is implemented as an alpha-release package; allowing an analyst to produce synthetic trajectories via the use of a modular coding framework and analysis tools.

Page Count

152

Year Degree Awarded

2020


Share

COinS