Sari Aslam, Nilufer;
(2022)
Inferring Trip Purposes from Travel Smart Card Data.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
PhDThesis_StudentNumber_1043879_NiluferSariAslam_17052022.pdf - Accepted Version Download (7MB) | Preview |
Abstract
Understanding human mobility, activities and trip purpose is essential for transport planning and commercial services in urban environments. Conventionally, household travel surveys have collected such information, but these have relatively small sample sizes with low update frequencies leading to an incomplete and inaccurate picture of overall urban mobility. Recently, big data sources such as Smart Card Data (SCD) have provided alternative sources from which to investigate human mobility due to their longitudinal nature, large volume and high level of spatiotemporal detail. While Primary Activities (PAs) (home and work/school for adults/students) are relatively easy to identify from SCD, Secondary Activities (SAs) (the rest of a person’s activities) and trip purposes are difficult to understand directly given only limited information provided by SCD, e.g., the tap-in/out station and time. The aim of this thesis is to investigate activities and trip purposes from large SCD by making use of survey data and Point-of-Interest (POI) data using both heuristic and machine learning approaches. The heuristic approach uses a set of rules/algorithms to identify PAs and SAs based upon journey counts, visit frequency, activity duration and direction information (from and to) extracted from SCD combined with spatiotemporal attributes of POIs. The machine learning approach, however, uses a deep learning framework, ActivityNET, to derive the trip purpose of both PAs and SAs from labelled SCD data contributed by volunteers (survey SCD, or SSCD) in one step. The proposed models are validated using London Travel Demand Survey (LTDS) data and SSCD, achieving higher detection accuracy than benchmark methods and the deep learning methods are found to be more accurate than the heuristic approach. Using volunteers’ survey data (SSCD) with their associated SCD is innovative in this study which overcomes the challenges of using machine learning for trip purpose detection and validation. The study has developed a cost-effective framework to use big data sources (SCD and POIs) for urban mobility analysis, which has strong policy implications. In addition, the study provides new ideas for future applications to help or eliminate conventional household surveys for travel demand analysis.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Inferring Trip Purposes from Travel Smart Card Data |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2022. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL SLASH UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of S&HS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of S&HS > Dept of Geography UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Civil, Environ and Geomatic Eng UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10148668 |
Archive Staff Only
 |
View Item |
