This project involves applying advanced machine learning models to big vehicle telematics data. Trip chaining means linking a sequence of trips by a vehicle into a “tour” (e.g. a truck departs depot, then makes pick-up/drop-off, then take rest and/or return to depot). GPS data allows the trip chains to be reconstructed and analysed for providing insights. For example, by using GPS traces, the origin and destination of trucks can be inferred without relying only on costly manual surveys. Trip chains also help identify successive stops, link them, and thus understand entire tours rather than isolated single trips.
School
Civil and Environmental Engineering
Research Area
Transport engineering | Computer science
Suitable for recognition of Work Integrated Learning (industrial training)?
No
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
This project is managed within the Research centre for Integrated Transport Innovations (rCITI), School of Civil and Environmental Engineering.
- The expected outcome would be in the form of data analysis, interpretation and data insights, written as in the format of research article or a research report.
Read the relevant articles below: