PhD Oral Exam - Godwin Badu-Marfo, Geography, Planning and Environment Studies
Privacy Preserved Model Based Approaches for Generating Open Travel Behavioural Data
This event is free
School of Graduate Studies
When studying for a doctoral degree (PhD), candidates submit a thesis that provides a critical review of the current state of knowledge of the thesis subject as well as the student’s own contributions to the subject. The distinguishing criterion of doctoral graduate research is a significant and original contribution to knowledge.
Once accepted, the candidate presents the thesis orally. This oral exam is open to the public.
With the pervasive nature of location-aware and mobile sensing technologies, concerns about privacy are becoming increasingly important and need to be addressed. Privacy protection and the need for disaggregate mobility data for transportation modelling needs to be balanced for applications and academic research. This dissertation focuses on developing modern privacy mechanisms that could satisfy requirements on privacy and data utility for fine-grained travel behavioural modelling applications using large-scale mobility data. To accomplish this, a review on the opportunities and challenges that are required to be addressed to harness the full potential of “Big Transportation Data” is done. Also, a quantitative evaluation on the degree of privacy provided by popular anonymization approaches are undertaken on sensitive location data (i.e. homes, offices) of a travel survey. A differentially-private generative model for simultaneously synthesizing both socio-economic attributes and sequences of activity diary is developed. Adversarial attack models are proposed and tested to evaluate the effectiveness of the proposed system against privacy attacks.
The results show that datasets from the developed privacy enhancing system can be used for travel behavioural modelling with satisfactory results while ensuring an acceptable level of privacy.