Aktivität: Vortrag ohne Tagungsband / Vorlesung › Präsentation auf einer wissenschaftlichen Konferenz / Workshop
Urban and transportation planning relies on accurate mobility data to model and optimize the use of the transportation network. Traditional household surveys conducted with questionnaires are very expensive and, hence, the sample size and update frequency of these surveys is limited. In contrast, massive and passive data such as cell phone traces provide huge samples of the whereabouts and movement patterns of the population. This has in the recent years inspired intensive research, such as the analysis of human mobility behavior, origin-destination flows, and road usage patterns. The main challenge is that phone traces have low spatial precision and are sparsely sampled in time. Moreover, some of the information required for transportation modeling, such as socio-demographic attributes or trip purposes, are not included in anonymized cell phone traces but have to be inferred. In this talk I will present set of techniques for extracting mobility data from cellular data and mining hidden valuable information they contain.