Urban Analytics of Big Transportation Data for Supporting Smart Cities

The advances in technologies and the popularity of the smart city concepts have led to an increasing amount of digital data available for urban research, which in turn has led to urban analytics. In urban research, researchers who conduct paper-based or telephone-based travel surveys often collect biased and inaccurate data about movements of their participants. Although the use of global positioning system (GPS) trackers in travel studies improves the accuracy of exact participant trip tracking, the challenge of labelling trip purpose and transportation mode still persists. The automation of such a task would be beneficial to travel studies and other applications that rely on contextual knowledge (e.g., current travel mode of a person). In DaWaK 2018, we made use of both the GPS and accelerometer data to classify ground transportation modes. In the current DaWaK 2019 paper, we explore additional parameters-namely, dwell time and dwell time history (DTH)-to further enhance the urban analytic capability. In particular, with these additional parameters, classification and predictive analytics of ground transportation modes becomes more accurate. This, in turn, helps the development of a smarter city.