Sensing the disturbed rhythm of city mobility with chaotic measures: anomaly awareness from traffic flows
Abstract: Big data-driven intelligent transportation plays an important role in smart cities. Moreover, upcoming abnormal events threatening to public safety can be altered prior to their appearance since such events break the regular rhythm of city mobility patterns. The purpose of this study is to detect and forecast abnormal events from the pulse of traffic flows. Specifically, information entropy, Boltzmann entropy, and fractal dimension are used to calculate the degree of the disequilibrium regarding how vehicles distribute on the transportation network. Then, the experiments were conducted based on simulated data and GPS traces of taxies in Shanghai, China. The results show that the proposed method can accurately indicate abnormal events to appear in reality. Finally, a comparison of the advantages and disadvantages of the three chaotic measures leads to insight into the rhythm of city mobility.
Loading