The Cluster Behavior Anomaly Detection And Traffic Flow Prediction

With the technological advance, tracking persons or vehicles via mobile phone, GPS, camera, and other sensors becomes practical.Trajectories of people provide rich information about the collective behaviors, where the term collective behavior means the behavior of a large number of people as a whole. Abnormal people trajectories that are rarely observed may correspond with some unusual events, for instance, natural disasters, terrorism attacks, or traffic accidents. To detect such abnormal people trajectories, namely outliers, we presents a solution based on Hidden Markov Model (HMM). Experiments with an artificial data set simulating collective behaviors and a real-world traffic data set validate the proposed solution.Traffic congestion is a serious problem in people’s daily life,which brings us inconvenience as the abnormal events.Solving the problem of traffic congestion will make us live better.On the other hand, traffic congestions can be viewed as a result of the collective movements of people and the interactions among them.Hence, it represents a singular pattern of human mobility. The HMM method is also applied in the experiment of traffic prediction and we find that the traffic pattern coincides with the3-phase theory in terms of transportation sciences.