The technologies of mobile communications pervade our society and wireless networks sense the movement of people, generating large volumes of mobility data, such as mobile phone call records and Global Positioning System (GPS) tracks. The striking analytical power of massive collections of trajectory data may contribute to unveil the complexity of human mobility. The knowledge discovery process, based on these data, addresses some fundamental questions of mobility analysts: what are the frequent patterns of people’s travels? How big attractors and extraordinary events influence mobility? How to predict areas of dense traffic in the near future? How to characterize traffic jams and congestions?
Mobility data mining: The mining of movement data is a research field that emerged only recently. It adapts and extends to trajectory data several data mining problems and solutions originally studied for transactional contexts and tabular data, such as clustering, frequent patterns and classification. The pioneering GeoPKDD project clearly moved this state-of-the-art to a next level and proposed a repertoire of methods and systems to discover useful knowledge about human movement behaviour from mobility data. The main analytical methods for mining trajectories are the following: trajectory pattern mining to extract the sequences of locations that are frequently visited in the trajectory dataset; trajectory clustering asa set of similar trajectories, according to a repertoire of trajectory similarity functions and appropriate visualization techniques; and trajectory classification and location prediction which are classification methods for inferring characteristics of a mobile object.
The system M-Atlas aggregates most of these techniques in a uniform platform for the advanced analysis of trajectory data.