MyWay: Location prediction via mobility profiling

Abstract

Forecasting the future positions of mobile users is a valuable task allowing us to operate efficiently a myriad of different applications which need this type of information. We propose MyWay, a prediction system which exploits the individual systematic behaviors modeled by mobility profiles to predict human movements. MyWay provides three strategies: the individual strategy uses only the user individual mobility profile, the collective strategy takes advantage of all users individual systematic behaviors, and the hybrid strategy that is a combination of the previous two. A key point is that MyWay only requires the sharing of individual mobility profiles, a concise representation of the user's movements, instead of raw trajectory data revealing the detailed movement of the users. We evaluate the prediction performances of our proposal by a deep experimentation on large real-world data. The results highlight that the synergy between the individual and collective knowledge is the key for a better prediction and allow the system to outperform the state-of-art methods

Online Long-Term Trajectory Prediction Based on Mined Route Patterns

“…A number of research efforts that emerged from the above ideas are the approaches of convoys [18,28], platoons [23], swarms [24], gathering pattern [42] and traveling companion [37]. Trasarti et al [40] introduced "individual mobility patterns" in order to extract the most representative trips of a specific moving object, so that they can predict object's future locations. However, all of the aforementioned approaches are centralized and cannot scale to massive datasets.…”

A survey of evaluation methods for personal route and destination prediction from mobility traces

“…The second approach is density based, upon which only destinations and routes shared by several individuals will be used to strengthen the models of other users—see for example Ref . Although this has clear performance potential, its parameters need to be carefully chosen and tested to guarantee the privacy of users.…”

Predicting encounter and colocation events

“…One challenge for using the WiFi and Cellular datasets for prediction (especially PoI prediction) is that PoIs are represented by ID (symbolic place) without any coordinates. Therefore some existing prediction scheme such as [29,35,37] would not be applicable. So our used datasets do not support the arithmetic or logic operation, which is usually are used to process GPS coordinates for location prediction.…”

“…One challenge when having at disposal WiFi data or CDR without spatial coordinates is represented by the impossibility to apply mobility prediction schemes such as [29,35,37] which are based on GPS information.…”

“…In this scenario, one of the challenges today is the design of algorithms to predict where, when and with whom a user will experience an encounter or colocation event by simply leveraging the mobility patterns of the user, especially where knowing people's encounter and colocation events is the key point for the success of the applications and protocols. When relying on spatial-temporal information only, a few algorithms were designed to predict the next place visited by a user with good accuracy [35,37,38]; however, to the best of our knowledge, only in [5] the issue of predicting the next encounter has been addressed.…”