Research On Behavior Analysis And Urban Sensing Based On Mobile Network Data

The analysis of human mobility is the hotspot research field. Studying the character-istics and regularity of human behaviors is of practical significance to various fields from personalized service, commercial promotion to urban sensing. In the past decade human be-haviors is mostly based on virtual social network. With the rapid growth of location based service, researchers are delving themselves into the newly researches valuable of realistic application. The pervasive wireless communication technology makes people much closer through voice call, SMS and streaming data. The widespread wireless communication, fast progress of smartphone operation system and development of mobile network have facili-tated a large interconnected network. Due to these features, call detail records is a better proxy reflecting human activities:on one hand it can reflect users’ social relationships, on the other hand it can reflect the real geographical position. By combining the social network with geographical position, we can go deep into the analysis of human behaviours.Human activities have a profound impact on surrounding environment. Conversely, natural and social environment also affect human behaviours. Although from the viewpoint of individuals the behavioral characteristics are complex and diverse, the group still reflects the inherent features of human society and mobility. Deep analysis of the human spatial-temporal activities can help unveil the motivations and intention of people. Further more, it is of great significance for exploring the evolution of natural and social environment. Mobile phone records can be used as a sensor for urban sensing for it containing the spatial-temporal characteristics of human behaviors.In this thesis the author is going to conduct research area into two parts which are analysis of social network and urban sensing based on location. The main achievements of research are outlined as follows:1. A specific model is constructed for users’ inter-communication network along with the analysis of basic characteristics of the social network, such as power law distri-bution, contact lists. Analysis of communication patterns of different areas is also given. 2. We study the patterns of human behaviours and give a prediction of social relation-ship. The topology of mobile telephone calls can be used to estimation of users’ potential relationship. In combination with users’overlap in their trajectories in urban lives, it can be beneficial for prediction of future interpersonal connection.3. A new method is proposed to uncover the barrier of urban city according to the mobility of users. Due to the small displacements of majority people during their consecutive calls, an assumption is concluded that traffic flux between neighbor cells are higher than other nonadjacent cells. Detecting the anomalous neighbor cell pairs caused by human traffic flux can unveil the road barrier and geographical features.4. We construct a new model which considers the urban area as a spatial network. We apply the algorithm based on modularity to discover the administrative districts and give some analysis and explanations to the new emerging area by comparison with reality. In addition, a new model based on LDA model was established to discover the functional similarity of urban city area.Our study is an exploratory research to analysis the human mobility and urban city. We improve the understanding of human behaviors through the analysis and mining of real data set in an innovative way. Models and results are expected to better understanding the human activities and urban to advance the application with high quality and personality.