The Research On Users’ Movements And Stay Point Identification Based On Mobile Data

The cell-based location data could be used to obtain the mobility regularity ofmobile users. These scalable and real-time data have attracted more attentions, and arewidely used in the urban computing. In this paper, we mainly focus on the cell-basedlocation data to carry out the following work.1. This paper develops a system to indentify mobile location based on semantictechnologies. The system can employ the cell-based location data to analyze theorigin-destination points and the trip purpose. The system uses semantic technologiesto describe the semantic information of multi-source traffic data, then creates thedatabase including multi-source traffic data. In this system, we can conduct the logicalreasoning by setting the rules, and analyze users’ trip purpose based on the cell-basedlocation data.2. Considering the mobile phone users’ privacy issues, researchers are usuallydifficult to obtain the cell-based data. Meanwhile, due to the lack of semanticannotation, these data are not available for scientific research. Therefore, it isnecessary to simulate the cell-based location data to support the research work. Thispaper develops “A System to Generate Mobile Data Based on Real User Behavior”.Firstly, we set a real mobile communication simulation system; Secondly, based onthe past real travel activities of users, we extract users’ trajectories; Then, users’ travelprocesses are shown once more, and users’ communication event information isrecorded in the process. Finally, the cell-based location data with semantic annotationare generated.3. Identifying stay points is a key step in the analysis of the mobility regularity ofmobile users. In order to detect stay points from a user’s mobile phone trajectory, thispaper makes use of the concept of a functional area to combine the trajectory ofmobile phones with background geographic information. By considering the overallactivities of users in a particular functional area, this method can identify whether auser stays or not, and avoid misjudgment due to a user’s normal switching and errorswitching. This method is more general because a stay point is a collection of cells ina continuous trajectory at a functional area instead of a small range covered by asingle base station.