Identifying Significant Places Using Multi-day Call Detail Records

Call detail records (CDRs) containing mass position information allow us to reveal characteristics about the city dynamics and human behaviors, which are crucial for policy decisions such as urban planning and transportation engineering. Being able to identify the trajectory and significant places is of prime importance. In this paper, we aim to extract trajectory from anonymized call detail records and adopt two-step clustering to obtain significant places from multi-day data. We propose a new method for mining trajectory by identifying users' stop and move state based on location gradient, which can be applied to users with low communication frequency. We analyze the feature of real CDR data and propose novel methods for noise handling. Home Time and Work Time are extracted from statistics of users' mobility pattern to recognize their significant places including home and work of a single day. Utilizing the characteristic of cyclical mobility, we conduct a cluster analysis to identify users' significant places which are not limited to one home or one work based on multi-day data. We run four experiments to show the robustness and stability of our method. During both typical stop and move period, our method performs better than state-of-art method.