CHEN Lue,XIONG Chen,CAI Ming.A comprehensive decision-making algorithm of residence and workplace based on the identification of cellular signaling track points[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2022,61(02):106-116.
CHEN Lue,XIONG Chen,CAI Ming.A comprehensive decision-making algorithm of residence and workplace based on the identification of cellular signaling track points[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2022,61(02):106-116. DOI: 10.13471/j.cnki.acta.snus.2020B027.
A comprehensive decision-making algorithm of residence and workplace based on the identification of cellular signaling track points
Due to the characteristics of cellular signaling, such as sparsity and spatial uncertainty, it is difficult to identify the location of workplace and residence. At the same time, the current cellular signaling residence and workplace identification algorithm is an insufficient basis and unknown effectiveness for the key elements affecting the identification results, such as time rules and spatial aggregation distance. In view of the above difficulties, this paper proposes a comprehensive decision-making algorithm based on celluar signaling track point identification, which eliminates the spatial uncertainty of mobile signaling and effectively defines the space-time boundary of the stay area. Based on the recognition of stay points, the distribution characteristics of stay points in each period are extracted, and the information entropy of each period is calculated to measure the possibility that the period belongs to the residence and workplace period, and the weighted value of the period is given in this paper. By discretizing the arrival and departure time axis of any semantic stay point, the stay time slot of semantic stay point is combined, and the characteristics of stay time slot are reflected by the time slot weight. Based on the characteristics of the stay time slot and stay time, a comprehensive decision matrix of residence and workplace is constructed to identify the most likely semantic stay point as the residence and workplace, and the cellular signaling with stay tag is used to verify the effectiveness of the algorithm.
关键词
手机信令轨迹点识别信息熵职住地决策矩阵
Keywords
cellular signalingidentification of cellular signaling track pointsinformation entropyresidence and workplacedecision matrix
GONZÁLEZ M C, HIDALGO C A, BARABÁSI A L.Understanding individual human mobility patterns[J].Nature, 2008,453:779-782.
CALABRESE F, COLONNA M ,LOVISOLO P ,et al.Real-Time urban monitoring using cell phones: a case study in rome[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(1):141-151.
LEE J K, HOU J C. Modeling steady-state and transient behaviors of user mobility: formulation, analysis, and application[C]//Conti M, et al. Proceedings of the 7th ACM International Symposium on Mobile Ad Hoc Networking & Computing. Florence: ACM, 2006:85-96.
FAYYAD U M. Multi-Interval discretization of continuous-valued attributes for classification learning[C]// Proc of the Int'l Joint Conf on Artificial Intelligence. 1993: 1022-1027.