Resident Point Recognition And Travel Trajectory Extraction Based On Mobile Data

With the popularization of mobile communication devices such as smart phones,smart watches and smart driving recorders,communication operators have accumulated massive mobile location data resources,which can provide detailed data support for the construction of Smart Transportation.In order to study the travel characteristics of urban residents based on mobile location data,considering that the actual travel time,number of people,the various travel modes and the complex situations such as transfers and roundtrips,it is necessary to identify the stay points in the user trajectory.Then,the trajectory should be divided into a single mode travel chain.Finally,the travel positioning trajectory is matched to the corresponding driving section segment by segment to complete the map matching.For recognizing the resident point in the user's trajectory,the volunteer data provided by the operator would be pre-processed to identify and eliminate trajectory oscillations to obtain accurate location.Then,based on the CFSFDP algorithm,the time dimension limitation is explicitly increased,and the local density is extended from two-dimension to three-dimension.Moreover,in order to characterize the cluster center point in the time dimension,the concept of high-density time interval is defined.And the suitable cluster center screening strategy is developed to automatically select the appropriate cluster center.Finally,it identifys the resident points in the travel trajectory of individual users over a period of time and completed the division of the travel chains.The experimental results show that the algorithm is suitable for signaling data with low sampling density and poor positioning accuracy.It is more suitable for spatio-temporal data than CFSFDP algorithm.Compared with Density-Based Spatial Clustering of Applications with Noise based on Spatio-Temporal data(ST-DBSCAN)algorithm,the recall rate is improved by 14%,the accuracy rate is increased by 8%,and the computational complexity is also reduced.In order to match the travel positioning trajectory to the corresponding road segment,the map matching is completed based on the Hidden Markov Model.Firstly,the imformation database of base stations and road networks is established and the sparse positioning trajectory is filled by interpolation.Then,considering the urban road network complexity and matching calculation cost,based on the Von Lonoy diagram,the candidate road search area is formulated to reduce the hidden state space size.Furthermore,the HMM was established in this thesis,considering the distance between the observation location point and the candidate road segment,the length of the candidate road segment in the search area,the similarity of the trajectory,the the connectivity between the current road and the candidate road,one-way-traffic traffic restrictions on the road.Finally,the map matching problem is converted into a prediction problem in HMM,and the Viterbi algorithm is used to obtain the road network trajectory corresponding to the actual trip.It studies the travel behavior of residents based on mobile location data in this thesis,which provides new ideas for the application research of low-precision location data represented by mobile data and lays an important foundation for specific applications such as travel modes and travel destination identification based on mobile data.