Research on the method of travel area clustering of urban public transport based on Sage-Husa adaptive filter and improved DBSCAN algorithm

The travel trajectory data of mobile intelligent terminal users are characterized by clutter, incompleteness, noise, fuzzy randomness. The accuracy of original data is an essential prerequisite for better results of trajectory data mining. The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is one of the most effective trajectory data mining methods, but the selection of input parameters often limits it. The Sage-Husa adaptive filtering algorithm effectively controls the error range of mobile phone GPS data, which can meet the positioning accuracy requirements for DBSCAN spatial clustering having the advantages of low cost and convenient use. Then, a novel cluster validity index was proposed based on the internal and external duty cycle to balance the influence of the distance within-cluster, the distance between clusters, and the number of coordinate points in the process of clustering. The index can automatically choose input parameters of density clustering, and the effective clustering can be formed on different data sets. The optimized clustering method can be applied to the in-depth analysis and mining of traveler behavior trajectories. Experiments show that the Sage -Husa adaptive filtering algorithm proposed further improves the positioning accuracy of GPS, which is 17.34% and 15.24% higher eastward and northward, 14.25%, and 18.17% higher in 2D and 3D dimensions, respectively. The number of noise points is significantly reduced. At the same time, compared with the traditional validity index, the evaluation index based on the duty cycle proposed can optimize the input parameters and obtain better clustering results of traveler location information.

INFORMATION TECHNOLOGY FOR TRAJECTORY DATA MINING

Introduction. Advanced technologies allow almost continuous tracking and recording the movement of objects inspace and time. Detecting interesting patterns in these data, popular routes, habits, and anomalies in object motion and understanding mobility behaviors are actual tasks in different application areas such as marketing, urban planning, transportation, biology, ecology, etc.Problem Statement. In order to obtain useful information from trajectories of moving objects, it is important to develop and to improve mathematical methods of spatiotemporal analysis and to implement them in highquality modern software.Purpose. The purpose of this research is the development of information technology for trajectory data mining.Materials and Methods. Information technology contains the three main algorithms: revealing key pointsand sequences of interest with the use of density-based trajectories clustering of studied objects; detecting patterns of an object movement based on association rules and hierarchical cluster analysis of its motion trajectories in the time interval of observations, similarity measure of the motion trajectories has been proposed to be calculated on the basis of the DTW method with the use of the modified Haversine formula; new algorithm for revealing permanent routes and detecting groups of similar objects has been developed on the basis of clustering ensemblesof all studied trajectories in time. The clustering parameters are selected with multi-criteria quality evaluation.Results. The modern software that implements the proposed algorithms and provides a convenient interactionwith users and a variety of visualization tools has been created. The developed algorithms and software have beentested in detail on the artificial trajectories of moving objects and applied to analysis of real open databases.Conclusions. The experiments have confirmed the efficiency of the proposed information technology thatmay have a practicable application to trajectory data mining in various fields.

Big Trajectory Data Mining: A Survey of Methods, Applications, and Services

The increasingly wide usage of smart infrastructure and location-aware terminals has helped increase the availability of trajectory data with rich spatiotemporal information. The development of data mining and analysis methods has allowed researchers to use these trajectory datasets to identify urban reality (e.g., citizens’ collective behavior) in order to solve urban problems in transportation, environment, public security, etc. However, existing studies in this field have been relatively isolated, and an integrated and comprehensive review is lacking the problems that have been tackled, methods that have been tested, and services that have been generated from existing research. In this paper, we first discuss the relationships among the prevailing trajectory mining methods and then, classify the applications of trajectory data into three major groups: social dynamics, traffic dynamics, and operational dynamics. Finally, we briefly discuss the services that can be developed from studies in this field. Practical implications are also delivered for participants in trajectory data mining. With a focus on relevance and association, our review is aimed at inspiring researchers to identify gaps among tested methods and guiding data analysts and planners to select the most suitable methods for specific problems.

A Trajectory Partition Method Based on Combined Movement Features

Trajectory data mining has become an increasing concern in the location-based applications, and the trajectory partition is taken as the primary procedure of trajectory data mining. The amount of movement trajectories of nodes is typically very large, and the trajectory shapes are extremely diverse, which makes the trajectory partition a vital issue to the trajectory data mining results. In this work, the movement behaviors of nodes are analyzed from the aspects of moving speeds, stop points, and moving directions, and then a novel Trajectory Partition Method based on combined movement Features (TPMF) is proposed to partition the trajectories. In TPMF, we first extract the change points where the movement speeds of nodes are varied significantly; then, we extract the stop points by detecting the speed variations of nodes; finally, the Douglas-Peucker algorithm is applied to partition the subtrajectories according to the extracted feature points (change points and stop points). Simulations are carried out on the Geolife trajectory dataset, and the simulation results indicate that TPMF can achieve a preferable trade-off between the simplification rate and the trajectory partition error, while the running time is shortened as well.