Abstract
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.
Funder
zhejiang provincial natural science foundation of china
zhejiang provincial educational committee
the scientific research foundation for the returned scholars, ministry of education of china
Publisher
Public Library of Science (PLoS)
Reference22 articles.
1. C. Huang, W. Su, P. Liu and M. Ma, "Application of adaptive Kalman filter technique in initial alignment of strapdown inertial navigation system," Proceedings of the 29th Chinese Control Conference,2010, pp. 2087–2090. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5573673&isnumber=5571954
2. F. Sun and H. Zhang, "Application of a new Adaptive Kalman Filtering algorithm in initial alignment of INS," 2011 IEEE International Conference on Mechatronics and Automation, 2011, pp. 2312–2316,DOI: 10.1109 / ICMA. 2011.5986346.
3. Chihang Zhao, Jie He, Liye Zhao and Libin Huang, “Denoising the Signal of the Quartz Flexural Gravitational Sensor based on Adaptive Kalman Filtering," 2011 International Conference on Electric Information and Control Engineering, 2011, Pp. 3792–3795. doi: 10.1109/ICEICE.2011.5777257
4. M. Narasimhappa, P. Rangababu, S. L. Sabat and J. Nayak, "A modified Sage-Husa adaptive Kalman filter for denoising Fiber Optic Gyroscope signal," 2012 Annual IEEE India Conference (INDICON), 2012, Pp. 1266–1271. doi: 10.1109/INDCON.2012.6420813
5. P. Yuzhen, Y. Quande and Z. Benfa, "Adaptive Extended Kalman Filter for Localization of mobile Robot," 2016 Chinese Control and Decision Conference (CCDC), 2016, pp. 5337–5342. doi: 10.1109/CCDC.2016.7531952
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献