Abstract—
Aiming at the need to discover user behavior characteristics and knowledge from moving trajectory data, a user behavior profiling method based on moving trajectory information was proposed. Firstly, the trajectory coordinates were preprocessed to clean out good data. Secondly, the travel rules and the points of interest of the user were found by means of stay points detection, staying points’ semantics and frequent pattern mining. In the aspect of predicting user trajectory information, Key Points Long Short-Term Memory Networks (KP-LSTM) was proposed to predict the user’s future travel location; then the user’s important attribute characteristics were taken through the user profiling, intuitively depicting the characteristics and patterns of users’ lives. Finally, the availability of the method was proved by experiments, and the prediction accuracy was better than the traditional Linear regression and LSTM neural network.
Similar content being viewed by others
REFERENCES
Wang, G., Zhang, X., Tang, S., et al., Unsupervised clickstream clustering for user behavior analysis, Chi Conference on Human Factors in Computing Systems, 2016.
Gao, Q., Zhang, F.L., Wang, R.J., and Zhou, F., Trajectory big data: A review of key technologies in data processing, J. Software, 2017, vol. 28, no. 4, pp. 959–992. http://www.jos.org.cn/1000-9825/5143.html.
Wang Liang, Hu Kun-Yuan, Ku Tao, and Wu Jun-Wei, Mining urban moving trajectory patterns based on multi-scale space partition and road network modeling, Acta Autom. Sin., 2015, vol. 41, no. 1, pp. 47–58.
Qiao, S.J., Han, N., Ding, Z.M., et al., A multiple-motion-pattern trajectory prediction model for uncertain moving objects, Acta Autom. Sin., 2018, vol. 44, no. 4, pp. 608–618.
Song, C., Qu, Z., Blumm, N., et al., Limits of predictability in human mobility, Science, 2010, vol. 327, no. 5968, pp. 1018–1021.
Centola, D., The spread of behavior in an online social network experiment, Science, 2010, vol. 329, no. 5996, pp. 1194–1197.
Qiao, S., Shen, D., Wang, X., et al., A self-adaptive parameter selection trajectory prediction approach via hidden Markov models, IEEE Trans. Intell. Transp. Syst., 2015, vol. 16, no. 1, pp. 284–296.
Ding, Z., Yang, B., Güting, R.H., et al., Network-matched trajectory-based moving-object database: Models and applications, IEEE Trans. Intell. Transp. Syst., 2015, vol. 16, no. 4, pp. 1918–1928.
Xu, J., Gao, Y., Liu, C., et al., Efficient route search on hierarchical dynamic road networks, Distrib. Parallel Databases, 2015, vol. 33, no. 2, pp. 227–252.
Wenbin, H., Shanchuan, X., Jiahui, W., et al., The profile construction of the mobile user, J. Mod. Inf., 2016, vol. 36, no. 10, pp. 54–61.
Garcia, S., Luengo, J., and Herrera, F., Tutorial on practical tips of the most influential data preprocessing algorithms in data mining, Knowl.-Based Syst., 2016, vol. 98, pp. 1–29.
Liua, X., Zhao, Y., and Sunb, M., An improved apriori algorithm based on an evolution-communication tissue-like P system with promoters and inhibitors, Discrete Dyn. Nat. Soc., 2017, vol. 2017, no. 1, pp. 1–11.
Liang, W., Hu, K., Tao, K., et al., Mining frequent trajectory pattern based on vague space partition, Knowl.-Based Syst., 2013, vol. 50, pp. 100–111.
Gers, F.A., Schmidhuber, J., et al., Learning to forget: Continual prediction with LSTM, Neural Comput., 2000, vol. 12, no. 10, pp. 2451–2471.
Li, M., Lu, F., Zhang, et al., Predicting future locations of moving objects with deep fuzzy-LSTM networks, Transportmetrica A: Transp. Sci., 2018, vol. 47, no. 12, pp. 102–111.
Sun Yasheng, Jiang Qi, Hu Jie, et al., Attention mechanism based pedestrian trajectory prediction generation model, J. Comput. Appl., 2019, vol. 39, no. 3, pp. 52–58.
Alahi, A., Goel, K., Ramanathan, V., et al., Social LSTM: Human trajectory prediction in crowded spaces, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
Wang, Z. and Yuan, X., Visual analysis of trajectory data, J. Comput.-Aided Des. Comput. Graphics, 2015, vol. 27, no. 1, pp. 9–25.
Funding
This work is partially supported by Natural Science Foundation of China no. 61370139, fund of Bistu improving the scientific research level no. 5 211 910 933, and “Information +” special fund.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare no conflict of interest.
About this article
Cite this article
Hao Li, Haiyan Kang Research on User Behavior Prediction and Profiling Method Based on Trajectory Information. Aut. Control Comp. Sci. 54, 456–465 (2020). https://doi.org/10.3103/S0146411620050065
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411620050065