Synthesis of an Algorithm for Processing the Trajectories of Moving Objects Using the Methods of Data Clustering Theory

Introduction.  Requirements for the quality of information about the trajectory of moving objects provided by sensor networks are increasingly becoming more stringent. For Information and Data Processing Centers (DPC) at control and management command posts, the issue of information mapping and forming the true trajectories of moving objects in the area of intersection of network detection zones is of particular importance. The use of conventional approaches to solving this problem involves issues  related to ensuring the efficient provision of users with complete and reliable information about trajectories in real time. In this article, wee propose a new approach to solving this problem using data mining theory, in particular, the methods of data clustering theory. Based on an analysis of the process of processing radar data in a DPC and its similarity with that of data clustering, we synthesized an algorithm for processing the trajectories of moving objects. The algorithm was verified by modelling and experimental research.

Aim.  To develop a generalized scheme for processing object trajectories (TP) in a DPC and to synthesized a TP algorithm using the methods of data clustering theory.

Materials  and  methods.  Data  Clustering  theory,  Systems   Engineering  theory,  Radar  Data  processing  theory (RD), methods of mathematical modelling and experimental research.

Results.  Based on an analysis of the essence of radar data processing (RD) in a DPC and its similarity with the process of data clustering,  an algorithm for processing the trajectories of moving objects was synthesized and verified by modelling and experimental research. A generalized scheme for processing the trajectories of moving objects in a DPC and a TP algorithm for a DPC were synthesized.

Conclusions.  An algorithm for processing object trajectories was proposed based on a new approach of data clustering theory. A generalized scheme and an algorithm for processing object trajectories (TP) in a DPC were suggested. These developments can be  effectively applied in various models, e.g. centralized, hierarchical and decentralized. The synthesized algorithm can provide output information about the true identified trajectories in terms of various indicators of data processing systems (DPS).

1. Bar-Shalom Y., Fortmann T. E. Tracking and data association. Boston, Academic Press, 2010, 322 p.

2. Voroshilin E. P., Tislenko V. I. Analysis of methods of automatic tracking of targets by range. Bulletin of the Tomsk Polytechnic University. 2006, vol. 309, no. 8, pp. 67-72. (In Russ.)

3. Ahmad A. Multiple. Targets Classification and Fuzzy Logic Decision Fusion in Wireless Sesor Networks. World Academy of Science, Engineering and Technology Intern. J. of Electrical and Coputer Engineering. 2014, vol. 8, no. 1, pp. 121-128.

4. Ba-Ngu Vo, Mallick M., Bar-Shalom Y., Coraluppi S., Osborne R., Mahler R., Ba-Tuong Multitarget Tracking. Vo Preprint, Wiley Encyclopedia of Electrical and Electronics Engineering, Wiley. Sept. 2015, pp. 1-23.

5. Baoliang Sun, Chunlan Jiang, Ming Li. Fuzzy Neural Network-Based Interacting Multiple Model for Multi-Node Target Tracking Algorithm. Sensors. 2016, vol. 16, iss. 11, pp. 1-14. doi: 10.3390/s16111823

6. Kuzmin S. Z. Digital radar. Introduction to theory. Kiev, KVITS, 2000, 428 p. (In Russ.)

7. Ageev S. A. Application of intelligent methods of information representation to manage information security risks in secure multiservice special-purpose networks. Proc. of SPIIRAS. 2015, vol. 4, iss. 41, pp. 149-162. (In Russ.)

8. Leochenkov A. V. Fuzzy modeling in MatLab and fuzzyTECH. St Petersburg BHV, 2005, 736 p. (In Russ.)

9. Shtovba S. Design of fuzzy systems by means of MatLab. M., Publishing house "Hotline-Telecom", 2007, 288 p. (In Russ.)

10. Yosefi M., Erza M., Aliakbari N., Khoshguian S. An effisient tracking algorithm based on spatial kerne and FCM classifier. Australian J. of basic and applied sciences. 2011, vol. 5, iss. 3, pp. 592-600.

11. Demidova L. A., Titov S. B. An approach to the problem of odd clusterization under conditions of uncertainty in the selection of the target function. Vest. RGRTU. Ryazan’. 2009, no. 3, iss. 29, pp. 54-60. (In Russ.)

12. Shaoming He, Hyo-Sang Shin, Tsourdos A. MultiSensor Multi-Target Tracking Using Domain Knowledge and Clustering. IEEE Sensors J. 2018, Aug., pp. 1-11. doi: 10.1109/JSEN.2018.2863105

13. Yang Yu, Zhang B., Rao B., Chen L. Internat An Improved Fuzzy C-means Cluster Algorithm for Radar Data Association. J. of Advancements in Computing Technology. 2019, vol. 4, iss. 20. doi: 10.4156/IJACT.VOL4.ISSUE20.22

14. Wang Hao, Liu Tangxing, Qing Bu, Bo Yang An Algorithm based on Hierarchical Clustering for Multitarget Tracking of Multi-sensor Data Fusion. Proc. of the 35 th Chinese Control Conf., Chengdu, China, Jul. 2016.doi: 10.1109/ChiCC.2016.7554147

15. Khizhnyak A. V., Belous A. A., Bely A. S. Identification of trajectory information by applying fuzzy automatic classification in the information association problem. Dokl. BGUIR. 2012, no. 4 (66), pp. 56-61. (In Russ.)