Evaluation of Indoor Positioning System Based on Difference of Signal Strength Using Fingerprinting Technique and K-Means Clustering Algorithm

Main Article Content

Jirapat Sangthong


This paper presents the evaluation of indoor positioning system based on DIFF parameter using fingerprinting technique and K-Means clustering algorithm. In training process, RSS values at the reference positions are surveyed and sent to server to generate the DIFF-fingerprint. After that, the similarly DIFF values have been grouped by using K-Means and keep them to the database. For testing process, the positions are estimated by using the fingerprinting technique and algorithms that are LS and k-NN algorithm. The results show that the DIFF parameter can be used to improve the accuracy of indoor positioning system. However, the no-clustering case was provided slightly higher accuracy than K-Means clustering case. But, the K-Means clustering case can computed faster than noclustering case in testing process. So, the indoor positioning system based on DIFF parameter using fingerprinting technique and K-Means clustering algorithm case can be suitable applied on the mobile devices that have limited CPU and memory. Moreover, it can be used for the system that require fast
computation in positioning process.

Article Details

Research Articles


[1] C. Yang and H. Shao, “WiFi-based indoor positioning,” IEEE Communications Magazine, vol. 53, no. 3, pp. 150-157, March 2015.
[2] D. Dardari, P. Closas and P. M. Djurić, “Indoor tracking: theory, methods, and technologies,” IEEE Transactions on Vehicular Technology, vol. 64, no. 4, pp. 1263-1278, April 2015.
[3] L. F. Shi, Y. Wang, G. X. Liu, S. Chen, Y. L. Zhao and Y. F. Shi, “A fusion algorithm of indoor positioning based on PDR and RSS fingerprint,” IEEE Sensors Journal, vol. 18, no. 23,pp. 9691-9698, December 2018.
[4] B. Koo, S. Lee, M. Lee, D. Lee, S. Lee and S. Kim, “PDR/fingerprinting fusion indoor location tracking using RSS recovery and clustering,” in Proc. The International Conference on Indoor Positioning and Indoor Navigation, pp. 699 – 704, October 2014.
[5] Q. Li, W. Li, W. Sun, J. Li and Z. Liu, “Fingerprint and assistant nodes based Wi-Fi localization in complex indoor environment,” IEEE Access, vol. 4, pp. 2993 – 3004, June 2016.
[6] S. Yoon, K. Lee and I. Rhee, “FM-based Indoor Localization via Automatic Fingerprint DB Construction and matching,” in Proc. The 11th Annual International Conference on Mobile Systems, Applications, and Services, pp. 207–220, June 2013.
[7] M. B. Kjærgaard, “Indoor Location Fingerprinting with Heterogeneous Clients,” Pervasive and Mobile Computing, vol. 7, no.1, pp. 31 – 43. February 2011.
[8] A. K. M. M. Hossain, Y. Jin, W. Soh and H. N. Van, “SSD: A Robust RF Location Fingerprint Addressing Mobile Devices' Heterogeneity,” IEEE Transactions on Mobile Computing, vol. 12, no. 1, p. 65–77, 2013.
[9] D. Lam, M. Wei and D. Wunsch, “Clustering data of mixed categorical and numerical type with unsupervised feature learning,” IEEE Access, vol. 3, pp. 1605-1613, 2015.
[10] C. Tsai, C. Lai, M. Chiang and L. T. Yang, “Data mining for internet of things: a survey,” IEEE Communications Surveys & Tutorials, vol. 16, no. 1, pp. 77-97, 2014.
[11] M. A. Alsheikh, S. Lin, D. Niyato and H. Tan, “Machine learning in wireless sensor networks: algorithms, strategies, and applications,” IEEE Communications Surveys & Tutorials, vol. 16, no. 4, pp. 1996-2018, 2014.
[12] R. Olyazadeh “Least Square Approach on Indoor Positioning Measurement Techniques,” Geomundus, 2012.
[13] M. Choi and B. Jang, “An Accurate Fingerprinting based Indoor Positioning Algorithm,” International Journal of Applied Engineering Research, vol. 12, no. 1, pp. 86-90, 2017.