Indoor Location Based on Supervised Learning Using FM Radio Stations

• David Ferreira Federal University of Amazonas
• Waldir da Silva Júnior Federal University of Amazonas
• Celso Carvalho Federal University of Amazonas

DOI: https://doi.org/10.5753/erigo.2020.13865

Abstract

For the location of mobile devices on wireless networks, three or more fixed devices must be installed, whose transmitted signals are used as location parameters. The problem with this approach is the increase in energy and monetary costs. Thus, the objective of this work is to propose a method of location using FM radio stations with a view to low cost and high precision. The tests were carried out in a domestic environment with approximately 30 m 2 and 15 reference points. As a result of the tests, the proposed QA-PCA-kNN method stood out when using 6 characteristics of the FM signals, providing the loca- tion with a mean error of 0.0688 meters and a standard deviation of 0.2536 and presenting an accuracy of 86.80%.

References

Al-Fuqaha, A., Guizani, M., Mohammadi, M., Aledhari, M., and Ayyash, M. (2015). Internet of things: A survey on enabling technologies, protocols, and applications. IEEE Communications Surveys Tutorials, 17(4):2347–2376.

Azur, M., Stuart, E., Frangakis, C., and Leaf, P. (2011). Multiple imputation by chained equations: What is it and how does it work? International journal of methods in psychiatric research, 20:40–9.

Brownlee, J. (2016). Master Machine Learning Algorithms: Discover How They Work and Implement Them From Scratch. Jason Brownlee.

Cai, X., Li, X., Yuan, R., and Hei, Y. (2015). Identification and mitigation of nlos based on channel state information for indoor wifi localization. In 2015 International Conference on Wireless Communications Signal Processing (WCSP), pages 1–5.

Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1):21–27.

Danbatta, S. J. and Varol, A. (2019). Comparison of zigbee, z-wave, wi-fi, and bluetooth wireless technologies used in home automation. In 2019 7th International Symposium on Digital Forensics and Security (ISDFS), pages 1–5.

Fang, S. and Lin, T. (2012). Principal component localization in indoor wlan environments. IEEE Transactions on Mobile Computing, 11(1):100–110.

Ferreira, D., Souza, R., and Carvalho, C. (2020). Qa-knn: Indoor localization based on quartile analysis and the knn classifier for wireless networks. Sensors, 20(17):4714. Gonzalez, R. and Woods, R. (2009). Processamento Digital De Imagens. ADDISON WESLEY BRA.

Harrell, F. E. (2001). Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis. Springer New York, New York, NY. Joarder, A. and Firozzaman, M. (2001). Quartiles for discrete data. Teaching Statistics, 23:86–89.

Kapetanovic, Z., Moore, G. E., Garman, S., and Smith, J. R. (2020). Classifying wlan packets from the rf envelope: Towards more efficient wireless network performance. In Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning, EMDL’20, page 13–18, New York, NY, USA. Association for Computing Machinery.

Khullar, R. and Dong, Z. (2017). Indoor localization framework with wifi fingerprinting. In 2017 26th Wireless and Optical Communication Conference (WOCC), pages 1–6.

Kim, K. S., Wang, R., Zhong, Z., Tan, Z., Song, H., Cha, J., and Lee, S. (2018). Large-scale location-aware services in access: Hierarchical building/floor classification and location estimation using wi-fi fingerprinting based on deep neural networks. Fiber and Integrated Optics, 37(5):277–289.

Langford, E. (2006). Quartiles in elementary statistics. Journal of Statistics Education, 14.

Lantz, B. (2015). Machine Learning with R. Packt Publishing, 2nd edition.

Le, W., Wang, Z., Wang, J., Zhao, G., and Miao, H. (2014). A novel wifi indoor positioning method based on genetic algorithm and twin support vector regression. In The 26th Chinese Control and Decision Conference (2014 CCDC), pages 4859–4862.

Li, H., Syed, M., Yao, Y.-D., and Kamakaris, T. (2009). Spectrum sharing in an ism band: Outage performance of a hybrid ds/fh spread spectrum system with beamforming. EU-RASIP J. Adv. Sig. Proc., 2009.

Moghtadaiee, V. and Dempster, A. (2014). Indoor location fingerprinting using fm radio signals. Broadcasting, IEEE Transactions on, 60:336–346.

Mosteller, F. and Tukey, J. W. (1977). Data Analysis and Regression: a Second Course in Statistics. pub-AW, pub-AW:adr.

Pearson, K. (1901). On lines and planes of closest fit to systems of points in space. Philosophical Magazine, 2:559–572.

Popleteev, A., Osmani, V., and Mayora, O. (2012). Investigation of indoor localization with ambient fm radio stations. In 2012 IEEE International Conference on Pervasive Computing and Communications, pages 171–179.

Rappaport, T. (2002). Wireless communications: Principles and practice. Prentice Hall communications engineering and emerging technologies series. Prentice Hall, 2nd edition. Includes bibliographical references and index.

Salamah, A. H., Tamazin, M., Sharkas, M. A., and Khedr, M. (2016). An enhanced wifi indoor localization system based on machine learning. In 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN), pages 1–8.

Salim, F., Williams, M., Sony, N., Dela Pena, M., Petrov, Y., Saad, A. A., and Wu, B. (2014). Visualization of wireless sensor networks using zigbee’s received signal strength indicator (rssi) for indoor localization and tracking. In 2014 IEEE International Conference on Pervasive Computing and Communication Workshops (PERCOM WORKSHOPS), pages 575–580.

Wen, F. and Liang, C. (2015). Fine-grained indoor localization using single access point with multiple antennas. IEEE Sensors Journal, 15(3):1538–1544.