Electrotechnical and Computer Engineering
Vol. 34 No. 11 (2019): Proceedings of the Faculty of Technical Sciences
MACHINE LEARNING – BASED INDOOR LOCALIZATION FOR MOBILE DEVICES
- Vukan Ninković
- Dejan Vukobratović
- Dejan Nemec
Abstract
With the proliferation of mobile devices, indoor localization has become an increasingly important problem. The latest ideas related to its solution are closely related to the principles of machine learning. We propose new algorithm wich considers time – frequency representation of the signal, after OFDM demodulation, as a picture and uses all benefits of machine learning that are alredy applied in solving the problem of image processing and classification. At the end we compare different architectures by accuracy and complexity.
References
[1] A. Khalajmehrabadi, N. Gatsis, D. Akopian “Modern WLAN Fingerprinting Indoor Positioning Methods and Deployment Challenges”, IEEE Commun. Surv. Tutor., 2017.
[2] J. Xiao, K. Wu, Y. Yi, L. Ni , “FIFS: Fine-grained indoor fingerprinting system”, Proc. IEEE ICCCN’12, pp. 1-7, August 2012.
[3] X. Wang, L. Gao, S. Mao, S. Pandey , “CSI-based fingerprinting for indoor localization: A deep learning approach”, IEEE Trans. Veh. Technol., vol. 66, no. 1, pp. 763-776, January 2017.
[4] X. Wang, L. Gao, S. Mao, “CSI phase fingerprinting for indoor localization with a deep learning approach”, IEEE Internet of Things J., vol. 3, no. 6, pp. 1113-1123, December 2016.
[5] X. Wang, S. Mao, “ResLoc: Deep Residual Sharing Learning for Indoor Localizaton with CSI Tensors”, Proc. IEEE PIMRC’17, pp. 1-7, October 2017.
[6] E.Perahia, R.Stacey, “Next Generation Wireless LANs: Throughput, Robustness, and Reliability in 802.11n”, Cambridge, 2008.
[7] A. Krizhevsky, I. Sutskever, G. Hinton, “Imagenet classification with deep convolutional neural networks”, Advances in neural information processing system, pp. 1097-1105, 2012.
[8] K. He, X. Zhang, S. Ren, J.Sun “Deep residual learning for image recognition”, Proc. of CVPR, pp. 770-778, 2016.