Towards Practical Indoor Positioning Based on Massive MIMO Systems

We showcase the practicability of an indoor positioning system (IPS) solely based on neural networks (NNs) and the channel state information (CSI) of a (Massive) multiple-input multiple-output (MIMO) communication system, i.e., only build on the basis of data that is already existent in today's systems. As such our IPS system promises both, a good accuracy without the need of any additional protocol/signaling overhead for the user localization task. In particular, we propose a tailored NN structure with an additional phase branch as feature extractor and (compared to previous results) a significantly reduced amount of trainable parameters, leading to a minimization of the amount of required training data. We provide actual measurements for indoor scenarios with up to 64 antennas covering a large area of 80m^2. In the second part, several robustness investigations for real-measurements are conducted, i.e., once trained, we analyze the recall accuracy over a period of several days. Further, we analyze the impact of pedestrians walking in-between the measurements and show that finetuning and pre-training of the NN helps to mitigate effects of hardware drifts and alterations in the propagation environment over time. This reduces the amount of required training samples at equal precision and, thereby, decreases the effort of the costly training data acquisition.

[1]  Vijay K. Bhargava,et al.  Machine Learning Methods for RSS-Based User Positioning in Distributed Massive MIMO , 2018, IEEE Transactions on Wireless Communications.

[2]  Doina Precup,et al.  Real-Time Indoor Localization in Smart Homes Using Semi-Supervised Learning , 2017, AAAI.

[3]  David Mascharka,et al.  LIPS: Learning Based Indoor Positioning System using mobile phone-based sensors , 2016, 2016 13th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[4]  Paramvir Bahl,et al.  RADAR: an in-building RF-based user location and tracking system , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[5]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[6]  Fredrik Tufvesson,et al.  Deep convolutional neural networks for massive MIMO fingerprint-based positioning , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[7]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[8]  Hao Chen,et al.  ConFi: Convolutional Neural Networks Based Indoor Wi-Fi Localization Using Channel State Information , 2017, IEEE Access.

[9]  Wei Zhang,et al.  CSI-based Outdoor Localization for Massive MIMO: Experiments with a Learning Approach , 2018, 2018 15th International Symposium on Wireless Communication Systems (ISWCS).

[10]  Michael Philippsen,et al.  Recurrent Neural Networks on Drifting Time-of-Flight Measurements , 2018, 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[11]  Sanghyuk Lee,et al.  A scalable deep neural network architecture for multi-building and multi-floor indoor localization based on Wi-Fi fingerprinting , 2017, ArXiv.

[12]  Lars Thiele,et al.  QuaDRiGa: A 3-D Multi-Cell Channel Model With Time Evolution for Enabling Virtual Field Trials , 2014, IEEE Transactions on Antennas and Propagation.

[13]  Moe Z. Win,et al.  NLOS identification and mitigation for localization based on UWB experimental data , 2010, IEEE Journal on Selected Areas in Communications.

[14]  David Akopian,et al.  Modern WLAN Fingerprinting Indoor Positioning Methods and Deployment Challenges , 2016, IEEE Communications Surveys & Tutorials.

[15]  Jing Wang,et al.  Accurate real time localization tracking in a clinical environment using Bluetooth Low Energy and deep learning , 2017, PloS one.

[16]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[17]  Emil Björnson,et al.  Massive MIMO Networks: Spectral, Energy, and Hardware Efficiency , 2018, Found. Trends Signal Process..

[18]  Xiangyu Wang,et al.  CiFi: Deep convolutional neural networks for indoor localization with 5 GHz Wi-Fi , 2017, 2017 IEEE International Conference on Communications (ICC).

[19]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[20]  Erik G. Larsson,et al.  Fingerprinting-Based Positioning in Distributed Massive MIMO Systems , 2015, 2015 IEEE 82nd Vehicular Technology Conference (VTC2015-Fall).

[21]  Petar M. Djuric,et al.  Estimation Of Spatial Fields Of Nlos/Los Conditions For Improved Localization In Indoor Environments , 2018, 2018 IEEE Statistical Signal Processing Workshop (SSP).

[22]  Stephan ten Brink,et al.  Novel Massive MIMO Channel Sounding Data Applied to Deep Learning-based Indoor Positioning , 2018, 1810.04126.

[23]  Ernst Eberlein,et al.  A Deep Learning Approach to Position Estimation from Channel Impulse Responses † , 2019, Sensors.

[24]  Stephan ten Brink,et al.  On Deep Learning-Based Massive MIMO Indoor User Localization , 2018, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[25]  Yan Chen,et al.  Achieving Centimeter-Accuracy Indoor Localization on WiFi Platforms: A Multi-Antenna Approach , 2017, IEEE Internet of Things Journal.

[26]  Junhai Luo,et al.  Deep Belief Networks for Fingerprinting Indoor Localization Using Ultrawideband Technology , 2016, Int. J. Distributed Sens. Networks.

[27]  K. J. Ray Liu,et al.  A Time-Reversal Paradigm for Indoor Positioning System , 2015, IEEE Transactions on Vehicular Technology.

[28]  Stephan ten Brink,et al.  On deep learning-based channel decoding , 2017, 2017 51st Annual Conference on Information Sciences and Systems (CISS).