CSI-based Outdoor Localization for Massive MIMO: Experiments with a Learning Approach

We report on experimental results on the use of a learning-based approach to infer the location of a mobile user of a cellular network within a cell, for a 5G-type Massive multiple input, multiple output (MIMO) system. We describe how the sample spatial covariance matrix computed from the CSI can be used as the input to a learning algorithm which attempts to relate it to user location. We discuss several learning approaches, and analyze in depth the application of extreme learning machines, for which theoretical approximate performance benchmarks are available, to the localization problem. We validate the proposed approach using experimental data collected on a Huawei 5G testbed, provide some performance and robustness benchmarks, and discuss practical issues related to the deployment of such a technique in 5G networks.

[1]  Yantao Han,et al.  The potential approaches to achieve channel reciprocity in FDD system with frequency correction algorithms , 2010, 2010 5th International ICST Conference on Communications and Networking in China.

[2]  Alexis Decurninge,et al.  Efficient Channel State Information Acquisition in Massive MIMO Systems using Non-Orthogonal Pilots , 2017, WSA.

[3]  Zhenyu Liao,et al.  A Random Matrix Approach to Neural Networks , 2017, ArXiv.

[4]  Dirk T. M. Slock,et al.  Channel Covariance Estimation in Massive MIMO Frequency Division Duplex Systems , 2015, 2015 IEEE Globecom Workshops (GC Wkshps).

[5]  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).

[6]  김용수,et al.  Extreme Learning Machine 기반 퍼지 패턴 분류기 설계 , 2015 .

[7]  Hao Jiang,et al.  A Robust Indoor Positioning System Based on the Procrustes Analysis and Weighted Extreme Learning Machine , 2016, IEEE Transactions on Wireless Communications.

[8]  Giuseppe Caire,et al.  Multi-Band Covariance Interpolation with Applications in Massive MIMO , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[9]  Sofiène Affes,et al.  Cost-effective localization in underground mines using new SIMO/MIMO-like fingerprints and artificial neural networks , 2014, 2014 IEEE International Conference on Communications Workshops (ICC).

[10]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[11]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[12]  Alexis Decurninge,et al.  Covariance estimation with projected data: Applications to CSI covariance acquisition and tracking , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[13]  Dirk T. M. Slock,et al.  Mobile Terminal Positioning via Power Delay Profile Fingerprinting: Reproducible Validation Simulations , 2006, IEEE Vehicular Technology Conference.

[14]  D. Shutin,et al.  Clustering wireless channel impulse responses in angular-delay domain , 2004, IEEE 5th Workshop on Signal Processing Advances in Wireless Communications, 2004..

[15]  Slawomir Stanczak,et al.  FDD Massive MIMO Channel Spatial Covariance Conversion Using Projection Methods , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Han Zou,et al.  Robust Extreme Learning Machine With its Application to Indoor Positioning , 2016, IEEE Transactions on Cybernetics.

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

[18]  Jie Zhang,et al.  Device-Free Localization via an Extreme Learning Machine with Parameterized Geometrical Feature Extraction , 2017, Sensors.

[19]  Sanjay Jha,et al.  CSI-MIMO: Indoor Wi-Fi fingerprinting system , 2014, 39th Annual IEEE Conference on Local Computer Networks.

[20]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[21]  Geoffrey Ye Li,et al.  Single-Site Localization Based on a New Type of Fingerprint for Massive MIMO-OFDM Systems , 2018, IEEE Transactions on Vehicular Technology.

[22]  Erik G. Larsson,et al.  Massive MIMO for next generation wireless systems , 2013, IEEE Communications Magazine.

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