Feature Importances: A Tool to Explain Radio Propagation and Reduce Model Complexity

Machine learning models have been widely deployed to tackle the problem of radio propagation. In addition to helping in the estimation of path loss, they can also be used to better understand the details of various propagation scenarios. Our current work exploits the inherent ranking of feature importances provided by XGBoost and Random Forest as a means of indicating the contribution of the underlying propagation mechanisms. A comparison between two different transmitter antenna heights, revealing the associated propagation profiles, is made. Feature selection is then implemented, leading to models with reduced complexity, and consequently reduced training and response times, based on the previously calculated importances.

[1]  Francesco Rinaldi,et al.  Path loss prediction in urban environment using learning machines and dimensionality reduction techniques , 2009, Comput. Manag. Sci..

[2]  Katherine Siakavara,et al.  Mobile radio propagation path loss prediction using Artificial Neural Networks with optimal input information for urban environments , 2015 .

[3]  Jing Wang,et al.  Path Loss Prediction Based on Machine Learning: Principle, Method, and Data Expansion , 2019, Applied Sciences.

[4]  Zunwen He,et al.  Air-to-Air Path Loss Prediction Based on Machine Learning Methods in Urban Environments , 2018, Wirel. Commun. Mob. Comput..

[5]  Andrea J. Goldsmith,et al.  A Measurement-Based Model for Predicting Coverage Areas of Urban Microcells , 1993, IEEE J. Sel. Areas Commun..

[6]  John N. Sahalos,et al.  A Neural Network Approach to the Prediction of the Propagation Path-loss for Mobile Communications Systems in Urban Environments , 2007 .

[7]  Sotirios K. Goudos,et al.  Neural Networks and Random Forests: A Comparison Regarding Prediction of Propagation Path Loss for NB-IoT Networks , 2019, 2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST).

[8]  Nasir Faruk,et al.  ANFIS Model for Path Loss Prediction in the GSM and WCDMA Bands in Urban Area , 2019 .

[9]  Henry L. Bertoni,et al.  Unified approach to prediction of propagation over buildings for all ranges of base station antenna height , 1993 .

[10]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  J. N. Sahalos,et al.  Modeling by optimal Artificial Neural Networks the prediction of propagation path loss in urban environments , 2013, 2013 IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications (APWC).

[13]  Nasir Faruk,et al.  Determination of Neural Network Parameters for Path Loss Prediction in Very High Frequency Wireless Channel , 2019, IEEE Access.

[14]  Luís M. Correia,et al.  A propagation model for urban microcellular systems at the UHF band , 2000, IEEE Trans. Veh. Technol..

[15]  Sotirios K. Goudos,et al.  Deep learning for radio propagation: Using image-driven regression to estimate path loss in urban areas , 2020, ICT Express.

[16]  K. Siakavara,et al.  Application of a Composite Differential Evolution Algorithm in Optimal Neural Network Design for Propagation Path-Loss Prediction in Mobile Communication Systems , 2013, IEEE Antennas and Wireless Propagation Letters.

[17]  Ramoni O. Adeogun.  Calibration of Stochastic Radio Propagation Models Using Machine Learning , 2019, IEEE Antennas and Wireless Propagation Letters.

[18]  Zunwen He,et al.  Path Loss Prediction Based on Machine Learning Methods for Aircraft Cabin Environments , 2019, IEEE Access.