Power Delay Profile Filtering Technique Using Artificial Neural Networks

This paper presents an alternative technique for the filtering of the power delay profile in mobile radio channel using artificial neural networks for the identification and extraction of impulsive noise. The power delay profiles obtained from field measurements in the 700 MHz band, were subjected to two filtering techniques: the CFAR (Constant False Alarm Rate) filtering technique and the proposed technique using artificial neural networks. The neural technique demonstrated to be a good alternative with 91.38% of average accuracy and more satisfactory filtering than the CFAR for the identification of valid multipaths. The results show the characteristic of the ANN technique in identifying a greater number of multipaths. The results of the temporal dispersion parameters Mean Excess Delay and RMS Delay Spread achieved by the new technique presented satisfactory values when compared with the CFAR and with the values described in the ITU-R (International Union of Telecommunications) standard P.1411-9.

[1]  Leni J. Matos,et al.  Time and Frequency Dispersion Parameters Measurements at 1 . 88 GHz in a Vegetated Channel , .

[2]  A.K. Barros,et al.  ECG Data Compression by Independent Component Analysis , 2005, 2005 IEEE Workshop on Machine Learning for Signal Processing.

[3]  M. P. C. de Almeida,et al.  Preliminary results of channel characterization at 700MHz band in urban and rural regions , 2014, 2014 International Telecommunications Symposium (ITS).

[4]  F. M. Landstorfer,et al.  Neural network approach to prediction of terrestrial wave propagation for mobile radio , 1993 .

[5]  J. D. Parsons,et al.  Sounding techniques for wideband mobile radio channels : a review , 1991 .

[6]  C. R. Ron,et al.  Characterization of a Mobile Urban Radio Channel with an Improved Multicarrier Sounding Technique , 2015 .

[7]  Gokhan M. Guvensen,et al.  An Efficient Beam and Channel Acquisition via Sparsity Map and Joint Angle-Delay Power Profile Estimation for Wideband Massive MIMO Systems , 2019, ArXiv.

[8]  Leni J. Matos,et al.  The Relevance Vector Machine Applied to the Modeling of Wireless Channels , 2013, IEEE Transactions on Antennas and Propagation.

[9]  Elvino S. Sousa,et al.  Delay spread measurements for the digital cellular channel in Toronto , 1994 .

[10]  Gokhan M. Guvensen,et al.  An Efficient Spatial Channel Covariance Estimation via Joint Angle-Delay Power Profile in Hybrid Massive MIMO Systems , 2020, 2020 IEEE International Conference on Communications Workshops (ICC Workshops).

[11]  L. J. Matos,et al.  Channel Characterization on Vehicle to Infrastructure Scenarios in 5.8 GHz , 2018, 2018 IEEE MTT-S Latin America Microwave Conference (LAMC 2018).

[12]  Leonardo H. Gonsioroski,et al.  Measurements of Building Transmission Loss and Delay Spread at 2.5 GHz , 2015 .

[13]  Joao M. M. Silva,et al.  Improvement of Outdoor Signal Strength Prediction in UHF Band by Artificial Neural Network , 2016, IEEE Transactions on Antennas and Propagation.

[14]  B. J. Cavalcanti,et al.  Optimizing empirical propagation models for LTE and LTE-A using genetic algorithms at 879 MHz , 2017, 2017 IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications (APWC).

[15]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[16]  Muhammad Iram Baig,et al.  Analysis of CFAR techniques , 2016, 2016 13th International Bhurban Conference on Applied Sciences and Technology (IBCAST).

[17]  Marcelo Molina Silva,et al.  Wideband Channel Sounding Using Modulated OFDM Signals , 2018, 2018 IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications (APWC).