A Study Towards Implementing Various Artificial Neural Networks for Signals Classification and Noise Detection in OFDM/PLC Channels | IEEE Conference Publication | IEEE Xplore

A Study Towards Implementing Various Artificial Neural Networks for Signals Classification and Noise Detection in OFDM/PLC Channels


Abstract:

The presence of noise in PLC can eventually lead to information corruption. In this design, we present the usage of several classification learners in detection of noise ...Show More

Abstract:

The presence of noise in PLC can eventually lead to information corruption. In this design, we present the usage of several classification learners in detection of noise that might found in received PLC signals at the receiving end of the OFDM channel. A database of 5,000 PLC signals with their corresponding categories was used for training and evaluation. Four neural networks were studied through experiments: radial basis function (RBF) neural network, supervised Kohonen network, counter propagation neural network, and X-Y fused neural network. The results of the experiments indicate that the RBF model achieves the best performance among the proposed methods, overall classification accuracy of 98.2%. Furthermore, the remaining proposed algorithms: CPNN and XYF networks are considerably robust classification learners, resulting in true classification percentages of 87.9%, 95.3% and 92.1% respectively.
Date of Conference: 20-22 July 2020
Date Added to IEEE Xplore: 10 November 2020
ISBN Information:
Conference Location: Porto, Portugal
Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg, South Africa
Department of Electrical Engineering, Higher colleges of Technology, Abu Dhabi, United Arab Emirates
Department of Electrical and Electronic Engineering Technology, University of Johannesburg, Johannesburg, South Africa

I. Introduction

The Power Line Communication (PLC) system can be considered an economical broadband medium since it takes advantage of the already existing power line distribution infrastructure present everywhere [1]. As a result of that substantial merit, PLC technology has recently attracted a lot of attention of researchers [4] and has been installed in several applications such as broadband transmission, gaming and high definition television (HDTV). However, the PLC technology suffers some damaging disadvantage e.g. noise presence, attenuation and multipath propagation [2], which might, unfortunately, pollute the information transmitted over the wired channels and accordingly, degrade the performance and reliability of PLC communications [1]. Hence, Chang [1] has suggested a functionally effective modulation scheme, known as the orthogonal frequency division multiplexer (OFDM) to overcome the obstacles facing the PLC networks. OFDM employs Inverse Fast Fourier Transform (IFFT) for the purpose of converting frequency-domain signals into time-domain signals, and Fast Fourier Transform (FFT) that reverses the action of IFFT. This new technology has indeed contributed in the enhancement of the transmission environment. However, the boost offered by means of OFDM modulation scheme was considered to be insufficient especially when noise energy distributes among the orthogonal sub channels of the OFDM, which might result in information loss or information deformation at the OFDM receiving end. Hence, noise detection techniques have become essential and strongly relied upon in the OFDM systems.

Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg, South Africa
Department of Electrical Engineering, Higher colleges of Technology, Abu Dhabi, United Arab Emirates
Department of Electrical and Electronic Engineering Technology, University of Johannesburg, Johannesburg, South Africa

Contact IEEE to Subscribe

References

References is not available for this document.