VLC Channel estimation for indoor environment using LSTM

Authors:

Abstract
In this paper, a visible light communication (VLC) indoor channel estimator was proposed using long-short term memory (LSTM). The proposed method of this paper is the use of a deep learning (DL) approach with an asymmetrically clipped optical-orthogonal frequency-division multiplexing (ACO-OFDM) optical modulation technique. The proposed estimator was evaluated using the bit error rate (BER) for different quadrature amplitude modulation (QAM) levels. i.e., 64-QAM, 128-QAM and 256-QAM. Moreover, we compared our results with Kalman filter (KF) estimator in the literature. Our model achieves better results compared to KF estimator in terms of BER.
Funding Information
  • King Fahd University of Petroleum and Minerals