Deep Learning-Assisted Index Estimator for Generalized LED Index Modulation OFDM in Visible Light Communication

In this letter, we present the first attempt of active light-emitting diode (LED) indexes estimating for generalized LED index modulation optical orthogonal frequency-division multiplexing (GLIM-OFDM) in visible light communication (VLC) system by using deep learning (DL). Instead directly transmitted binary bit sequence with DL, LEDs at transmitter are estimated to maintain acceptable complexity and improve performance gain compared those previously proposed receivers. Particularly, a novel DL-based estimator termed estimator-based neural network (IE-DNN) is proposed, which can employ three different DNN structures fully connected layers (FCL) or convolution (CL) recover GLIM-OFDM system. By received signal dataset generated simulations, IE-DNN trained offline minimize error rate (IER); subsequently, model deployed estimation demodulation The simulation results show that significantly improves IER (BER) conventional detectors run time.