Abstract
The research work involves the channel estimation of the received signal transmitted using the OFDM multiplexing technique. The modulation is QAM used in which the received data is estimated by mapping the received signal in the IQ plane. Since the era of the new technology came, Deep Learning is one of them. Deep learning is used in the physical layer in wireless communication system. We are using Machine Learning to train the deep learning model based on the input received data and output actual data transmitted through OFDM channels. The project aims to modify and improvise the existing work done using the same data set. The performance measure is taken by two different measures BER (bit error rate) and RMSE (root mean square error). Impact of different scenarios like pilot numbers, number of epochs and SNR are considered. The comparison of the performance will be done at the end and experimental results will be illustrated.