Paper Title
Channel Estimation In OFDM System Using Multi-Layered Perceptron Neural Network Combined With Artificial Bee Colony Algorithm

Abstract
For many modern wireless and telecommunications systems, Orthogonal Frequency Division Multiplexing (OFDM) is being used as a modulation technique. OFDM has been adopted for the cellular telecommunications standard LTE / LTE-A, also it has been chosen by other standards including WiMAX, Wi-Fi and many more. In this study, a multi-layered perceptron based neural network has been trained with Artificial Bee Colony (ABC) optimization algorithm for channel estimation of an OFDM system. The results of proposed algorithm (ABCNN) are compared with conventional channel estimators such as Least Square (LS) and Minimum Mean Square Error (MMSE) and also with conventional back propagation neural network (BPNN). In this work, mean square error (MSE) and bit error rate (BER) have been used to evaluate the performance of ABC-NN. The simulation results show that channel estimation based on proposed algorithm gives better performance as compared to LS algorithm and BP-NN without the need of channel statistics and noise information. Although MMSE algorithm performs better than ABC-NN for channel estimation of OFDM, ABC-NN is less complex and does not require channel state information in advance. Index Terms—OFDM, Channel Estimation, Neural Network, Artificial Bee Colony Optimization Algorithm