Abstrato

Channel Estimation Using DFT Based Automoly Classifying Neural Network

Navneet Kaur, Ramanpreet Kaur

Channel Estimation refers to the evaluation of the performance of a channel through which the data is sent. MIMO OFDM(Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing) systems are quite effective in terms of sending bulk data to the receiving end but it suffers with few problems also, like high amplification to noise ratio, etc. In such a scenario estimation techniques defines the ways of optimization against the data packets send and received through the channel. DFT is one of the effective techniques which can be used for the channel estimation. This paper focuses on the DFT based channel estimation technique and its comparison with other existing estimation techniques like MMSE, LS. This paper also includes a suggestion for the future enhancement of channel estimation techniques. An optimization technique like bacterial foraging optimization has been suggested here. The current paper focuses on the existing scenarios of channel estimation techniques. The current paper also describes that the future aspects of channel estimation may include variation in MMSE techniques. This paper gives a review of the initialization of the neural network through which the estimation can further be enhanced.