An Enhanced Approach of MIMO-OFDM Data Transfer by Varying User Location Optimized by Machine and AI Learning

Objectives: Orthogonal Frequency Division Multiplexing (OFDM) was designed in order to increase the data transfer rate in a channel. Furthermore to cope up with the demand of the user, Multiple Inputs Multiple Output (MIMO) concepts were introduced to it. Methods/Statistical Analysis: This work has taken the existing architecture to the next level. It presents a solution to a problem in which the user changes its location rapidly and then attempts to transfer the data from one end to another. Users have been divided into regions, MIMO OFDM architecture has been used to transfer the data. The data to send have been optimized with a combination of natural and swarm intelligence technique and then finally classified with Artificial Intelligence algorithm to make the transfer smoother. The process is judged by mean square error and bit error rate. Findings: This research has optimized data transfer process and uses the channel well. Application/Improvements: The result has shown that the proposed algorithm has put an important impact in lessening both MSE and BER.