• JALADI VIVEK

Multi-input multi-output (MIMO) systems have been researched for wireless networks to boost transmission reliability. However, one of the main issues that need to be addressed for optimal information transfer in MIMO is channel estimation. Though viable techniques for estimation are being presented, more investigation needs to be undertaken to boost estimation precision. Thus, for accurate channel estimation, this research introduces an innovative machine learning (ML) approach called bacterial foraging search-joint boosted recurrent network (BFS-BRN). Initially, every pilot block's channel outputs are computed with the least square channel estimator. Subsequently, the recommended BFS-BRN algorithm is trained to forecast the present channel response. The BFS optimization technique is used to maximize the functionality of the BRN. By adjusting the duration of the pilot series and the number of antennas, the suggested channel estimation scheme effectiveness is evaluated to figure out the measures such as mean squared error and bit-error-rate (BER and MSE). The suggested BFS-BRN scheme's complexity assessment is compared with previous methods.

Machine learning (ML), transmission reliability, channel estimation, bacterial foraging search-joint boosted recurrent network (BFS-BRN), multiple-input multiple-output (MIMO)

"Machine Learning Approaches for Channel Estimation in MIMO Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.f585-f590, April-2024, Available :http://www.jetir.org/papers/JETIR2404563.pdf

"Machine Learning Approaches for Channel Estimation in MIMO Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppf585-f590, April-2024, Available at : http://www.jetir.org/papers/JETIR2404563.pdf