• Busineni VishnuVandana Kumari
• Dr. S. Narayana Reddy

The rapid development of wireless communication systems in future, where Filter bank multicarrier (FBMC) modulation is auspicious candidate modulation method with hopeful waveforms. Although FBMC system indirectly use channel estimation methods for orthogonal frequency-division multiplexing (OFDM) system because of it’s intrinsic inherent imaginary interference due to it’s non-orthogonal nature in the imaginary field, which is a barrier to bid multiple input multiple output (MIMO) with FBMC/OQAM. This paper proposes Deep Neural Network (DNN) based Deep learning channel estimation (DL-CE) and equalization to deal with imaginary interference. Channel State Information (CSI) and the method of constellation de-mapping learned by a DNN model and varied with frequency domain sequences are simplified equally to obtain binary bits directly. The proposed methodology is verified on the MATLAB software and simulation results shows DL-CE and other existing schemes performance on equalization and estimation with art performance in terms of bit error rate (BER).

Deep Neural Networks, FBMC, OQAM, channel estimation, equalizer, equalization

"AI-Based Approach for Optimal Channel Estimation and Equalization for FBMC/OQAM Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.p319-p323, May-2023, Available :http://www.jetir.org/papers/JETIR2305G44.pdf

"AI-Based Approach for Optimal Channel Estimation and Equalization for FBMC/OQAM Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppp319-p323, May-2023, Available at : http://www.jetir.org/papers/JETIR2305G44.pdf