MULTI USER DETECTION USING FUZZY LOGIC EMPOWERED ADAPTIVE BACK PROPAGATION NEURAL NETWORK S. Abbas * , M. Adnan Khan † , A. Ata *‡ , G. Ahmad * , A. Saeed § , N. Anwar ¶ Abstract: In Wireless communication, Multiple Input and Multiple Output (MIMO) systems have always been quite popular. Multicarrier systems are es- tablished along with different techniques of space-time coding to accomplish the demands of these systems. One of the most popular techniques is Multi-Carrier Code Division Multiple Access (MC-CDMA) with Alamouti’s Space-Time Block Codes (STBC). This article, proposed the Fuzzy Logic empowered Adaptive Back Propagation Neural Network (FLeABPNN) based Multi User Detection (MUD) system, which is used to determine the receiver weights of MC-CDMA with the scheme of two variations. The proposed FLeABPNN approach takes advantage of a neuro-fuzzy hybrid system which conglomerates the competences of both fuzzy logic and neural networks for multi-user detection. It is observed that due to the fuzzy logic-based learning rate, proposed FLeABPNN based receiver without rela- tionship & with relationship achieved the 3.04 × 10 -06 and 2.05 × 10 -06 Bit Error Rate (BER) respectively. The proposed FLeABPNN based receiver gives fast con- vergence rate & low BER as compared to other suboptimal published techniques like GA & LMS. It also observed that the Computational Complexity of the pro- posed FLeABPNN based MC-CDMA receiver is less then LMS based receiver up to 18 users, but higher than GA based receiver. Key words: MC-CDMA, FLeABPNN, MIMO, BER, ANN, STBC, MMSE, GA, LMS Received: January 22, 2019 DOI: 10.14311/NNW.2019.29.024 Revised and accepted: December 30, 2019 1. Introduction Multiple access techniques are very popular when it comes to real-time wireless communication systems. There are numerous varieties of multiple access tech- niques are Time Division Multiple Access (TDMA), Frequency Division Multiple * Sagheer Abbas, Gulzar Ahmad; School of Computer Science, NCBA&E, Lahore, E-Mail: dr.sagheer@ncbae.edu.pk, Gulzar.phd@ncbae.edu.pk † Muhammad Adnan Khan – corresponding author; Department of Computer Science, Lahore Garrison University, Lahore, E-Mail: madnankhan@lgu.edu.pk ‡ A. Ata; School of Computer Science, NCBA&E, Lahore & Dept of Computer Science, GCU, Lahore, E-mail: ayesha.ravian@gmail.com § Anwaar Saeed, Nida Anwar; Department of Computer Science, Virtual University, Lahore. E-Mail: anwarsaeed@vu.edu.pk, nidaanwar@vu.edu.pk c CTU FTS 2019 381