2020/01/31 by Shabnam Rezaei, Rezaei, Shabnam, Sofiène Affes +2 · 2 citations
Computer Science · Engineering · Mathematics · #Algorithm #Bit error rate #Blind Source Separation Techniques #Channel (broadcasting) #Computer science #Decoding methods #Detector #Electronic engineering #Engineering #Error Correcting Code Techniques #FOS: Computer and information sciences #FOS: Electrical engineering #Information Theory (cs.IT) #MIMO #MIMO-OFDM #Machine Learning (cs.LG) #Mathematics #Minimum mean square error #Modulation (music) #Orthogonal frequency-division multiplexing #Signal Processing (eess.SP) #Statistics #Telecommunications #Wireless Signal Modulation Classification #cs.IT #cs.LG #eess.SP #electronic engineering #information engineering #math.IT
paper · pdf · doi:10.48550/arxiv.2001.11643
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/01/31 · openalex publication_date 2020/01/31 · arxiv updated 2020/02/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we propose a multi-layer artificial neural network (ANN) that is trained with the Levenberg-Marquardt algorithm for use in signal detection over multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems, particularly those with low-resolution analog-to-digital converters (LR-ADCs). We consider a blind detection scheme where data symbol estimation is carried out without knowing the channel state information at the receiver (CSIR)---in contrast to classical algorithms. The main power of the proposed ANN-based detector (ANND) lies in its versatile use with any modulation scheme, blindly, yet without a change in its structure. We compare by simulations this new receiver with conventional ones, namely, the maximum likelihood (ML), minimum mean square error (MMSE), and zero-forcing (ZF), in terms of symbol error rate (SER) performance. Results suggest that ANND approaches ML at much lower complexity, outperforms ZF over the entire range of assessed signal-to-noise ratio (SNR) values, and so does it also, though, with the MMSE over different SNR ranges.