Deep Learning-Based Detector for OFDM-IM

Abstract

This letter presents the first attempt of exploiting deep learning (DL) in the signal detection of orthogonal frequency division multiplexing with index modulation (OFDM-IM) systems. Particularly, we propose a novel DL-based detector termed as DeepIM, which employs a deep neural network with fully-connected layers to recover data bits in an OFDM-IM system. To enhance the performance of DeepIM, the received signal and channel vectors are pre-processed based on the domain knowledge before entering the network. Using datasets collected by simulations, DeepIM is first trained offline to minimize the bit error rate (BER) and then the trained model is deployed for the online signal detection of OFDM-IM. Simulation results show that DeepIM can achieve a near-optimal BER with a lower runtime than existing hand-crafted detectors.

Deep-Learning-Aided Joint Channel Estimation and Data Detection for Spatial Modulation

“…Additionally, we can see from Table 2 that the MAT-LAB runtime [36,37] of the maximum-likelihood approach increases significantly when either N t or M 2 increases. By contrast, when DNN-aided approaches are employed, the MATLAB runtime can be greatly reduced and remains similar as the increase of modulation order N t or M 2 , since the DNN structure allows the parallel operations in MAT-LAB, significantly reducing the communication latency.…”

Deep Learning-Aided Multicarrier Systems

“…DL [12] has recently been applied to numerous aspects in the field of communications, in particular the physical layer issues. For example, deep neural networks (DNNs) were employed for efficient signal detection of OFDM [13] and OFDM-IM [14], especially under channel impairments. In [15], a deep autoencoder (AE) architecture was adopted to reduce the peak-to-average power ratio (PAPR) of OFDM.…”

Deep Energy Autoencoder for Noncoherent Multicarrier MU-SIMO Systems

“…Recently, DL based on deep neural networks (DNNs) [12] has emerged as a powerful tool to address diverse problems in physical-layer wireless communications. For instance, in [19], channel estimation and signal detection of OFDM systems were performed by DNNs, while in [20] a DL-based detector, called as DeepIM, was proposed for OFDM-IM. Particularly, in [21], a novel end-to-end learning-based system was proposed, where both the transmitter and receiver are represented by DNNs, which are known as the encoder and decoder of an AE.…”