Deep Energy Autoencoder for Noncoherent Multicarrier MU-SIMO Systems

  title={Deep Energy Autoencoder for Noncoherent Multicarrier MU-SIMO Systems},
  author={Thien van Luong and Youngwook Ko and Ngo Anh Vien and Michail Matthaiou and Hien Quoc Ngo},
  journal={IEEE Transactions on Wireless Communications},
We propose a novel deep energy autoencoder (EA) for noncoherent multicarrier multiuser single-input multiple-output (MU-SIMO) systems under fading channels. In particular, a single-user noncoherent EA-based (NC-EA) system, based on the multicarrier SIMO framework, is first proposed, where both the transmitter and receiver are represented by deep neural networks (DNNs), known as the encoder and decoder of an EA. Unlike existing systems, the decoder of the NC-EA is fed only with the energy… 

Model-Driven Deep Learning for Non-Coherent Massive Machine-Type Communications

A deep learning modified AMP network (DL-mAMPnet) that enhances the detection performance by effectively exploiting the pilot activity correlation and can outperform traditional algorithms in terms of the symbol error rate performance.

Real-time Outdoor Localization Using Radio Maps: A Deep Learning Approach

A convolutional, end-to-end trained neural network for the localization task, which is able to estimate the position of a user from the received signal strength of a small number of Base Stations, which can localize users with state-of-the-art accuracy and enjoys high robustness to inaccuracies in the estimations of radio maps.

Deep Learning Algorithm for Maximizing the Spectral Efficiency of Wireless Systems

  • E. Bobrov
  • Computer Science
    Pattern Recognition and Image Analysis
  • 2022
The construction of precoding matrices and their distribution for the SE objective function using the VAE and CVAE methods is described in a publication for the first time.

Deep Neural Network-Based Detector for Single-Carrier Index Modulation NOMA

A DNN-based detector whose structure relies on the model-based SIC for jointly detecting both M-ary symbols and index bits of all users after trained with sufficient simulated data is proposed and achieves near-optimal error performance and significantly reduced runtime complexity in comparison with the existing hand-crafted detectors.

Deep Learning-Based Signal Detection for Dual-Mode Index Modulation 3D-OFDM

A deep neural network is proposed at the receiver to jointly and reliably detect both symbols and index bits of DM-IM-3D-OFDM under Rayleigh fading channels in a data-driven manner and achieves near-optimal performance at significantly lower runtime complexity compared to the conventional maximum likelihood detector.

Generalized BER of MCIK-OFDM with imperfect CSI: selection combining GD versus ML receivers

A generalized framework to derive the BER for both the low-complexity greedy detector (GD) and maximum likelihood (ML) detector is proposed to provide opportunities for using the GD instead of the ML under each specific CSI uncertainty, which depend on the number of receiver antennas and the M-ary modulation size.

Enhancing diversity of OFDM with joint spread spectrum and subcarrier index modulations

This paper proposes a novel spread spectrum and sub-carrier index modulation (SS-SIM) scheme, which is integrated to orthogonal frequency division multiplexing (OFDM) framework to enhance the

Deep Learning Based Successive Interference Cancellation for the Non-Orthogonal Downlink

A deep learning-aided SIC detector termed SICNet is proposed, which replaces the interference cancellation blocks of SIC by deep neural networks (DNNs), which reliably detects the superimposed symbols in the downlink of non-orthogonal systems while being less sensitive to CSI uncertainty than its model-based counterpart.

Machine Learning and Optimization Algorithms in Applied Problems of Wireless Cellular Communications

  • E. Bobrov
  • Computer Science
    Moscow University Computational Mathematics and Cybernetics
  • 2022
A review of the literature shows certain algorithms needed for MIMO cellular communication systems have not yet been developed.

Noncoherent OFDM-IM and Its Performance Analysis

  • Jinho Choi
  • Business
    IEEE Transactions on Wireless Communications
  • 2018
A closed-form expression is derived for the probability of index error when no transmit diversity is considered under frequency-selective Rayleigh fading and an upper-bound is derived when the transmit diversity scheme is employed.

An Introduction to Deep Learning for the Physical Layer

  • Tim O'SheaJ. Hoydis
  • Computer Science
    IEEE Transactions on Cognitive Communications and Networking
  • 2017
A fundamental new way to think about communications system design as an end-to-end reconstruction task that seeks to jointly optimize transmitter and receiver components in a single process is developed.

Scaling Laws for Noncoherent Energy-Based Communications in the SIMO MAC

It is shown that, for general channel fading statistics, the performance of the considered one-shot multiuser noncoherent scheme is the same, in a scaling law sense, as that of the optimal coherent scheme exploiting perfect channel knowledge and coding across time.

Deep learning in neural networks: An overview

Deep Learning-Based Detector for OFDM-IM

A novel DL-based detector termed as DeepIM is proposed, which employs a deep neural network with fully connected layers to recover data bits in an OFDM-IM system, which can achieve a near-optimal BER with a lower runtime than existing hand-crafted detectors.

Performance of ED-Based Non-Coherent Massive SIMO Systems in Correlated Rayleigh Fading

The analytical results demonstrate the adverse impact of channel correlation on the error probability, which can be attributed to the fact that channel correlation reduces the degrees of freedom.

Spread OFDM-IM With Precoding Matrix and Low-Complexity Detection Designs

A new spread orthogonal frequency division multiplexing with index modulation (S-OFDM-IM), which employs precoding matrices such as Walsh-Hadamard and Zadoff-Chu matrices to increase the transmit diversity, and derive the bit error probability (BEP) to provide an insight into the diversity and coding gains.

Unsupervised Deep Learning for MU-SIMO Joint Transmitter and Noncoherent Receiver Design

This letter aims to handle the joint transmitter and noncoherent receiver optimization for multiuser single-input multiple-output (MU-SIMO) communications through unsupervised deep learning. It is

Optimal ASK Levels for Channel Magnitude Based Diversity Reception in Rayleigh Fading

Analytical results on the optimization of the transmit symbol amplitude levels to minimize the SEP subject to a total energy constraint for high SNR and large number of receive diversity branches for both the ED and the WENVD receivers are presented.

Channel Agnostic End-to-End Learning Based Communication Systems with Conditional GAN

An end-to-end wireless communication system in which DNNs are employed for all signal-related functionalities, including encoding, decoding, modulation, and equalization is developed, in which accurate instantaneous channel transfer function is necessary to compute the gradient of the DNN representing.