Deep Learning Based Fast Multiuser Detection for Massive Machine-Type Communication

Abstract

Massive machine-type communication (MTC) with sporadically transmitted small packets and low data rate requires new designs on the PHY and MAC layer with light transmission overhead. Compressive sensing based multiuser detection (CS-MUD) is designed to detect active users through random access with low overhead by exploiting sparsity, i.e., the nature of sporadic transmissions in MTC. However, the high computational complexity of conventional sparse reconstruction algorithms prohibits the implementation of CS-MUD in real communication systems. To overcome this drawback, in this paper, we propose a fast Deep learning based approach for CS-MUD in massive MTC systems. In particular, a novel block restrictive activation nonlinear unit, is proposed to capture the block sparse structure in wide-band wireless communication systems (or multi-antenna systems). Our simulation results show that the proposed approach outperforms various existing algorithms for CS-MUD and allows for ten-fold decrease of the computing time.

Convolutional Neural Network-Based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis

“…In [33], a new block activation unit with the block size of six has been proposed to handle the block-sparse vector in wideband wireless communication systems. Inspired by it, we use two 7 × 7 convolutional layers in CsiNet+ to replace the first 3 × 3 convolution layer of CsiNet at the encoder.…”

Detection Techniques for Massive Machine-Type Communications: Challenges and Solutions

“…The work in [55] compares different approaches of the Hierarchical Hard Thresholding Pursuit (HiHTP) algorithm. Machine learning approaches are also suggested, as in [56]- [60].…”

“…Machine learning BRNN [56] • Consists in a feedforward neural network with interleaved fully connected layers and non-linear transformation layers. • A batch normalization is added for initialization and residual connection is used to avoid vanishing/exploding gradients.…”

“…By implicitly reproducing the behavior of the channel with the LSTM algorithm, this approach considers the greedy SISD algorithm [40] to perform activity and data detection. On the other hand, the works in [56] and [59] uses the DL approach to explicitly estimate the channels. Using the metadata vectors as the training set, both works map each received vector y as an input and considers as the loss function the mean square error (MSE) ĥ DNN − h 2 2 , whereĥ DNN is the estimated channel gain and h is the known channel gain in the training set.…”

User activity detection for massive Internet of things with an improved residual convolutional neural network

“…Particularly, it is revealed in Reference 21 that deep learning can achieve better performance in user detection and channel estimation for IoT networks with a new structure of block‐restrict neural network (BRNN). The work in Reference 21 reveals the fact that, through sufficient training, deep learning has advantages on both performance and computational complexity compared against OMP and other CS methods, and the computation time is reduced more than an order of magnitude. However, although deep learning shows the potential in this problem, currently the network structure is simply a fully connected network, which can not take full advantage of the power of the deep neural network.…”