.png){kind=icon}
Return
Deep learning based MIMO systems using open-loop autoencoder
.png){kind=icon}
OA
AI
DOI：10.1016/j.aeue.2023.154712.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article introduces two novel multiple input multiple output spatial division multiplexing (MIMO-SDM) systems based on deep learning techniques using bit-wise (BW) and symbol-wise (SW) open-loop autoencoders (AE), abbreviated as SWAE-MIMO and BWAE-MIMO. Based on the detection methods, we introduce three detectors at the receiver: Radio Transformation Network (RTN), Minimum Mean Square Error (MMSE) technique, and the combination of MMSE technique and neural network (MMSEnet), which can suppress co -channel interference (CCI) among received signal streams resulting in low bit error rates (BER). Furthermore, the considered systems are trained in a single phase to optimally synchronize the transmitter's and receiver's learning parameters, thus successfully exploiting spatial diversities to improve the error performance of conventional MIMO systems using the MMSE detector with different numbers of transmit-receive antennas. In a specific case, the BWAE-MIMO system using the RTN detector (BWAE-MIMO-RTN) achieves a BER comparable to that of the conventional MIMO system with a maximum likelihood detector (MIMO-ML) when both systems are equipped with two transmitting and receiving antennas.
Keywords:
Deep learning
Autoencoder
MIMO-SDM
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
A
IF:
3.2
Papers:
5.8K
Citations:
8.3K
Organization
Cited Papers
ShareSaveTrans effect and trans influence in ruthenium(II) tetraammines: Imidazole as a probe ligand.png)
Polyhedron
PolyhedronIF0
PREAI
ShareSave
ShareSaveShareSave
View more