Complex-Valued Phase Transmittance RBF Neural Networks for Massive MIMO-OFDM Receivers

Area of Science:

• Electrical Engineering
• Computer Science
• Wireless Communications

Background:

• Multi-input Multi-output (MIMO) transmission enhances spectral efficiency in wireless networks.
• Designing cost-effective MIMO receivers with high performance is a significant challenge.
• Maximum Likelihood (ML) detection offers superior performance but suffers from high computational complexity.

Purpose of the Study:

• To propose a novel MIMO scheme employing a practical decoding algorithm.
• To introduce a Phase Transmittance Radial Basis Function (PTRBF) neural network for MIMO decoding.
• To evaluate the performance and complexity of the proposed PTRBF-based MIMO scheme.

Main Methods:

• Development of a novel MIMO decoding algorithm utilizing a PTRBF neural network.
• Simulation of the proposed scheme within MIMO-OFDM systems.
• Performance evaluation under 5G wireless Rayleigh fading channels.
• Comparison with existing reference techniques, including Maximum Likelihood (ML) detection.

Main Results:

• The proposed PTRBF-based MIMO scheme demonstrates improved receiver performance in certain practical scenarios.
• The novel scheme achieves lower computational complexity compared to ML decoding.
• The PTRBF algorithm enhances the applicability of MIMO systems by balancing performance and complexity.

Conclusions:

• The PTRBF neural network offers a feasible and efficient solution for MIMO decoding.
• This approach presents a practical alternative to computationally intensive MIMO detection methods.
• The proposed scheme holds significant potential for advancing 5G wireless communication systems.