Deep learning-based detection scheme for visible light communication with generalized spatial modulation.

Area of Science:

• Optical Communications
• Machine Learning
• Signal Processing

Background:

• Visible Light Communication (VLC) systems offer high bandwidth potential.
• Generalized Spatial Modulation (GenSM) enhances VLC system capacity.
• Conventional detection schemes in VLC systems face performance limitations.

Purpose of the Study:

• To propose a deep learning-based detection scheme for VLC systems employing GenSM.
• To enhance the efficiency and accuracy of signal detection in GenSM-VLC systems.
• To evaluate the performance of the proposed deep learning scheme against conventional methods.

Main Methods:

• A deep neural network (DNN) architecture was designed for signal detection.
• Signal processing modules from conventional schemes were integrated into the DNN.
• The DNN was trained offline to extract information bits from received signals.
• Performance was evaluated through simulations comparing error rates and complexity.

Main Results:

• The proposed deep learning scheme achieved superior detection error performance compared to conventional schemes.
• The integrated DNN efficiently extracts information bits from received signals.
• The scheme demonstrates effectiveness for VLC systems utilizing GenSM.

Conclusions:

• Deep learning offers a promising approach for advanced signal detection in VLC systems.
• The proposed GenSM-VLC detection scheme provides significant performance gains.
• This method represents an efficient and effective solution for future VLC applications.