Orthogonal frequency multiplexing division based modulation recognition using deep belief network with tangent search optimization in wireless optic communication

doi:10.1007/s11082-023-05095-y

Orthogonal frequency multiplexing division based modulation recognition using deep belief network with tangent search optimization in wireless optic communication

2023-06-30

0

PRE

AI

DOI：10.1007/s11082-023-05095-y

Original

Original request for help

Save

Abstract

En 中文

Many important signal processing applications are made possible by automatic modulation classification (AMC). More advanced than traditional machine learning (ML) techniques connected to hand-crafted features, deep learning (DL) methods have recently been employed in modulation recognition. However, several conventional Road-based AMC methods have caused confusion amongst OFDM-based signals because to the differences in usable symbol lengths of OFDM schemes. This research creates a Modulation Recognition System for OFDM wireless optical communication using Tangent Search Optimisation with Deep Belief Networks (TSODBN-MRS). Using a feature extraction procedure based on the communication signals, the described TSODBN-MRS technique identifies and classes modulation signals in an OFDM communication system. The DBN model is used for modulation recognition, and the TSO method is used to improve recognition accuracy. The results of the experiments proved that the TSODBN-MRS model provides effective modulation classification performance and has exhibited improved performance with greater pf 99.95%.

Keywords:

OFDM signals

Wireless optical communication

Deep belief network

Modulation recognition

Tangent search algorithm

Orthogonal frequency multiplexing division based modulation recognition using deep belief network with tangent search optimization in wireless optic communication

Abstract

Journal

Organization