Logo image
A Hybrid Fuzzy Logic-Neural Network Approach For Multi-path Separation Of Underwater Acoustic Signals
Conference proceeding

A Hybrid Fuzzy Logic-Neural Network Approach For Multi-path Separation Of Underwater Acoustic Signals

Abigail Lee-Leon, Chau Yuen, Dorien Herremans and IEEE
IEEE Vehicular Technology Conference, Vol.2019-, pp.1-5
IEEE Vehicular Technology Conference Proceedings
01/01/2019

Abstract

Science & Technology Technology Transportation Transportation Science & Technology
Underwater acoustic channels are generally recognized as one of the most difficult communication media in use today. One of the most important constraints of underwater communications is the chaotic acoustic propagation of the signals. The aim of a multi-path separator is to extract individual correlated signals from their mixtures. We present an algorithm, Tag Receiver, that is similar to the rake receiver, but interpreted from the neural network viewpoint. First, the received signal is split into frames. Next, the frames are tagged with a predicted number of multi-path in the framed segment via fuzzy logic on extracted audio features. Finally, the frame and the number of multi-path are inputted into a neural network, which separates the signals. The analysis of the proposed algorithm shows a 1.2dB improvement when bit error rate (BER) is 10 over the conventional rake receiver.

Metrics

1 Record Views

Details

Logo image