Signal Processing Using Octonionic Modules – a Path Towards a New Computational Intelligence Model

Authors

  • Wiesław Citko Gdynia Maritime University
  • Wiesław Sienko Gdynia Maritime University

Abstract

This study proposes a modular structure designed for pattern and word sequence recognition. The developed structure is based on an extended Hopfield neural network. The architecture of the word sequence recognition system employs octonionic modules, which are implemented as transversal filter banks. The structure can be used to recognize word sequences  containing data represented as both real and complex numbers. The proposed procedure for synthesizing the word sequence recognition system may be useful for the development of computational intelligence systems.

Additional Files

Published

2026-02-17

Issue

Section

Signals, Circuits, Systems