Deakin University
Browse

File(s) under embargo

A theoretical analysis of continuous firing condition for pulse-coupled neural networks with its applications

journal contribution
posted on 2023-10-10, 05:22 authored by X Jin, P Zhang, Y He, Q Jiang, P Wang, Jingyu HouJingyu Hou, W Zhou, S Yao
The pulse-coupled neural network (PCNN) has become a popular biology-inspired model because of its remarkable performance, such as image fusion, segmentation, and recognition. Although the PCNN is an unsupervised neural network model, its parameters are often manually adjusted, which leads to the shortcomings of being time-consuming, verbose, and with bad consistency. Researchers have conducted work on the PCNN's neurodynamic analysis and parameter settings. However, most of these works were proposed for specific application areas, and there are no widely recognized and accepted methods or theories for PCNN parameter setting at present. Thus, how to reduce the difficulty of parameter setting based on neurodynamic analysis is a very important research area for applying PCNN. In this work, we proposed a general formulae of a continuous firing condition based on the dynamic analysis of PCNN neurons to avoid constructing an invalid model and to learn the neurons' firing characteristics. The results obtained from the proposed formulae were used to explore the usability of the PCNN parameter setting theory. We first utilized the pre-existing theory of the PCNN firing period to examine the rationality of our theory, and then we also introduce an image fusion method using our theory and whale optimization algorithm to verify our method and theory, besides, numerical tests and experiments on common images were also performed to verify our theory. Experimental results show that our method and theory is effective.

History

Journal

Engineering Applications of Artificial Intelligence

Volume

126

Article number

107101

Pagination

1-30

Location

Amsterdam, The Netherlands

ISSN

0952-1976

Language

eng

Issue

Part D

Publisher

Elsevier

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC