Probabilistic neural network based on neighbor statistic character and its application in automatic target recognition

Tianrong Liu, Dinggang Shen, Feihu Qi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Based on one of the improved probabilistic neural network models - FD0 (full domain optimum) neural network, the paper presented an idea of taking the effect of the 8 neighbors of every pix element into consideration in designing the convergent domain of the network. The activation function of the network was modified, thus, endowing the network with good stability and high running speed. The recognition capabilities of FD0 network and its improved version were compared in the simulation experiment. The result proves that the improved network is especially suitable for the recognition of targets with Gaussian noise.

Original languageEnglish
Pages (from-to)52-58
Number of pages7
JournalHongwai Yu Haomibo Xuebao/Journal of Infrared and Millimeter Waves
Volume14
Issue number1
Publication statusPublished - 1995 Feb 1
Externally publishedYes

Fingerprint

target recognition
statistics
random noise
activation

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

@article{6e6c9ce02c1b42a6b66b4b18db16a137,
title = "Probabilistic neural network based on neighbor statistic character and its application in automatic target recognition",
abstract = "Based on one of the improved probabilistic neural network models - FD0 (full domain optimum) neural network, the paper presented an idea of taking the effect of the 8 neighbors of every pix element into consideration in designing the convergent domain of the network. The activation function of the network was modified, thus, endowing the network with good stability and high running speed. The recognition capabilities of FD0 network and its improved version were compared in the simulation experiment. The result proves that the improved network is especially suitable for the recognition of targets with Gaussian noise.",
author = "Tianrong Liu and Dinggang Shen and Feihu Qi",
year = "1995",
month = "2",
day = "1",
language = "English",
volume = "14",
pages = "52--58",
journal = "Hongwai Yu Haomibo Xuebao/Journal of Infrared and Millimeter Waves",
issn = "1001-9014",
publisher = "Chinese Optical Society",
number = "1",

}

TY - JOUR

T1 - Probabilistic neural network based on neighbor statistic character and its application in automatic target recognition

AU - Liu, Tianrong

AU - Shen, Dinggang

AU - Qi, Feihu

PY - 1995/2/1

Y1 - 1995/2/1

N2 - Based on one of the improved probabilistic neural network models - FD0 (full domain optimum) neural network, the paper presented an idea of taking the effect of the 8 neighbors of every pix element into consideration in designing the convergent domain of the network. The activation function of the network was modified, thus, endowing the network with good stability and high running speed. The recognition capabilities of FD0 network and its improved version were compared in the simulation experiment. The result proves that the improved network is especially suitable for the recognition of targets with Gaussian noise.

AB - Based on one of the improved probabilistic neural network models - FD0 (full domain optimum) neural network, the paper presented an idea of taking the effect of the 8 neighbors of every pix element into consideration in designing the convergent domain of the network. The activation function of the network was modified, thus, endowing the network with good stability and high running speed. The recognition capabilities of FD0 network and its improved version were compared in the simulation experiment. The result proves that the improved network is especially suitable for the recognition of targets with Gaussian noise.

UR - http://www.scopus.com/inward/record.url?scp=0029241524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029241524&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0029241524

VL - 14

SP - 52

EP - 58

JO - Hongwai Yu Haomibo Xuebao/Journal of Infrared and Millimeter Waves

JF - Hongwai Yu Haomibo Xuebao/Journal of Infrared and Millimeter Waves

SN - 1001-9014

IS - 1

ER -