Study on modeling of multispectral emissivity and optimization algorithm

Chunling Yang; Yong Yu; Dongyang Zhao; Guoliang Zhao

doi:10.1109/TNN.2005.860837

Study on modeling of multispectral emissivity and optimization algorithm

Chunling Yang^*
, Yong Yu
, Dongyang Zhao
, Guoliang Zhao

^*Corresponding author for this work

School of Electrical Engineering and Automation

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

Target's spectral emissivity changes variously, and how to obtain target's continuous spectral emissivity is a difficult problem to be well solved nowadays. In this letter, an activation-function-tunable neural network is established, and a multistep searching method which can be used to train the model is proposed. The proposed method can effectively calculate the object's continuous spectral emissivity from the multispectral radiation information. It is a universal method, which can be used to realize on-line emissivity demarcation.

Original language	English
Pages (from-to)	238-242
Number of pages	5
Journal	IEEE Transactions on Neural Networks
Volume	17
Issue number	1
DOIs	https://doi.org/10.1109/TNN.2005.860837
State	Published - Jan 2006

Keywords

Neural networks
Optimization algorithm
Spectral emissivity
Tunable activation function

Access to Document

10.1109/TNN.2005.860837

Cite this

@article{e52ef83957ac420d9ca1e4e9b4ef2234,

title = "Study on modeling of multispectral emissivity and optimization algorithm",

abstract = "Target's spectral emissivity changes variously, and how to obtain target's continuous spectral emissivity is a difficult problem to be well solved nowadays. In this letter, an activation-function-tunable neural network is established, and a multistep searching method which can be used to train the model is proposed. The proposed method can effectively calculate the object's continuous spectral emissivity from the multispectral radiation information. It is a universal method, which can be used to realize on-line emissivity demarcation.",

keywords = "Neural networks, Optimization algorithm, Spectral emissivity, Tunable activation function",

author = "Chunling Yang and Yong Yu and Dongyang Zhao and Guoliang Zhao",

year = "2006",

month = jan,

doi = "10.1109/TNN.2005.860837",

language = "英语",

volume = "17",

pages = "238--242",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "IEEE Computational Intelligence Society",

number = "1",

}

TY - JOUR

T1 - Study on modeling of multispectral emissivity and optimization algorithm

AU - Yang, Chunling

AU - Yu, Yong

AU - Zhao, Dongyang

AU - Zhao, Guoliang

PY - 2006/1

Y1 - 2006/1

N2 - Target's spectral emissivity changes variously, and how to obtain target's continuous spectral emissivity is a difficult problem to be well solved nowadays. In this letter, an activation-function-tunable neural network is established, and a multistep searching method which can be used to train the model is proposed. The proposed method can effectively calculate the object's continuous spectral emissivity from the multispectral radiation information. It is a universal method, which can be used to realize on-line emissivity demarcation.

AB - Target's spectral emissivity changes variously, and how to obtain target's continuous spectral emissivity is a difficult problem to be well solved nowadays. In this letter, an activation-function-tunable neural network is established, and a multistep searching method which can be used to train the model is proposed. The proposed method can effectively calculate the object's continuous spectral emissivity from the multispectral radiation information. It is a universal method, which can be used to realize on-line emissivity demarcation.

KW - Neural networks

KW - Optimization algorithm

KW - Spectral emissivity

KW - Tunable activation function

UR - https://www.scopus.com/pages/publications/33144486080

U2 - 10.1109/TNN.2005.860837

DO - 10.1109/TNN.2005.860837

M3 - 文章

AN - SCOPUS:33144486080

SN - 1045-9227

VL - 17

SP - 238

EP - 242

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 1

ER -

Study on modeling of multispectral emissivity and optimization algorithm

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this