Neural-fuzzy controller with heterogeneous neurons

Chih Chi Chang; Chung-Yong Tsai

doi:10.1109/IJCNN.1999.833411

Neural-fuzzy controller with heterogeneous neurons

Chih Chi Chang^*, Chung-Yong Tsai

^*Corresponding author for this work

Department of Electrical and Computer Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

For engineering applications, complex pre-calculations may be necessary to evaluate the fuzzy degree of a simple linguistic term in the conditional part. A situation in which if these pre-calculations are excluded from the system would make, it will be difficult to discriminate the physical meaning of the rule from the neural nets. Therefore, this work applies feature extraction to replace these pre-calculations. The proposed neural fuzzy system extracts features by heterogeneous neurons. The proposed system's structure and its advantages are described in detailed. A controller designed by the proposed neural fuzzy system is presented as well.

Original language	English
Pages	2245-2248
Number of pages	4
DOIs	https://doi.org/10.1109/IJCNN.1999.833411
State	Published - 1 Dec 1999
Event	International Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA Duration: 10 Jul 1999 → 16 Jul 1999

Conference

Conference	International Joint Conference on Neural Networks (IJCNN'99)
City	Washington, DC, USA
Period	10/07/99 → 16/07/99

Access to Document

10.1109/IJCNN.1999.833411

Cite this

@conference{409c19b1be1e44f3bdc0ec8731bd9f25,

title = "Neural-fuzzy controller with heterogeneous neurons",

abstract = "For engineering applications, complex pre-calculations may be necessary to evaluate the fuzzy degree of a simple linguistic term in the conditional part. A situation in which if these pre-calculations are excluded from the system would make, it will be difficult to discriminate the physical meaning of the rule from the neural nets. Therefore, this work applies feature extraction to replace these pre-calculations. The proposed neural fuzzy system extracts features by heterogeneous neurons. The proposed system's structure and its advantages are described in detailed. A controller designed by the proposed neural fuzzy system is presented as well.",

author = "Chang, {Chih Chi} and Chung-Yong Tsai",

year = "1999",

month = dec,

day = "1",

doi = "10.1109/IJCNN.1999.833411",

language = "English",

pages = "2245--2248",

note = "International Joint Conference on Neural Networks (IJCNN'99) ; Conference date: 10-07-1999 Through 16-07-1999",

}

TY - CONF

T1 - Neural-fuzzy controller with heterogeneous neurons

AU - Chang, Chih Chi

AU - Tsai, Chung-Yong

PY - 1999/12/1

Y1 - 1999/12/1

N2 - For engineering applications, complex pre-calculations may be necessary to evaluate the fuzzy degree of a simple linguistic term in the conditional part. A situation in which if these pre-calculations are excluded from the system would make, it will be difficult to discriminate the physical meaning of the rule from the neural nets. Therefore, this work applies feature extraction to replace these pre-calculations. The proposed neural fuzzy system extracts features by heterogeneous neurons. The proposed system's structure and its advantages are described in detailed. A controller designed by the proposed neural fuzzy system is presented as well.

AB - For engineering applications, complex pre-calculations may be necessary to evaluate the fuzzy degree of a simple linguistic term in the conditional part. A situation in which if these pre-calculations are excluded from the system would make, it will be difficult to discriminate the physical meaning of the rule from the neural nets. Therefore, this work applies feature extraction to replace these pre-calculations. The proposed neural fuzzy system extracts features by heterogeneous neurons. The proposed system's structure and its advantages are described in detailed. A controller designed by the proposed neural fuzzy system is presented as well.

UR - http://www.scopus.com/inward/record.url?scp=0033332126&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.1999.833411

DO - 10.1109/IJCNN.1999.833411

M3 - Paper

AN - SCOPUS:0033332126

SP - 2245

EP - 2248

T2 - International Joint Conference on Neural Networks (IJCNN'99)

Y2 - 10 July 1999 through 16 July 1999

ER -

Neural-fuzzy controller with heterogeneous neurons

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this