Compensatory fuzzy neural networks-based intelligent detection of abnormal neonatal cerebral Doppler ultrasound waveforms

Huseyin Seker; David H. Evans; Nizamettin Aydin; Ertugrul Yazgan

doi:10.1109/4233.945289

Compensatory fuzzy neural networks-based intelligent detection of abnormal neonatal cerebral Doppler ultrasound waveforms

Huseyin Seker^*, David H. Evans, Nizamettin Aydin, Ertugrul Yazgan

^*Corresponding author for this work

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

34 Citations (Scopus)

Abstract

Compensatory fuzzy neural networks (CFNN) without normalization, which can be trained with a backpropagation learning algorithm, is proposed as a pattern recognition technique for intelligent detection of Doppler ultrasound wave-forms of abnormal neonatal cerebral hemodynamics. Doppler ultrasound signals were recorded from the anterior cerebral arteries of 40 normal full-term babies and 14 mature babies with intracranial pathology. The features of normal and abnormal groups as inputs to pattern recognition algorithms were extracted from the maximum velocity waveforms by using principal component analysis. The proposed technique is compared with the CFNN with normalization and other pattern recognition techniques applied to Doppler ultrasound signals from various arteries. The results show that the proposed method is superior to the others, and can be a powerful technique to be used in analyzing Doppler ultrasound signals from various arteries.

Original language	English
Pages (from-to)	187-194
Number of pages	8
Journal	IEEE Transactions on Information Technology in Biomedicine
Volume	5
Issue number	3
DOIs	https://doi.org/10.1109/4233.945289
Publication status	Published - Sept 2001
Externally published	Yes

Funding

Manuscript received March 13, 2001. This work was supported by the British Council and The Scientific and Technical Research Council of Turkey. H. Seker is with the Biomedical Computing Research Group, School of Mathematical and Information Sciences, Coventry University, Coventry CV1 5FB, U.K. (e-mail: [email protected]). D. H. Evans is with the Department of Medical Physics, Leicester Royal Infirmary, Leicester LE1 5WW, U.K. (e-mail: [email protected]). N. Aydin is with the Department of Electronics and Electrical Engineering, University of Edinburgh, Edinburgh EH9 3JL, Scotland (e-mail: [email protected]). E. Yazgan is with the Department of Electronics Engineering, Istanbul Technical University, Istanbul, Turkey (e-mail: [email protected]). Publisher Item Identifier S 1089-7771(01)04575-7.

Funders	Funder number
British Council
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

Backpropagation learning
Blood-flow velocity
Doppler ultrasound
Fuzzy neural networks
Neonatal cerebral arteries
Pattern recognition
Principal component analysis

Access to Document

10.1109/4233.945289

Cite this

@article{46146081a8a94edfa03578ff1849c84f,

title = "Compensatory fuzzy neural networks-based intelligent detection of abnormal neonatal cerebral Doppler ultrasound waveforms",

abstract = "Compensatory fuzzy neural networks (CFNN) without normalization, which can be trained with a backpropagation learning algorithm, is proposed as a pattern recognition technique for intelligent detection of Doppler ultrasound wave-forms of abnormal neonatal cerebral hemodynamics. Doppler ultrasound signals were recorded from the anterior cerebral arteries of 40 normal full-term babies and 14 mature babies with intracranial pathology. The features of normal and abnormal groups as inputs to pattern recognition algorithms were extracted from the maximum velocity waveforms by using principal component analysis. The proposed technique is compared with the CFNN with normalization and other pattern recognition techniques applied to Doppler ultrasound signals from various arteries. The results show that the proposed method is superior to the others, and can be a powerful technique to be used in analyzing Doppler ultrasound signals from various arteries.",

keywords = "Backpropagation learning, Blood-flow velocity, Doppler ultrasound, Fuzzy neural networks, Neonatal cerebral arteries, Pattern recognition, Principal component analysis",

author = "Huseyin Seker and Evans, {David H.} and Nizamettin Aydin and Ertugrul Yazgan",

year = "2001",

month = sep,

doi = "10.1109/4233.945289",

language = "English",

volume = "5",

pages = "187--194",

journal = "IEEE Transactions on Information Technology in Biomedicine",

issn = "1089-7771",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Compensatory fuzzy neural networks-based intelligent detection of abnormal neonatal cerebral Doppler ultrasound waveforms

AU - Seker, Huseyin

AU - Evans, David H.

AU - Aydin, Nizamettin

AU - Yazgan, Ertugrul

PY - 2001/9

Y1 - 2001/9

N2 - Compensatory fuzzy neural networks (CFNN) without normalization, which can be trained with a backpropagation learning algorithm, is proposed as a pattern recognition technique for intelligent detection of Doppler ultrasound wave-forms of abnormal neonatal cerebral hemodynamics. Doppler ultrasound signals were recorded from the anterior cerebral arteries of 40 normal full-term babies and 14 mature babies with intracranial pathology. The features of normal and abnormal groups as inputs to pattern recognition algorithms were extracted from the maximum velocity waveforms by using principal component analysis. The proposed technique is compared with the CFNN with normalization and other pattern recognition techniques applied to Doppler ultrasound signals from various arteries. The results show that the proposed method is superior to the others, and can be a powerful technique to be used in analyzing Doppler ultrasound signals from various arteries.

AB - Compensatory fuzzy neural networks (CFNN) without normalization, which can be trained with a backpropagation learning algorithm, is proposed as a pattern recognition technique for intelligent detection of Doppler ultrasound wave-forms of abnormal neonatal cerebral hemodynamics. Doppler ultrasound signals were recorded from the anterior cerebral arteries of 40 normal full-term babies and 14 mature babies with intracranial pathology. The features of normal and abnormal groups as inputs to pattern recognition algorithms were extracted from the maximum velocity waveforms by using principal component analysis. The proposed technique is compared with the CFNN with normalization and other pattern recognition techniques applied to Doppler ultrasound signals from various arteries. The results show that the proposed method is superior to the others, and can be a powerful technique to be used in analyzing Doppler ultrasound signals from various arteries.

KW - Backpropagation learning

KW - Blood-flow velocity

KW - Doppler ultrasound

KW - Fuzzy neural networks

KW - Neonatal cerebral arteries

KW - Pattern recognition

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=0035437751&partnerID=8YFLogxK

U2 - 10.1109/4233.945289

DO - 10.1109/4233.945289

M3 - Article

C2 - 11550840

AN - SCOPUS:0035437751

SN - 1089-7771

VL - 5

SP - 187

EP - 194

JO - IEEE Transactions on Information Technology in Biomedicine

JF - IEEE Transactions on Information Technology in Biomedicine

IS - 3

ER -

Compensatory fuzzy neural networks-based intelligent detection of abnormal neonatal cerebral Doppler ultrasound waveforms

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this