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 waveforms 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.

Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network

“…The problem of fuzzy clustering is to find the optimum membership matrix U. The most widely used objective function for fuzzy clustering is the weighted within-groups sum of squared errors J m , which is used to define the following constrained optimisation problem Dazzi et al, 2001;De et al, 2002;Fan et al, 2003;Jang et al, 1997;Li et al, 2002;Liao et al, 2003;Meesad & Yen, 2000;Pektatlı et al, 2003;Seker et al, 2001;Zhang & Kandel, 1998) …”

“…The matrix A is commonly selected as the identity matrix, leading to Euclidean distance and, consequently, to spherical clusters. Fuzzy partitions are carried out using the fuzzy c-means (FCM) algorithm through an iterative optimisation of (Fan et al, 2003;Li et al, 2002;Liao et al, 2003;Jang et al, 1997;Seker et al, 2001;Pektatlı et al, 2003;Zhang & Kandel, 1998) according to the following steps (Jang et al, 1997):…”

An efficient quantum neuro-fuzzy classifier based on fuzzy entropy and compensatory operation

“…Many researchers (Ouyang and Lee 1999;Seker et al 2001;Lin and Ho 2003;Lin and Chen 2003) have used the compensatory operation in fuzzy systems successfully.…”

A compensation-based recurrent fuzzy neural network for dynamic system identification

“…Zhang and Kandel [11] proposed more extensive compensatory operations based on the pessimistic operation and the optimistic operation. Recently, many researchers [12][13][14] have used the compensatory operation on fuzzy systems successfully. Therefore, in this paper, we propose a fuzzy neural network model that cannot only adaptively adjust fuzzy membership functions but can also dynamically optimize the adaptive fuzzy operators.…”