Engin Avci

Comparison of wavelet families for texture classification by using wavelet packet entropy adaptive network based fuzzy inference system

Recently, significant of the robust texture image classification has increased. The texture image classification is used for many areas such as medicine image processing, radar image processing, etc. In this study, a new method for invariant pixel regions texture image classification is presented. Wavelet packet entropy adaptive network based fuzzy inference system (WPEANFIS) was developed for classification of the twenty 512x512 texture images obtained from Brodatz image album. There, sixty 32x32 image regions were randomly selected (overlapping or non-overlapping) from each of these 20 images. Thirty of these image regions and other 30 of these image regions are used for training and testing processing of the WPEANFIS, respectively. In this application study, Daubechies, biorthogonal, coiflets, and symlets wavelet families were used for wavelet packet transform part of the WPEANFIS algorithm, respectively. In this way, effects to correct texture classification performance of these wavelet families were compared. Efficiency of WPEANFIS developed method was tested and a mean %93.12 recognition success was obtained.

Speech recognition using a wavelet packet adaptive network based fuzzy inference system

Abstract In this paper, an expert speech recognition system is presented. This paper especially deals with the combination of feature extraction and classification for real speech signals. A Wavelet packet adaptive network based fuzzy inference system (WPANFIS) model is developed in this study. WPANFIS consists of two layers: wavelet packet and adaptive network based fuzzy inference system. The wavelet packet layer is used for adaptive feature extraction in the time–frequency domain and is composed of wavelet packet decomposition and wavelet packet entropy. The performance of the developed system is evaluated by using noisy speech signals. Test results showing the effectiveness of the proposed speech recognition system are presented in the paper. The rate of correct classification is about 92% for the sample speech signals.

Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using hybrid genetic algorithm-support vector machines: HGASVM

The support vector machines is a new technique for many pattern recognition areas. The digital modulation classification is one of these pattern recognition areas. In SVM training, the kernels, kernel parameters, and feature selection have very important roles for SVM classification accuracy. Therefore, most appropriates of these kernel types, kernel parameters and features should be used for SVM training. In this study, a hybrid of genetic algorithm-support vector machines (HGASVM) approach is presented in digital modulation classification area for increasing the support vector machines (SVM) classification accuracy. This HGASVM approach proposed in this paper selects of the optimal kernel function type, kernel function parameter, most appropriate wavelet filter type for problem, wavelet entropy parameter, and soft margin constant C penalty parameter of support vector machines (SVM) classifier. The classification accuracy of this HGASVM approach is tried by using real digital modulation dataset and compared with the SVMs, which has kernel function type, kernel function parameter, wavelet filter type, wavelet entropy parameter, and C parameter are randomly selected. Here, discrete wavelet transform (DWT) and adaptive wavelet entropy are used in feature extraction stage of this HGASVM approach. The digital modulation types used in this study are ASK-2, ASK-4, ASK-8, FSK-2, FSK-4, FSK-8, PSK-2, PSK-4, and PSK-8. The experimental studies conducted in this study show that the classification accuracy of this HGASVM approach is more superior than SVM, which has constant parameters.

An expert Discrete Wavelet Adaptive Network Based Fuzzy Inference System for digital modulation recognition

This paper presents a comparative study of implementation of feature extraction and classification algorithms based on discrete wavelet decompositions and Adaptive Network Based Fuzzy Inference System (ANFIS) for digital modulation recognition. Here, in first stage, 20 different feature extraction methods are generated by separately using Daubechies, Biorthogonal, Coiflets, Symlets wavelet families. In second stage, the performance comparison of these feature extraction methods is performed by using a new Expert Discrete Wavelet Adaptive Network Based Fuzzy Inference System (EDWANFIS). The digital modulated signals used in this experimental study are ASK8, FSK8, PSK8, QASK8. EDWANFIS structure consists of two parts. The first part is Discrete Wavelet Transform (DWT)-adaptive wavelet entropy and Adaptive Network Based Fuzzy Inference System for Automatic Digital Modulation Recognition (ADMR). The performance of this comparison system is evaluated by using total 800 digital modulated signals for each of these feature extraction methods. The performance comparison of these features extraction methods and the advantages and disadvantages of the methods are examined.

Intelligent target recognition based on wavelet packet neural network

In this paper, an intelligent target recognition system is presented for target recognition from target echo signal of High Resolution Range (HRR) radars. This paper especially deals with combination of the feature extraction and classification from measured real target echo signal waveforms using X-band pulse radar. Because of this, a wavelet packet neural network model developed by us is used. The model consists of two layers: wavelet and multi-layer perceptron. The wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of wavelet packet decomposition and wavelet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the developed system has been evaluated in noisy radar target echo (RTE) signals. The test results showed that this system was effective in detecting real RTE signals. The correct classification rate was about 95% for used target subjects.

An expert system based on Wavelet Neural Network-Adaptive Norm Entropy for scale invariant texture classification

Nowadays, texture classification becomes more important, as the computational power increases. The most important hardness of texture image analysis in the past was the deficiency of enough tools to characterize variety scales of texture images effectively. Recently, multi-resolution analysis such as Gabor filters, wavelet decompositions provide very good multi-resolution analytical tools for different scales of texture analysis and classification. In this paper, a Wavelet Neural Network based on Adaptive Norm Entropy (WNN-ANE) expert system is used for increasing the effectiveness of the scale invariant feature extraction algorithm (Best Wavelet Statistical Features (WSF)-Wavelet Co-occurrence Features (WCF)). Efficiently of proposed method was proved using exhaustive experiments conducted with Brodatz texture images.

An intelligent diagnosis system based on principle component analysis and ANFIS for the heart valve diseases

In this paper, an intelligent diagnosis system based on principle component analysis (PCA) and adaptive network based on fuzzy inference system (ANFIS) for the heart valve disease is introduced. This intelligent system deals with combination of the feature extraction and classification from measured Doppler signal waveforms at the heart valve using the Doppler ultrasound (DHS). Here, the wavelet entropy is used as features. This intelligent system has three phases. In pre-processing phase, the data acquisition and pre-processing for DHS signals are performed. In feature extraction phase, the feature vector is extracted by calculating the 12 wavelet entropy values for per DHS signal and dimension of Doppler signal dataset, which are 12 features, is reduced to 6 features using PCA. In classification phase, these reduced wavelet entropy features are given to inputs ANFIS classifier. The correct diagnosis performance of the PCA-ANFIS intelligent system is calculated in 215 samples. The classification accuracy of this PCA-ANFIS intelligent system was 96% for normal subjects and 93.1% for abnormal subjects.

A new optimum feature extraction and classification method for speaker recognition: GWPNN

Abstract Speech and speaker recognition is an important topic to be performed by a computer system. In this paper, an expert speaker recognition system based on optimum wavelet packet entropy is proposed for speaker recognition by using real speech/voice signal. This study contains both the combination of the new feature extraction and classification approach by using optimum wavelet packet entropy parameter values. These optimum wavelet packet entropy values are obtained from measured real English language speech/voice signal waveforms using speech experimental set. A genetic-wavelet packet-neural network (GWPNN) model is developed in this study. GWPNN includes three layers which are genetic algorithm, wavelet packet and multi-layer perception. The genetic algorithm layer of GWPNN is used for selecting the feature extraction method and obtaining the optimum wavelet entropy parameter values. In this study, one of the four different feature extraction methods is selected by using genetic algorithm. Alternative feature extraction methods are wavelet packet decomposition, wavelet packet decomposition – short-time Fourier transform, wavelet packet decomposition – Born–Jordan time–frequency representation, wavelet packet decomposition – Choi–Williams time–frequency representation. The wavelet packet layer is used for optimum feature extraction in the time–frequency domain and is composed of wavelet packet decomposition and wavelet packet entropies. The multi-layer perceptron of GWPNN, which is a feed-forward neural network, is used for evaluating the fitness function of the genetic algorithm and for classification speakers. The performance of the developed system has been evaluated by using noisy English speech/voice signals. The test results showed that this system was effective in detecting real speech signals. The correct classification rate was about 85% for speaker classification.

A new intelligent diagnosis system for the heart valve diseases by using genetic-SVM classifier

In this study, an intelligent system based on genetic-support vector machines (GSVM) approach is presented for classification of the Doppler signals of the heart valve diseases. This intelligent system deals with combination of the feature extraction and classification from measured Doppler signal waveforms at the heart valve using the Doppler ultrasound. GSVM is used in this study for diagnosis of the heart valve diseases. The GSVM selects of most appropriate wavelet filter type for problem, wavelet entropy parameter, the optimal kernel function type, kernel function parameter, and soft margin constant C penalty parameter of support vector machines (SVM) classifier. The performance of the GSVM system proposed in this study is evaluated in 215 samples. The test results show that this GSVM system is effective to detect Doppler heart sounds. The averaged rate of correct classification rate was about 95%.

Intelligent target recognition based on wavelet adaptive network based fuzzy inference system

In this paper, an intelligent target recognition system is presented for target recognition from target echo signal of High Resolution Range (HRR) radars. This paper especially deals with combination of the feature extraction and classification from measured real target echo signal waveforms using X –band pulse radar. Because of this, a wavelet adaptive network based fuzzy inference systemmodel developed by us is used. The model consists of two layers: wavelet and adaptive network based fuzzy inference system. The wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of wavelet decomposition and wavelet entropy. The used for classification is an adaptive network based fuzzy inference system. The performance of the developed system has been evaluated in noisy radar target echo signals. The test results showed that this system was effective in detecting real radar target echo signals. The correct classification rate was about 93% for used target subjects.