Zümray Dokur

ECG beat classification by a novel hybrid neural network

This paper presents a novel hybrid neural network structure for the classification of the electrocardiogram (ECG) beats. Two feature extraction methods: Fourier and wavelet analyses for ECG beat classification are comparatively investigated in eight-dimensional feature space. ECG features are determined by dynamic programming according to the divergence value. Classification performance, training time and the number of nodes of the multi-layer perceptron (MLP), restricted Coulomb energy (RCE) and a novel hybrid neural network are comparatively presented. In order to increase the classification performance and to decrease the number of nodes, the novel hybrid structure is trained by the genetic algorithms (GAs). Ten types of ECG beats obtained from the MIT-BIH database and from a real-time ECG measurement system are classified with a success of 96% by using the hybrid structure.

Classification of heart sounds using an artificial neural network

A novel method is presented for the classification of heart sounds (HSs). Wavelet transform is applied to a window of two periods of HSs. Two analyses are realized for the signals in the window: segmentation of the first and second HSs, and extraction of the features.After the segmentation, feature vectors are formed by using the wavelet detail coefficients at the sixth decomposition level. The best feature elements are analyzed by using dynamic programming. Grow and learn (GAL) network and linear vector quantization (LVQ) network are used for the classification of seven different HSs.It is observed that HSs of patients are successfully classified by the GAL network compared to the LVQ network.

Classification of electroencephalogram signals with combined time and frequency features

Epilepsy is a neurological disorder that causes people to have seizures and the main application field of electroencephalography. In this study, combined time and frequency features approach for the classification of healthy and epileptic electroencephalogram (EEG) signals is proposed. Features in the time domain are extracted using the cross correlation (CC) method. Features related to the frequency domain are extracted by calculating the power spectral density (PSD). In the study, these individual time and frequency features are considered to carry complementary information about the nature of the EEG itself. By using divergence analysis, distributions of the feature vectors in the feature space are quantitatively measured. As a result, using the combination rather than individual feature vectors is suggested for classification. In order to show the efficiency of this approach, first of all, the classification performances of the time and frequency based feature vectors in terms of overall accuracy are analyzed individually. Afterwards, the feature vectors obtained by the combination of the individual feature vectors are used in classification. The results achieved by different classifier structures are given. Obtained performances in the study are comparatively evaluated by the help of the other studies for the same dataset in advance. Results show that the combination of the features derived from cross correlation and PSD is very promising in discriminating between epileptic and healthy EEG segments.

Heart sound classification using wavelet transform and incremental self-organizing map

Determination of heart condition by heart auscultation is a difficult task and requires special training of medical staff. Computerized techniques suggest objective and more accurate results in a fast and easy manner. Hence, in this study it is aimed to perform computer-aided heart sound analysis to give support to medical doctors in decision making. In this study, a novel method is presented for the classification of heart sounds (HSs). Discrete wavelet transform is applied to windowed one cycle of HS. Wavelet transform is used both for the segmentation of S1-S2 sounds and determination of the features. Based on the third, fourth and the fifth decomposition-level detail coefficients, the timings of S1-S2 sounds are determined by an adaptive peak-detector. For the feature extraction, powers of detail coefficients in all five sub-bands are utilized. In the classification stage, Kohonens SOM network and an incremental self-organizing map (ISOM) are examined comparatively. In order to increase the performance of heart sound classification, an incremental neural network is proposed in this study. It is observed that ISOM successfully classifies the HSs even in noisy environment.

Detection of ECG waveforms by neural networks.

In this study, ECG waveform detection was performed by using artificial neural networks (ANNs). Initially, the R peak of the QRS complex is detected, and then feature vectors are formed by using the amplitudes of the significant frequency components of the DFT spectrum. Grow and Learn (GAL) and Kohonen networks are comparatively investigated to detect four different ECG waveforms. The comparative performance results of GAL and Kohonen networks are reported.

Tumor detection by using Zernike moments on segmented magnetic resonance brain images

In this study, a novel method is proposed for the detection of tumor in magnetic resonance (MR) brain images. The performance of the novel method is investigated on one phantom and 20 original MR brain images with tumor and 50 normal (healthy) MR brain images. Before the segmentation process, 2D continuous wavelet transform (CWT) is applied to reveal the characteristics of tissues in MR head images. Then, each MR image is segmented into seven classes (six head tissues and the background) by using the incremental supervised neural network (ISNN) and the wavelet-bands. After the segmentation process, the head is extracted from the background by simply discarding the background pixels. Symmetry axis of the head in the MR image is determined by using moment properties. Asymmetry is analyzed by using the Zernike moments of each of six tissues segmented in the head: two vectors are individually formed for the left and right hand sides of the symmetry axis on the sagittal plane by using the Zernike moments of the segmented tissues in the head. Presence of asymmetry and the tumors are inquired by considering the distance between these two vectors. The performance of the proposed method is further investigated by moving the location of the tumor and by modifying its size in the phantom image. It is observed that tumor detection is successfully realized for the tumorous 20 MR brain images.

Segmentation of ultrasound images by using a hybrid neural network

A hybrid neural network is presented for the segmentation of ultrasound images.Feature vectors are formed by the discrete cosine transform of pixel intensities in region of interest (ROI). The elements and the dimension of the feature vectors are determined by considering only two parameters: The amount of ignored coefficients, and the dimension of the ROI.First-layer-nodes of the proposed hybrid network represent hyperspheres (HSs) in the feature space. Feature space is partitioned by intersecting these HSs to represent the distribution of classes. The locations and radii of the HSs are found by the genetic algorithms.Restricted Coulomb energy (RCE) network, modified RCE network, multi-layer perceptron and the proposed hybrid neural network are examined comparatively for the segmentation of ultrasound images.

Feature determination for heart sounds based on divergence analysis

Heart auscultation (the interpretation of heart sounds by a physician) is a fundamental component of cardiac diagnosis. It is, however, a difficult skill to acquire. In decision making, it is important to analyze heart sounds by an algorithm to give support to medical doctors. In this study, two feature extraction methods are comparatively examined to represent different heart sound (HS) categories. First, a rectangular window is formed so that one period of HS is contained in this window. Then, the windowed time samples are normalized. Discrete wavelet transform is applied to this windowed one period of HS. Based on the wavelet detail coefficients at several bands, the time locations of S1-S2 sounds are determined by an adaptive peak detector. In the first feature extraction method, sub-bands belonging to the detail coefficients are partitioned into ten segments. Powers of the detail coefficients in each segment are computed. In the second feature extraction method, the power of the signal in a window which consists of 64 samples is computed without filtering the HSs. In the study, performances of these two feature extraction methods are comparatively examined by the divergence analysis. The analysis quantitatively measures the distribution of vectors in the feature space.

A unified framework for image compression and segmentation by using an incremental neural network

This paper presents a novel unified framework for compression and decision making by using artificial neural networks. The proposed framework is applied to medical images like magnetic resonance (MR), computer tomography (CT) head images and ultrasound image. Two artificial neural networks, Kohonen map and incremental self-organizing map (ISOM), are comparatively examined. Compression and decision making processes are simultaneously realized by using artificial neural networks. In the proposed method, the image is first decomposed into blocks of 8x8 pixels. Two-dimensional discrete cosine transform (2D-DCT) coefficients are computed for each block. The dimension of the DCT coefficients vectors (codewords) is reduced by low-pass filtering. This way of dimension reduction is known as vector quantization in the compression scheme. Codewords are the feature vectors for the decision making process. It is observed that the proposed method gives higher compression rates with high signal to noise ratio compared to the JPEG standard, and also provides support in decision-making by performing segmentation.

Medical image segmentation with transform and moment based features and incremental supervised neural network

In this study, a novel incremental supervised neural network (ISNN) is proposed for the segmentation of medical images. Performance of the ISNN is investigated for tissue segmentation in medical images obtained from various imaging modalities. Two feature extraction methods based on transform and moments are comparatively investigated to segment the tissues in medical images. Two-dimensional (2D) continuous wavelet transform (CWT) and the moments of the gray-level histogram (MGH) are computed in order to form the feature vectors of ultrasound (US) bladder and phantom images, X-ray computerized tomography (CT) and magnetic resonance (MR) head images. In the 2D-CWT method, feature vectors are formed by the intensity of one pixel of each wavelet-plane of different energy bands. The MGH represents the tissues within the sub-windows by using the spatial variation of image intensities. In this study, the ISNN and Grow and Learn (GAL) network are employed for the segmentation task. It is observed that the ISNN has significantly eliminated the disadvantages of the GAL network in the segmentation of the medical images.