Computer aided diagnosis of ECG data on the least square support vector machine

Department of Electrical and Electronics Engineering, Selcuk University, 42075 Konya, Turkey
Digital Signal Processing (Impact Factor: 1.5). 01/2008; DOI: 10.1016/j.dsp.2007.05.006
Source: DBLP

ABSTRACT In this paper we describe a technique that has successfully classified arrhythmia from an ECG dataset using a least square support vector machine (LSSVM). LSSVM was applied to the ECG dataset to distinguish between healthy persons and diseased persons (arrhythmia). The LSSVM classifier trained with four train-test parts including a training-to-test split of 50–50%, a training-to-test split of 70–30%, and a training-to-test split of 80–20%. We have used the classification accuracy, sensitivity and specificity analysis, and ROC curves to test the performance of LSSVM classifier on the detection of ECG arrhythmia. The classification accuracies obtained are 100% for all the training-to-test splits. These results show that the proposed method is more promising than previously reported classification techniques. The results suggest that the proposed method can be used to enhance the performance of a new intelligent assistance diagnosis system.

1 Bookmark
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, an evolutionary hybrid approach is studied for fault diagnosis and it is applied to classify the loopers faults in hot rolling process. The algorithm called evolutionary KPCA-LSSVM is the combination of genetic algorithm (GA), kernel principal component analysis (KPCA) and Least Squares Support Vector Machine (LSSVM), which can obtain better fault recognition rate. Firstly, kernel function concept is introduced, and then GA is used to select the kernel parameter in order to improve the performances of nonlinear feature extraction and fault classification of KPCA-LSSVM method. Secondly, KPCA is used to extract the nonlinear principal features of loopers by adopting the optimal kernel trick to map nonlinearly the data into a feature space and employing the PCA procedure. Thirdly, the nonlinear principal features of loopers are taken as input into a LSSVM to classify the faults of loopers in hot rolling process. The results of contrastive experiments show that the evolutionary KPCA-LSSVM using GA to optimize the kernel parameters can extract fault features associated with the loopers effectively, reduce the computational cost and enhance fault classification properties.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Low-loss and low-priced channel branching filters are of great interest e.g. for radio relay systems and cellular radio base stations. The paper describes a novel concept for modularly constructed waveguide multiplexers of manifold type to assure the expansion or reduction of an already existing multiplexer by a predetermined number of channel filters - during system operation. Furthermore high-selection dielectric-resonator-filters guarantee good climate conditions as well as low passband loss, symmetric attenuation skirts and attenuation poles at finite frequencies. All the measured results are in good correspondence with theory and confirm the applicability of the novel concept.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Magnetic resonance imaging (MRI) is often the medical imaging method of choice when soft tissue delineation is necessary. This paper presents a new approach for automated diagnosis based on classification of the magnetic resonance images (MRI). The proposed method consists of two stages namely feature extraction and classification. In the first stage, we have obtained the features related to MRI images using discrete wavelet transformation (DWT). Wavelet transform based methods are a well known tool for extracting frequency space information from non-stationary signals. The features extracted using DWT of magnetic resonance images have been reduced, using principal component analysis (PCA), to the more essential features. In the classification stage, two classifiers have been developed. The first classifier is based on feed forward back propagation artificial neural network (FP-ANN) and the second classifier is based on k-nearest neighbor (k-NN). The features hence derived are used to train a neural network based binary classifier, which can automatically infer whether the image is that of a normal brain or a pathological brain, suffering from brain lesion. A classification with a success of 90% and 99% has been obtained by FP-ANN and k-NN, respectively. This result shows that the proposed technique is robust and effective compared with other recent work.