An Electrocardiogram (ECG) is used as one of the important diagnostic tools for the detection of the health of a heart. An automatic heart abnormality identification methods sense numerous abnormalities or arrhythmia and decrease the physician's pressure as well as share their work load. In ECG analysis, the main focus is to enhance degree of accuracy and include a number of heart diseases that can be classified. In this research paper, arrhythmia classification is proposed using Hybrid features of T-wave in ECG. The classification system consists of majorly three phases, windowing technique, feature extraction and classification. In feature extraction phase various features are used such as Differential Entropy (DE), Peak-Magnitude RMS ratio, Auto Regressive feature based Yule Walker, Burgs method. In classification phase Deep Neural Network (DNN) classifier is used. This classifier categorizes the normal and abnormal signals efficiently. The experimental analysis showed that, the Hybrid features Arrhythmia classification performance of accuracy approximately 98.3%, Specificity 98.0% and Sensitivity 98.6% using MIT-BIH database.

No abstract

Electrocardiogram (ECG) is one of the monitoring methodology for the identification of arrhythmia disease. The conventional methodologies of arrhythmia identification are based on morphological features or certain transformation technique. These conventional techniques are partially successful in arrhythmia identification, because it treats heart as a linear structure. In this paper, ECG based arrhythmia identification is assessed by employing MIT-BIH arrhythmia dataset. The proposed approach contains two major steps: feature extraction and classification. Initially, a combination of non-linear and linear feature extraction is carried-out using Principal Component Analysis (PCA), Kernel Independent Component Analysis (KICA) and Higher Order Spectrum (HOS) for achieving optimal feature subsets. The linear experiments on ECG data achieves high performance in noise free data and the non-linear experiments distinguish the ECG data more effectively, extract hidden information and also helps to attain better performance under noisy conditions. After finding the feature information, a binary classifier Support Vector Machine (SVM) is employed for classifying the normality and abnormality of arrhythmia. In experimental analysis, the proposed approach distinguishes the normality and abnormality of arrhythmia ECG signals in terms of specificity, sensitivity and accuracy. Experimental outcome shows that the proposed approach improved accuracy in arrhythmia detection up to 0.5-1% compared to the existing methods: neural network and SVM based radial basis function.

No abstract

No abstract