A SVM adaptive approach for Ventricular disease classification
Author Name : Anu Ahlawat, Shamsher Malik
ABSTRACT ECG signal is the electrical signal form to represent the heart rate. ECG signal processing is effective to identify and classify the heart disease. The most critical heart disease form is vehicular disease. In this work, a HMM integrated SVM model is presented to identify the ventricular disease. The model is applied on the real time ECG signals. A layered model is presented in this work to transform the signal to the feature form. After generating the feature set, the classifier is applied to perform the disease identification. The implementation result shows that the work model has provided the significant identification of disease.