Title :
Identification of QRS complexes in single-lead ECG Using LS-SVM
Author :
Sharma, Shantanu ; Nagal, Devendra
Author_Institution :
Dept. of Electr. Eng., Jodhpur Nat. Univ., Jodhpur, India
Abstract :
The Electrocardiogram (ECG) is a sensitive diagnostic tool that is used to detect various cardio-vascular diseases by measuring and recording the electrical activity of the heart in exquisite detail. Identification of QRS-complexes in ECGs has been a challenging task ever since the beginning of automated ECG analysis. The identification of QRS-complexes using LS-SVM as classifier has been presented in the paper. Since slope of the ECG is much more in QRS region as compared to other region, it has been used as an important discriminating feature. Using LS-SVM as a classifier, the QRS-complexes have been identified with an accuracy of 99.51 % with 0.49% of false negative (FN) and 0.25% of false positive (FP) respectively. The QRS-complexes have also been delineated with the tolerance limit as specified by CSE.
Keywords :
bioelectric potentials; cardiovascular system; diseases; electrocardiography; feature extraction; medical signal detection; medical signal processing; support vector machines; LS-SVM classifier; QRS complex identification; automated ECG analysis; cardiovascular disease detection; feature discrimination; heart electrical activity measurement; heart electrical activity recording; single-lead electrocardiogram; Computers; Electrocardiography; Lead; MATLAB; Publishing; Support vector machines; Vectors; LS-SVM; QRS Complex; SVM; Slope;
Conference_Titel :
Recent Advances and Innovations in Engineering (ICRAIE), 2014
Conference_Location :
Jaipur
Print_ISBN :
978-1-4799-4041-7
DOI :
10.1109/ICRAIE.2014.6909243