Discrete Cosine Transform Features in Automated classification of Cardiac Arrhythmia Beats

Desai, Usha and Roshan, Joy Martis and Nayak, Gurudas C and Sarika, K and Nayak, Sagar G and Shirva, Ashwin and Nayak, Vishwas and Mudassir, Shaik Discrete Cosine Transform Features in Automated classification of Cardiac Arrhythmia Beats. In: Emerging Research in Computing, Information,. Springer International Publishing, pp. 153-162. ISBN 978-81-322-2549-2

[img] PDF
BOOK-CGN.pdf - Published Version
Restricted to Registered users only

Download (132kB) | Request a copy


Arrhythmia is an abnormal beat result from any disorder in the conduction of the cardiac electrical impulse. It is very essential to identify and detect arrhythmias correctly in its early phases. Manual diagnosis of arrhythmia beats is very difficult due to their unfamiliar mechanisms and composite nature. Current paper introduces, a machine learning-based methodology proposed for automated cardiac arrhythmia detection. The methodology follows ECG filtering and segmentation using general approach, followed by Discrete Cosine Transform (DCT) for feature extraction, Principal Component Analysis (PCA) for feature reduction and finally classification of arrhythmia beats using k-Nearest Neighbor (k-NN) classifier. In this study, the statistical significance of PCA features is verified using Analysis of Variance (ANOVA) test. Statistically signify cant features are classified using k-NN and tenfold cross validation. In this study, all the beats of entire MIT-BIH (Massachusetts Institute of Technology—Boston’s Beth Israel Hospital) arrhythmia database are considered. The five classes recommended by ANSI/AAMI EC57:1998 standard: Non-ectopic (N), Supraventricular ectopic (S), Ventricular ectopic (V), Fusion (F) and Unknown (U) cardiac beats are recognized with an average class specific accuracy of 99.93, 98.41, 98.09, 96.93, 99.7 % respectively and overall average accuracy of 98.61 %. Added validation of the proposed method can result in suitable outcome for therapeutic applications.

Item Type: Book Section
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 12 Jan 2016 09:55
Last Modified: 12 Jan 2016 09:55
URI: http://eprints.manipal.edu/id/eprint/145060

Actions (login required)

View Item View Item