Classification Methodology of CVD with Localized Feature Analysis Using Phase Space Reconstruction Targeting Personalized Remote Health Monitoring

Vemishetty, N and Acharyya, Amit and Das, S and Maharatna, K and Puddu, P E (2016) Classification Methodology of CVD with Localized Feature Analysis Using Phase Space Reconstruction Targeting Personalized Remote Health Monitoring. In: Computing in Cardiology Conference (CINC), September 11-14, 2016, Vancouver, Canada.

Preview

Text
512_CinCFinalPDF.pdf - Accepted Version
Download (527kB) | Preview

Abstract

This paper introduces the classification methodology of C ardiovascular Disease ( CVD ) with lo calized feature analysis using Phase Space R econstruction (PSR) technique targeting personalized health care . The proposed classification methodology uses a few localized features (QRS inter val and PR interval ) of individual Electrocardiogram ( ECG ) beats from the Feature Extraction (FE) block and detect s the desynchronization in the given intervals after applying the PSR technique. Considering the QRS interval, if any notch is present in the QRS complex, then th e corresponding contour will appear and the variation in the box count indicating a notch in the QRS complex. Likewise, the contour and the disparity of box count due to the variation in the PR interval localized wave have been noticed using the proposed PSR technique. ECG database from the Phy sionet (MIT - BIH and PTBDB) has been used t o verify the proposed analysis on localized features using proposed PSR and has enabled us to classify the various abnorm alities like fragmented QRS complexes, myocardial infarction , ventricular arrhythmia and atrial fibrillation. The design have been successfully tested for diagnosing various disorders with 98% accuracy on all the specified abnormal databases.

[error in script]

IITH Creators: