Please use this identifier to cite or link to this item: http://localhost:8081/xmlui/handle/123456789/8459
Title: FEATURE EXTRACTION OF ECG SIGNAL USING SYNTACTIC APPROACH
Authors: Prajapati, Natthoo Lal
Keywords: ELECTRICAL ENGINEERING;FEATURE EXTRACTION;ECG SIGNAL;SYNTACTIC APPROACH
Issue Date: 1999
Abstract: The syntactic approach utilized is based on the assumption that ECG waveform are composed of different patterns. Pattern can be decomposed into sub-patterns and the sub-pattern into other sub-patterns and so on. For instant, the QRS-pattern is composed of sub-patterns called `waves', namely the Q; R and S waves. In this approach, first of all, a given frame of ECG signal is approximated piecewise linearly into a set of line segments which are completely specified in terms of their lengths and slopes. The -slope values -are quantized into five distinct levels and a unit length line segment with a slope values in each of these levels is coded as a slope symbol. Five such slope symbols constitute the set of primitives. The given signal is represented as a string of such symbols based on the length and angle of the line segments approximating the - signal. On the other hand, given ECG signal is then represented by a language like structure. The features and nature of a given ECG signal are extracted by matching.the string of reference pattern with the complete string of given signal. The approach has been tested for creating the primitives and then creating the strings from ECG signal. The testing patterns have been developed and tested using both the sImvlated as well as CSE data base ECG signals. The technique has been extended to test the ECG signals for left ventricular hypertrophy (LVH) type of cardiac disease. The technique has produced reliable and satisfactory results and can be perfected by lot of testing on real time ECG signal for computer aided diagnostics of cardiac diseases.
URI: http://hdl.handle.net/123456789/8459
Other Identifiers: M.Tech
Research Supervisor/ Guide: Anand, R. S.
Saxena, S. C.
metadata.dc.type: M.Tech Dessertation
Appears in Collections:MASTERS' THESES (Electrical Engg)

Files in This Item:
File Description SizeFormat 
EED 247879.pdf3.64 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.