Fuzzy Classification of ECG Signals using a QRS-Like FIR Filter Bank with Lattice Structures

Significant features of the ECG signal include the P wave, the QRS complex, and he T wave. This paper focuses on the detection of the QRS complex. A 1st order Gaussian derivative function has a similar shape to QRS complex part of the ECG. In this paper, an FIR filter bank is efficiently designed with lattice structures for QRS features extraction, using Gaussian function with standard deviation value . ECG features are taken after three-level decompositions of the proposed filter bank. Significant energy values of the filter bank output coefficients are calculated and treated as crucial points for identification of the diseases/disorders in the ECG signal. Such values are used for the design of a rule-based fuzzy classifier.