The Detection and Recognition of Electrocardiogram's Waveform Based on Sparse Decomposition and Fuzzy Theory
Chunguang Wang · Signal Processing · 2009
Electrocardiogram(ECG) is an important method of diagnosis.Using computer to detect and recognize all kinds of wave of ECG can release doctor's tension coming from more and more ECG data,and decrease error because of tiredness,negligence, and subjective warp.Based on Gabor dictionary modified and the particle swarm optimization,ECG data are decomposed by the theory of sparse decomposition.Then,to detect QRS-complex,the fuzzy rules are instituted in term of coefficients and atoms.Beside QRS-complex, atoms which represent P-wave or T-wave with the most probability can be found through sparse decomposition,and then the detections and reorganizations of P-waves and T-waves can be completed with the help of fuzzy system.The experiments have proved the algorithm proposed could get a high ratio of QRS-complex' s detection,and recognitions of P-waves and T-waves were accord with expert' s judgments.