DETECTION OF HEART ARRHYTHMIAS USING ANALYTIC SPECTRA TECHNIQUE
V. E. Antsiperov
1, I. V. Zabrosaev
1,2,
D.V. Rastjagaev 3
1
Kotel’nikov Institute of Radio-engineering and
Electronics of RAS
2
Moscow Institute of Physics and
Technology
3
Russian New University (Moscow)
The paper is received on November 30, 2015
Abstract.
The paper is devoted to research and development of new ECG processing
methods, based on multiscale correlation analysis approach, in particular, the
development of new methods for arrhythmia detection. It is shown that in case
of ECG, where a signal has a form of repeated wave pulses, the instruments
previously developed and called the analytic spectra technique are highly
effective. Computational algorithm based on this technique accurately estimates
the heart rate. Heart rate estimation allows for building premature beats
detection algorithm. The report provides results received in this direction.
The results of premature ventricular complexes / supraventricular premature
beats detection for long ECG recordings from PhysioBank’s MIT-BIH NSRDB and
SADB databases are briefly summarized in the last section.
Key words: biomedical signals processing, ECG analysis, premature beats
detection, computer aided diagnosis, personal medicine, analytic spectra.