Title :
Stochastic complexity measures for physiological signal analysis
Author :
Rezek, I.A. ; Roberts, S.J.
Author_Institution :
Dept. of Electr. & Electron. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
Abstract :
Traditional feature extraction methods describe signals in terms of amplitude and frequency. This paper takes a paradigm shift and investigates four stochastic-complexity features. Their advantages are demonstrated on synthetic and physiological signals; the latter recorded during periods of Cheyne-Stokes respiration, anesthesia, sleep, and motor-cortex investigation.
Keywords :
electroencephalography; entropy; feature extraction; medical signal processing; spectral analysis; stochastic processes; Cheyne-Stokes respiration; anesthesia; motor-cortex investigation; physiological signals; signal amplitude; signal description; signal frequency; sleep; synthetic signals; traditional feature extraction methods; Anesthesia; Biomedical engineering; Biomedical measurements; Entropy; Feature extraction; Frequency measurement; Power system modeling; Predictive models; Signal analysis; Stochastic processes; Anesthesia; Cheyne-Stokes Respiration; Electroencephalography; Fourier Analysis; Humans; Monitoring, Physiologic; Motor Cortex; Nonlinear Dynamics; Signal Processing, Computer-Assisted; Sleep; Stochastic Processes;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
