Stochastic complexity measures for physiological signal analysis

IEEE Transactions on Biomedical EngineeringPublished 1 January 1998

Iead Rezek, Stephen Roberts

DOI10.1109/10.709563

Source URL

Citations291

SJR quartileQ1

SJR score1.11

SNIP1.58

TL;DR

This paper takes a paradigm shift and investigates four stochastic-complexity features and their advantages are demonstrated on synthetic and physiological signals; the latter recorded during periods of Cheyne-Stokes respiration, anesthesia, sleep, and motor-cortex investigation.

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

MathematicsNeuroscienceEngineering

Proceedings of the National Academy of SciencesApproximate entropy as a measure of system complexity.

5,769 Citations1991Steven M. Pincus

Analysis of a recently developed family of formulas and statistics, approximate entropy (ApEn), suggests that ApEn can classify complex systems, given at least 1000 data values in diverse settings that include both deterministic chaotic and stochastic processes.

Proceedings of the IEEESpectrum analysis—A modern perspective

3,142 Citations1981Steven Kay, S.L. Marple

A summary of many of the new techniques developed in the last two decades for spectrum analysis of discrete time series is presented, including the classical periodogram, classical Blackman-Tukey, autoregressive, moving average, autotegressive-moving average, maximum likelihood, Prony, and Pisarenko methods.

View PDF

Physica D Nonlinear PhenomenaExtracting qualitative dynamics from experimental data

2,292 Citations1986D.S. Broomhead, Gregory P. King

Electroencephalography and Clinical NeurophysiologyEEG analysis based on time domain properties

1,425 Citations1970Bo Hjorth

The proposed method offers a way to on-line measurement of basic signal properties by means of a time-based calculation, requiring less complex equipment compared to conventional frequency analysis and the data-reducing capability of the parameters has been experimentally stated.

Singular Spectrum Analysis: A New Tool in Time Series Analysis

419 Citations1996James B. Elsner, Anastasios A. Tsonis

Singular Spectrum Analysis

377 Citations1996James B. Elsner, Anastasios A. Tsonis

Medical Engineering & PhysicsA review of parametric modelling techniques for EEG analysis

290 Citations1996James Pardey, Stephen Roberts +1 more

This review provides an introduction to the use of parametric modelling techniques for time series analysis, and in particular the application of autoregressive modelling to the analysis of physiological signals such as the human electroencephalogram.

Electroencephalography and Clinical NeurophysiologyDifferentiation between finger, toe and tongue movement in man based on 40 Hz EEG

171 Citations1994G. Pfurtscheller, Doris Flotzinger +1 more

It was found that, based on single EEG trials, the data from the 4 movements could be differentiated with an accuracy of 70% when alpha and gamma band activity were used but only with 58% in the case of the alpha band activity alone.

IEE Proceedings - Vision Image and Signal ProcessingModel order selection for the singular value decomposition and the discrete Karhunen–Loeve transform using a Bayesian approach

51 Citations1997J.J. Rajan, P. J. Rayner

Bayesian model order selection is considered in relation to the singular value decomposition (SVD) and the discrete Karhunen-Loeve transform (DKLT) and results that illustrate the usefulness of the method are included.

Computer Methods and Programs in BiomedicineNeural networks and nonlinear regression modelling and control of depth of anaesthesia for spontaneously breathing and ventilated patients

13 Citations1993Hidayat Ur Rehman, D.A. Linkens +1 more

This study is concerned with the development of controllers and patient models via Artificial Neural Networks and regression analysis and the robustness to the sensitivity of the regression patient model was investigated.