The Analysis of Noisy Signals by Nonparametric Smoothing and Differentiation

While smoothing methods are commonly applied to noisy signals, this is not true for differentiation. Derivatives are often of intrinsic interest when analyzing biological dynamics, and as will be illustrated, they are useful for determining characteristic points (local extrema, inflection, and saddle points) in the curve, in the presence of noise. There are inherent difficulties in computing derivatives which might have inhibited wider usage. Kernel estimation is a statistical approach to nonparametric regression (i.e., without specifying a functional model for the signal), which allows detertining the signal itself and its derivatives from noisy data. This method is presented, together with its properties. The influence and the choice of the weight function (kernel) of the smoothing parameter and the treatment of boundary points deserve particular attention.

[1]  McGillem Cd,et al.  Signal processing in evoked potential research: applications of filtering and pattern recognition. , 1981 .

[2]  Michael D. Lesh,et al.  A Gait Analysis Subsystem for Smoothing and Differentiation of Human Motion Data , 1979 .

[3]  L Molinari,et al.  An analysis of the mid-growth and adolescent spurts of height based on acceleration. , 1985, Annals of human biology.

[4]  M Rappaport,et al.  Peak identification in visual evoked potentials. , 1973, Psychophysiology.

[5]  H. Müller,et al.  Kernels for Nonparametric Curve Estimation , 1985 .

[6]  A. Terry Bahill,et al.  Frequency Limitations and Optimal Step Size for the Two-Point Central Difference Derivative Algorithm with Applications to Human Eye Movement Data , 1983, IEEE Transactions on Biomedical Engineering.

[7]  W. Härdle,et al.  Optimal Bandwidth Selection in Nonparametric Regression Function Estimation , 1985 .

[8]  Shiro Usui,et al.  Digital Low-Pass Differentiation for Biological Signal Processing , 1982, IEEE Transactions on Biomedical Engineering.

[9]  Clare D. McGillem,et al.  Measurements of Signal Components in Single Visualy Evoked Brain Potentials , 1977, IEEE Transactions on Biomedical Engineering.

[10]  Theo Gasser,et al.  Performance and Measures of Performance for Estimators of Brain Potentials Using Real Data , 1986, IEEE Transactions on Biomedical Engineering.

[11]  K. A. Kooi,et al.  OBSERVATIONS ON EARLY COMPONENTS OF THE VISUAL EVOKED RESPONSE AND OCCIPITAL RHYTHMS. , 1964, Electroencephalography and clinical neurophysiology.

[12]  H. Müller,et al.  Estimating regression functions and their derivatives by the kernel method , 1984 .

[13]  A. Terry Bahill,et al.  An adaptive control model for human head and eye movements while walking , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[14]  R Verleger,et al.  SELAVCO: a method to deal with trial-to-trial variability of evoked potentials. , 1983, Electroencephalography and clinical neurophysiology.

[15]  H. Müller,et al.  Nonparametric Regression Analysis of Growth Curves , 1984 .

[16]  A. Blum,et al.  Does smoking interfere with the effect of histamine H2-receptor antagonists on intragastric acidity in man? , 1987, Gut.