MATLAB smooth函数

原文地址：http://powerelite.blog.163.com/blog/static/429658912013459306166/

 
 
 
  smooth  Smooth data.

    Z = smooth(Y) smooths data Y using a 5-point moving average.

 

    Z = smooth(Y,SPAN) smooths data Y using SPAN as the number of points used

    to compute each element of Z.

 

    Z = smooth(Y,SPAN,METHOD) smooths data Y with specified METHOD. The

    available methods are:

 

            'moving'   - Moving average (default)

            'lowess'   - Lowess (linear fit)

            'loess'    - Loess (quadratic fit)

            'sgolay'   - Savitzky-Golay

            'rlowess'  - Robust Lowess (linear fit)

            'rloess'   - Robust Loess (quadratic fit)

 

    Z = smooth(Y,METHOD) uses the default SPAN 5.

 

    Z = smooth(Y,SPAN,'sgolay',DEGREE) and Z = smooth(Y,'sgolay',DEGREE)

    additionally specify the degree of the polynomial to be used in the

    Savitzky-Golay method. The default DEGREE is 2. DEGREE must be smaller

    than SPAN.

 

    Z = smooth(X,Y,...) additionally specifies the X coordinates.  If X is

    not provided, methods that require X coordinates assume X = 1:N, where

    N is the length of Y.

 

    Notes:

    1. When X is given and X is not uniformly distributed, the default method

    is 'lowess'.  The 'moving' method is not recommended.

 

    2. For the 'moving' and 'sgolay' methods, SPAN must be odd.

    If an even SPAN is specified, it is reduced by 1.

 

    3. If SPAN is greater than the length of Y, it is reduced to the

    length of Y.

 

    4. In the case of (robust) lowess and (robust) loess, it is also

    possible to specify the SPAN as a percentage of the total number

    of data points. When SPAN is less than or equal to 1, it is

    treated as a percentage.

 

    For example:

 

    Z = smooth(Y) uses the moving average method with span 5 and

    X=1:length(Y).

 

    Z = smooth(Y,7) uses the moving average method with span 7 and

    X=1:length(Y).

 

    Z = smooth(Y,'sgolay') uses the Savitzky-Golay method with DEGREE=2,

    SPAN = 5, X = 1:length(Y).

 

    Z = smooth(X,Y,'lowess') uses the lowess method with SPAN=5.

 

    Z = smooth(X,Y,SPAN,'rloess') uses the robust loess method.

 

    Z = smooth(X,Y) where X is unevenly distributed uses the

    'lowess' method with span 5.

 

    Z = smooth(X,Y,8,'sgolay') uses the Savitzky-Golay method with

    span 7 (8 is reduced by 1 to make it odd).

 

    Z = smooth(X,Y,0.3,'loess') uses the loess method where span is

    30% of the data, i.e. span = ceil(0.3*length(Y)).