MATLAB POLYSPACE RELEASE NOTES Manuale Utente Scaricare il pdf (Pagina 177)

Preprocessing Data

Noisy data shows random variations about expected values. You may want

to smooth the data to reveal its main features before building a model. Two

basic assumptions u nderlie smoothing:

• The relationship between the predictor (time) and the res po nse (traffic

volume) is smooth.

• The smoothing algorithm results in v a lues that are better estim ates of

expected values because the noise has been reduced.

Apply a simple moving average smoother to the data using the MATLAB

convn function:

span = 3; % Size of the averaging window

window = ones(span,1)/span;

smoothed_c3m = convn(c3m,window,'s ame' );

h = plot(smoothed_c3m, 'ro-');

legend('Data','Smoothed Data')

5-7

1 2 ... 172 173 174 175 176 177 178 179 180 181 182 ... 239 240

Nessun commento

MATLAB POLYSPACE RELEASE NOTES Manuale Utente Pagina 177