| [ KAIST ] in KIDS 글 쓴 이(By): iLUSiON (화려한집념) 날 짜 (Date): 2003년 3월 1일 토요일 오전 10시 08분 09초 제 목(Title): Re: [Q]필터 잘아시는분 not sure what is your model. if it is a very basic model like this y(t) = \int K_1(t-s)x_1(s) + ... \int K_n(t-s)x_n(s) + e(t) where K filter function, x_i : i-th input signal. e : noise \int integral. now linearize the integral by Riemaan sum and estimate the filter itself from your data. then from your estimation, you choose filter shape that matches your estimate most closely. nothing beats this deconvolution analysis. :) iLUSiON whitepolarcow@hotmail.com |