This preview shows page 1. Sign up to view the full content.
Unformatted text preview: robability density function for n sample points is estimated as follows [Duda & Hart, 1973]: f n (e ) = 1 n 1 ei − e ∑ ϕ n i =1 h h (7) where φ is the window function. A Gaussian function with a mean of zero and a variance of unity is the popular choice for the φ. In this work, since we wish to 140 A. Barari, H. A. ElMaraghy and G. K. Knopf recognize discontinuities in the density function, the window function φ is defined as follows: 1 u≤ ϕ (u ) = 1 (8) 2 0 Otherwise This function simply counts the number of observed samples inside the window centered on any arbitrary value of e. Therefore the probability density function is estimated based on the ratio of samples inside the selected window to the total samples. 3.2. Discontinuity in the density function The density function is calculated for m windows centered with incremental distance of h. The first and the last windows are centered at: h min (ei ) − 2 )× h e 1 = floor ( i (9) h h max (ei ) + m i 2 )× h e = ceil ( (10) h where the floor and...
View Full Document
This note was uploaded on 08/03/2010 for the course DD 1234 taught by Professor Zczxc during the Spring '10 term at Magnolia Bible.
- Spring '10
- The Land