Research Article
Integrating Correlation-Based Feature Selection and Clustering for Improved Cardiovascular Disease Diagnosis
Algorithm 1
Proposed feature selection algorithm using reversed correlations
Input: F = f1, f2, f3, … fn/ set of all the features /; | P/ statistical significance level /; | R/ a threshold for correlation coefficient levels ∗/; | N/ the maximum of features for the subset/; | Output: Fs/ selected subset of features /; | (1) Initialize Fs with feature fj ϵ F that is the least correlated with other ones; | (2) do | (3) Compute Cij(Fs, F \ Fs) as a vector of correlation coefficients between Fs and each fi ϵ {F \ Fs}; | (4) Choose fj ϵ {F \ Fs} with the lowest value of correlation coefficient in a vector Cij(Fs, F \ Fs); | (5) Include fj in Fs | (6) while (s < N AND p > P AND Cij(Fs, F \ Fs) < R). |
|