An Efficient Online Multiparty Interactive Medical Prediagnosis Scheme with Privacy Protection

Algorithm 1

Relief feature weight distribution algorithm.

Input: training data set , sample sampling times , feature set

, which has n features in total.

Output: feature weight .

1:The feature rights are reset to 0;

2:for to do

3: Randomly select a sample ;

4: Find the nearest neighbor sample in the same class of ,

and the nearest neighbor sample in different classes of ;

5: for to do

6:  ;

7: end for

8:end for

9:return .