3

Output attribute is risky patient. Values are yes and no. If yes then patient is risky, and if no then patient is not risky.

If I am combining 3 classifier for classification model in weka, and if final result will be calculated by average voting:

For Exp: Classifier 1 result- yes, Classifier 2 result- no, Classifier 3 result- yes,

count of yes=2, count of no=1

Final result will be yes as it's count is high. This is understandable.

But if I am combing 2 classifier,

For Exp: Classifier 1 result-yes, Classifier 2 result-no

count of yes=1, count of no=1

Now, What will be result? As yes and no has same count value.

How is weka working in case of this kind of combination of two multiple classifier? It's really confusing..

Mirza Sisic
  • 2,401
  • 4
  • 24
  • 38
Rutvij Mehta
  • 31
  • 3
  • It will choose randomly in case of same vote.see edit portion of answer 2nd paragraph. http://stackoverflow.com/questions/11626417/majority-vote-algorithm-in-weka-classifiers-meta-vote – Dhruv Kapatel Mar 29 '16 at 15:16
  • @Dhruv: Thanks for reference. One has also suggested In the cases of a tie, the Voting Classifier will select the class based on the ascending sort order. E.g., in the following scenario:classifier 1 result >class 2, and classifier 2 result >class1. The class label 1 will be assigned to the sample. – Rutvij Mehta Mar 29 '16 at 17:41

0 Answers0