Research Article
Incremental Optimization Mechanism for Constructing a Decision Tree in Data Stream Mining
Pseudocode 3
Pseudocode of training approach.
PROCEDURE doNodeSplitting (, , , , ): | FOR each attribute at the leaf | Compute | Let be the attribute with highest and the second | Compute HB with | Let | END-FOR | IF () or ( and | or ( and | or ( and | Replace by an internal node splits on | Update adaptive tie and | FOR each branch of splitting | Add a new leaf and let | Let be the obtained by predicting the class in | according to at | FOR each class and each value of each attribute | and reset OCD: | END-FOR | END-FOR | END-IF | Return updated HT |
|