An improved random forest classifier for multi-class classification 论文

摘要

The paper presents an improved-RFC (Random Forest Classifier) approach for multi-class disease classification problem. It consists of a combination of Random Forest machine learning algorithm, an attribute evaluator method and an instance filter method. It intends to improve the performance of Random Forest algorithm. The performance results confirm that the proposed improved-RFC approach performs better than Random Forest algorithm with increase in disease classification accuracy up to 97.80% for multi-class groundnut disease dataset. The performance of improved-RFC approach is tested for its efficiency on five benchmark datasets. It shows superior performance on all these datasets.