Cooperative Profit Random Forests With Application in Ocean Front Recognition

Abstract

Random Forests are powerful classification and regression tools that are commonly applied in machine learning and image processing. In the majority of random classification forests algorithms, the Gini index and the information gain ratio are commonly used for node splitting. However, these two kinds of node-split methods may pay less attention to the intrinsic structure of the attribute variables and fail to find attributes with strong discriminate ability as a group yet weak as individuals. In this paper, we propose an innovative method for splitting the tree nodes based on the cooperative game theory, from which some attributes with good discriminate ability as a group can be learned. This new random forests algorithm is called Cooperative Profit Random Forests (CPRF). Experimental comparisons with several other existing random classification forests algorithms are carried out on several real-world data sets, including remote sensing images. The results show that CPRF outperforms other existing Random Forests algorithms in most cases. In particular, CPRF achieves promising results in ocean front recognition.