Individual optimal feature selection based on comprehensive evaluation indexs

摘要: Individual optimal feature selection algorithm is simple and effective. Generally, single criterion chosen for selection. But in this case, it possible that features with good performance on other criteria will be neglected, causing a negative impact to result. For the problem, paper proposes comprehensive evaluation model based fuzzy correlation projection evaluating indexs of individual features, takes results as basis Definition its application procedure are described. Finally, proposed method applied evaluate select underwater target recognition feature. The experimental result shows selected subset has higher testing rate than criterion, e.g. Relief-F indexs. Therefore, feasible