大脑胶质瘤诊断中不均衡问题的特征选择  

Feature Selection for Imbalanced Prediction of Brain Glioma

作　　者：刘天羽[1] 李国正[2] 

机构地区：[1]上海电机学院电气学院,上海200240 [2]司济大学控制科学与工程系,上海201804

出　　处：《广西师范大学学报（自然科学版）》2009年第3期101-104,共4页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金资助项目(20503015,60873129);上海市科委“创新行动计划”重大资助项目(07DZ19726);上海高校选拔培养优秀青年教师科研专项基金资助项目(sdj-07003);上海市青年科技启明星计划资助项目(08QA1403200);上海市教育委员会重点学科建设项目资助(J51901)

摘　　要：在大脑胶质瘤诊断数据集中,病例样本数通常比正常样本数要少,由此引发了数据不均衡问题下病例诊断的问题。此外,在大脑胶质瘤数据集中有一些冗余甚至是不相关的特征,这些特征降低了学习器的泛化能力。为解决这类问题,提出一种基于互信息特征选择的E asyEnsem b le算法来解决大脑胶质瘤诊断中的数据不均衡问题。在UC I数据集和大脑胶质瘤数据集上的实验结果表明新算法提高了分类器在不均衡数据集上的分类性能和预报能力。The degree of malignancy in brain glioma dominates the way of treatment and is critical beiore brain surgery. The class imbalance problem is encountered in diagnosing brain glioma. Though it is critical, few previous works paid attention to this class imbalance problem in prediction of malignancy degree in brain glioma. In imbalanced problems,some features are redundant or irrelevant. These features will hurt the generalization performance of learning machines. Here we propose MIEE （Mutual Information based feature selection for EasyEnsemble） is proposed to solve the imbalanced class problem and to predict the degree of malignancy in brain glioma. Experimental results on UCI data sets and dataset of brain glioma show that MIEE improves the classification performance and prediction ability on the imbalanced dataset.

关 键 词：特征选择 不均衡数据集 集成学习 互信息 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]