计算机科学 ›› 2017, Vol. 44 ›› Issue (Z11): 98-101.doi: 10.11896/j.issn.1002-137X.2017.11A.019
师彦文,王宏杰
SHI Yan-wen and WANG Hong-jie
摘要： 针对不平衡数据集的有效分类问题,提出一种结合代价敏感学习和随机森林算法的分类器。首先提出了一种新型不纯度度量,该度量不仅考虑了决策树的总代价,还考虑了同一节点对于不同样本的代价差异；其次,执行随机森林算法,对数据集作K次抽样,构建K个基础分类器；然后,基于提出的不纯度度量,通过分类回归树(CART)算法来构建决策树,从而形成决策树森林；最后,随机森林通过投票机制做出数据分类决策。在UCI数据库上进行实验,与传统随机森林和现有的代价敏感随机森林分类器相比,该分类器在分类精度、AUC面积和Kappa系数这3种性能度量上都具有良好的表现。
| [1] 刘偲,秦亮曦.模糊决策粗糙集代价敏感属性约简研究[J].计算机科学,2016,43(S2):67-72. [2] LPEZ V,FERNNDEZ A,MORENO-TORRES J G,et al.Analysis of preprocessing vs.cost-sensitive learning for imbalanced classification.Open problems on intrinsic data characteristics[J].Expert Systems with Applications,2012,39(7):6585-6608. [3] AODHA O M,BROSTOW G J.Revisiting Example Dependent Cost-Sensitive Learning with Decision Trees[J].2013,25(6):193-200. [4] 邓生雄,雒江涛,刘勇,等.集成随机森林的分类模型[J].计算机应用研究,2015,32(6):1621-1624. [5] 赵士伟,卓力,王素玉,等.一种基于NNIA多目标优化的代价敏感决策树构建方法[J].电子学报,2011,39(10):2348-2352. [6] BAHNSEN A C,AOUADA D,OTTERSTEN B.Example-dependent cost-sensitive decision trees[J].Expert Systems with Applications,2015,42(19):6609-6619. [7] 邓少军,冯少荣,林子雨.一种新的多分类代价敏感算法[J].厦门大学学报(自然科学版),2017,56(2):231-236. [8] THAI -NGHE N,GANTNER Z,SCHMIDT-T HIEME L.Cost-sensitive learning methods for imbalanced data[C]∥International Joint Conference on Neural Networks.IEEE,2010:1-8. [9] ZHOU Q,ZHOU H,LI T.Cost-sensitive feature selection using random forest:Selecting low-cost subsets of informative features[J].Knowledge-Based Systems,2016,95(3):1-11. [10] 王爱平,万国伟,程志全,等.支持在线学习的增量式极端随机森林分类器[J].软件学报,2011,22(9):2059-2074. [11] 张钰,陈珺,王晓峰,等.随机森林在滚动轴承故障诊断中的应用[J].计算机工程与应用,2017,3(6):312-319. [12] 胡记兵.基于决策树的组合分类器的构建和部署[D].杭州:浙江工业大学,2008:17-18. [13] SOFEIKOV K I,TYUKIN I Y,GORBAN A N,et al.Learning optimization for decision tree classification of non-categorical data with information gain impurity criterion[C]∥International Joint Conference on Neural Networks.IEEE,2014:3548-3555. [14] D’AMBROSIO A,TUTORE V A.Conditional Classification Treesby Weighting the Gini Impurity Measure[M]∥New Perspectives in Statistical Modeling and Data Analysis.Springer Berlin Heidelberg,2011:273-280. [15] 黄光鑫.支持向量数据描述与支持向量机及其应用[D].成都:电子科技大学,2011:64-66. |
| No related articles found! |
|
||
首页