1. 湖北省农业科学院 农业经济技术研究所,湖北,武汉,430064
2. 中国地质大学(武汉)信息工程学院,湖北,武汉,430074
纸质出版:2018
移动端阅览
马海荣, 程新文. 一种处理非平衡数据集的优化随机森林分类方法[J]. 微电子学与计算机, 2018, 35(11): 28-32.
MA Hai-rong, CHENG Xin-wen. A Method for Unbalanced Big Data Classification Based on Optimization Random Forest[J]. 2018, 35(11): 28-32.
利用传统随机森林(random forest
RF)模型进行分类时存在分类精度受不平衡样本集的影响
以及投票平局现象会导致算法停滞等问题.本文对RF模型进行了优化改进
首先随机抽取等量的少数类与多数类样本构建训练样本集进行RF建模
然后根据投票熵与基于样本特征参数的广义欧几里得距离逐步添加具有最大投票熵的样本到训练样本集
解决传统RF模型随机抽取样本时训练样本集中包含不同类别样本数不平衡问题.对于分类过程中可能出现投票结果的平局现象
利用测试样本与邻近训练样本的广义欧几里得距离决定其分类结果
以消除投票平局现象造成的停滞问题.实验结果表明
本文优化RF模型对于非平衡数据集的分类可以取得较好的分类结果.
When utilized traditional random forest (RF) model for classification
there were following problems exist:for example
the classification accuracy was affected by the unbalanced sample set
equality votes of each class would lead to algorithms stalling. We improved the traditional RF model
first of all
we randomly selected the same number of samples from minority class and majority class to build training sample set for RF modeling. Then
according to the voting entropy and the generalized Euclidean distance based on the sample characteristic parameters gradually add the sample with maximum voting entropy to the training sample set. This could solve the problem that in traditional RF model training samples randomly selected contained too few minority class samples. In the classification process when the voting draw occurs
we utilized the generalized Euclidean distance between the test samples and the adjacent training samples to determine the classification result
this would eliminate the stagnation caused by the equality votes of each class. The experimental results show that the optimized RF model in this paper could achieve better classification results for unbalanced data sets.
Behling R, Roessner S, Kaufmann H, et al. Automated spatiotemporal landslide mapping over large areas using rapid eye time series data[J]. Remote Sensing, 2014, 6(9):8026-8055. DOI: 8026
Weiss G M.Mining with rarity:a unifying framework[J].Acm Sigkdd Explorations Newsletter, 2004, 6(1):7-19. DOI: 7
刘亚东, 崔日鲜.基于可见光光谱和随机森林算法的冬小麦冠层图像分割[J].光谱学与光谱分析, 2015, 35(12):3480-3484. DOI: 3480
秦静, 钱雪忠, 王卫涛, 等.一种处理不平衡大数据的并行随机森林算法[J].微电子学与计算机, 2017, 34(4):22-27. DOI: 22
Stumpf A, Kerle N. Combining random forests and object-oriented analysis for landslide mapping from very high resolution imagery[J]. Procedia Environmental Sciences, 2011, 3(1):123-129. DOI: 123
马越, 贺光辉.一种改进的基于随机森林的快速人眼定位方法[J].微电子学与计算机, 2016, 33(7):1-4. DOI: 1
焦盛岚, 杨炳儒, 翟云, 等.一种用于非平衡数据分类的集成学习模型[J].计算机工程与应用, 2012, 48(29):119-123. DOI: 119
Martha T R, Kerle N, Westen C J V, et al.Object-oriented analysis of multi-temporal panchromatic images for creation of historical landslide inventories[J].Isprs Journal of Photogrammetry % Remote Sensing, 2012, 67(2):105-119. DOI: 105
曹正凤.随机森林算法优化研究[D].北京: 首都经济贸易大学, 2014.
Breiman L.Random forests[J].Machine Learning, 2001, 45(1):5-32. DOI: 5
Ho T K.The random subspace method for constructing decision forests[J].IEEE Transactions on Pattern Analysis % Machine Intelligence, 1998, 20(8):832-844. DOI: 832
赵悦, 穆志纯.基于委员会投票选择方法的主动学习的研究[J].太原理工大学学报, 2006, 37(4):469-472. DOI: 469
尹留志.关于非平衡数据特征问题的研究[D].合肥: 中国科学技术大学, 2014.
陈荣鑫.R软件的数据挖掘应用[J].重庆工商大学学报(自然科学版), 2011, 28(6):602-607. DOI: 602
0
浏览量
23
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号