计算机科学 ›› 2015, Vol. 42 ›› Issue (5): 54-56.doi: 10.11896/j.issn.1002-137X.2015.05.011
黄 源,李 茂,吕建成
HUANG Yuan, LI Mao and LV Jian-cheng
摘要： 开方检验是目前文本分类中一种常用的特征选择方法。该方法仅关注词语和类别间的关系,而没有考虑词与词之间的关联,因此选择出的特征集具有较大的冗余度。定义了词语的“剩余互信息”概念,提出了对开方检验的选择结果进行优化的方法。使用该方法可以得到既有很强表征性又有很高独立性的特征集。实验表明,该方法表现良好。
| [1] 胡洁.高维数据特征降维研究综述[J].计算机应用研究,2008,25(9):2601-2606 [2] John H,Kohavi R,Pfleger K.Irrelevant feature and the subset selection problem[C]∥Proc.of the 11th Int.Conf.on Machine Learning,1994.San Francisco:Morgan Kaufmann Publishers,1994:121-129 [3] Jasper.文本分类入门(十)特征选择算法之开方检验.2008-08-31[2014-01-18].http://www.blogjava.net/zhenandaci/archive/2008/08/31/225966.html [4] Yu Lei,Liu Huan.Efficient Feature Selection via Analysis ofRelevance and Redundancy[J].Journal of Machine Learning Research,2004,10(5):1205-1224 [5] Battiti R.Using mutual information for selecting features in supervised neural net learning[J].IEEE Trans.Neural Network,1994,5(4):537-550 [6] Estevez P,Tesmer M,Perez C,et al.Normalized mutual information feature selection[J].IEEE Trans.Neural Network,2009,20(2):189-201 [7] Sun X,Liu Y,Xu M,et al.Feature selection using dynamicweights for classification[J].Knowledge-Based Systems,2013,37:541-549 [8] Li B,Chow T W S,Huang D.A novel feature selection methodand its application[J].Journal of Intelligent Information Systems,2013,41(2):235-268 [9] Lee S,Park Y T,d’Auriol B J.A novel feature selection method based on normalized mutual information[J].Applied Intelligence,2012,37(1):100-120 [10] Aliferis C F,Statnikov A,Tsamardinos I,et al.Local causal and markov blanket induction for causal discovery and feature selection for classification part i:Algorithms and empirical evaluation[J].The Journal of Machine Learning Research,2010,11:171-234 [11] Lv Jian-cheng,Tan K K,Zhang Yi,et al.A family of fuzzy lear-ning algorithms for robust principal component analysis neural networks[J].IEEE Transactions on Fuzzy Systems,2010,18(1):217-226 [12] Lv Jian-cheng,Zhang Yi,Tan K K.Global Convergence of Oja’s PCA Learning Algorithm with a Non-Zero-Approaching Adaptive Learning Rate[J].Theoretical Computer Science,2006,367(3):286-307 |
| No related articles found! |
|
||
首页