第21卷第8期 2013年8月
文章编号
1004-924X(2013)08-2121-08
光学精密工程
Optics and Precision Engineering
Vol.21No.8
Aug.2013
面向田间籽棉成熟度判别的二种特征选择算法比较
王玲，刘德营，姬长英“
（南京农业大学工学院/江苏省现代设施农业技术与装备工程实验室，江苏南京210031）
摘要：为了快速、准确地判别田间籽棉的成熟度，提取了描述棉期形状的15个结构特征，基于10折交叉验证比较了封装器下穷举搜索并基于封装器停止搜索(WE-W)和过滤器下启发式搜索并基于封装器停止搜索(FH-W)这二种特征选择算法的执行效率和分类性能。分别以验证集上Bayes分类器的误分率(WE-W)和训练集上的类可分性测量值（FH-W）为评价函数，在训练集上穷举搜索(WE-W)和启发式搜索(FH-W)最优（维特征子集，I=1，2，"，15，并于Bayes分类器在验证集上的平均误分率极小时停止搜索（WE-W和FH-W)。结果显示，WE-W和FH-W算法在预测集上于[=3处分别获得了85.39%（WE-W)和85.28%(FH-W)的平均识别率，表明FH-W算法执行效率高、分类性能好，对实际应用有参考意义。
关键调：籽棉成熟度;封装器；穷举搜案索；过滤器；启发式搜索；特征选择
中图分类号：TP391.4
文献标识码：A
doi;10.3788/OPE.20132108.2121
Comparisonoftwofeatureselectionalgorithmsorientedto
rawcottonripenessdiscrimination WANGLing,LIUDe-ying,JIChang-ying
(CollegeofEngineering,NanjingAgriculturalUniversity/JiangsuProuinceEngineering LabforModernFacitityAgricultureTechnology&Equipment,Nanjing210031,China)
Correspondingauthor,E-mail:chyji@njau.edu.cn
Abstract: To discriminate the ripeness of cotton quickly and accurately, 15 shape structure features were extracted from cotton images and the execute efficiencies and classification accuracy of their fea ture subset selection algorithms such as Wrapper-based Exhaustive searching and Wrapper-based stop ping(WE-W) and Filter-based Heuristic searching and Wrapper-based stopping(FH-W) were com-pared by using 1o-fold cross-validation. By taking the error rate of a Bayes classifier on validation set(WE-W) and the class-separability measuring value on a training set (FH-W)as assessing functions, the optimal / (/=1,2,3, -**, 15) feature subset was searched by using exhaustive (WE-W) and heu-ristic (FH-W) strategies on the training set, which stops at the minimum error rate of Bayes-classifier on the validation set(WE-W and FH-W). Experimental results show that the average classification rates of WE-W and FH-W algorithms on the prediction set are 85.39% (WE-W) and 85.28% (FH-W) at /=3, respectively. It concludes that the FH-W algorithm can be a reference in practice for its
收稿日期：2013-02-07；修订日期：2013-03-14.
基金项目：国家863高技术研究发展计划资助项目（No，2006AA10Z259)；江苏省农机基金资助（No，GXZ10007）