期刊文献+

面向宏观地表分类的特征选择算法比较研究 被引量:1

Comparative study of feature selection methods for regional land cover classification
下载PDF
导出
摘要 为了成功将土地覆盖进行分类,选择合适的特征是至关重要的。针对利用MODIS数据进行宏观土地覆盖的分类问题,对三种典型的特征选择方法进行了比较研究。研究结果表明:分支定界法(BB)最适合于该土地覆盖分类问题,与此同时,ReliefF和mRMR方法在目标应用中的精度非常接近。研究结果同样表明进行特征选择是非常必要的,它不仅能够大大地降低计算复杂度,而且分类精度能够保持不变,甚至更高。 Selecting suitable features is very crucial for achieving successful classification of land cover types.This paper presents a comparative study of three typical feature selection methods for the task of regional land cover classification using MODIS data.Comparison results have shown that Branch and Bound is the best for land cover classification with MODIS data,while ReliefF and mRMR achieve nearly the same accuracies on the target application.The experimental results also show that it is necessary to conduct feature selection,which can reduce the computation cost largely,while the accuracy remains the same or even better.
出处 《计算机工程与应用》 CSCD 北大核心 2008年第21期130-132,170,共4页 Computer Engineering and Applications
基金 国家自然科学基金(the National Natural Science Foundation of China under Grant No.60673141)
关键词 特征选择 土地覆盖分类 分支定界 RELIEFF mRMR feature selection land cover classification branch and bound ReliefF mRMR
  • 相关文献

参考文献18

二级参考文献100

  • 1李国正,杨杰,孔安生,陈念贻.基于聚类算法的选择性神经网络集成[J].复旦学报(自然科学版),2004,43(5):689-691. 被引量:15
  • 2洪家荣,丁明峰,李星原,王丽薇.一种新的决策树归纳学习算法[J].计算机学报,1995,18(6):470-474. 被引量:92
  • 3权光日,崔明根,张朝晖,洪家荣.基于Hopfield-Tank模型的神经网络的变参数方法[J].电子学报,1996,24(8):87-89. 被引量:7
  • 4陈彬,洪家荣,王亚东.最优特征子集选择问题[J].计算机学报,1997,20(2):133-138. 被引量:96
  • 5蔡元龙.模式识别[M].西安:西安电子科技大学出版社,1992.67-69.
  • 6钱国良.基于机器学习的手写汉字识别的研究与实现[硕士论文].哈尔滨:哈尔滨工业大学,1995..
  • 7Friedl M A. Maximizing Land Cover Classification Accurac-ies Produced by Decision Trees at Continental to Global Scales[J]. IEEE Trans Geosci Remote Sensing,1999,37:969-977.
  • 8Enhanced Vegetation Index (EVI)[R]. http://tbrs.arizona.edu/project/MODIS/evi.php,2003.
  • 9Mcfeeters S K. The Use of the Normalized Difference Water Index(NDWI)in the Delineation of Open Water Features[J]. Int J Remote Sensing,1996,17(7):1425-1432.
  • 10Borak J S, Strahler A H. Feature Selection and Land Cover Classification of a MODIS-like Data Set for a Semiarid Environment[J]. Int J Remote Sensing,1999,20:919-938.

共引文献95

同被引文献13

  • 1顾志伟,吴秀清,荆浩,尹东,王艺元.一种基于特征选择的医学图像检索方法[J].中国生物医学工程学报,2007,26(1):30-34. 被引量:9
  • 2LIU Huan, YU Lei. Toward integrating feature selection algorithms for classification and clustering [ J ]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(4) : 491 -502.
  • 3DING C, PENG H. Minimum redundancy feature selection from microarray gene expression data[ J ]. Journal of Bioinformatics and Computational Biology, 2005, 3 (2) : 185 - 205.
  • 4VAPNIK V. The nature of statistical learning theory [ M ]. New York : Springer Verlag, 2000.
  • 5YOON Sejong, KIM Saejoon. Mutual information-based SVM-RFE for diagnostic classification of digitized mam mograms [ J ]. Pattern Recognition Letter, .2009, 30(16) : 1489 - 1495.
  • 6OPHIR J, CESPEDES I, PONNEKANTI H, et al. Elas-tography: a quantitative method for imaging the elasticity of biological tissues [J]. Ultrasonic imaging, 1991, 13 (2) : 111 - 134.
  • 7SHIINA T, YAMAKAWA M, NITTA N, et al. Clinical assessment of real-time, freehand elasticity imaging sys- tem based on the combined autocorrelation method [ C ]//Proceedings of the IEEE Ultrasonics Sympos. Washington : IEEE Xplore, 2003 : 664 - 667.
  • 8Shirley SELVAN M K, SHENBAGADEVI S, SURESH S. Feature extraction for characterization of breast lesions in ultrasound echography and elastography [ J ]. Journal of Computer Science, 2010, 6( 1 ) : 67 -74.
  • 9Huang Chiun-Sheng, MOON Woo-Kyung, SHEN WeiChih, et al. Analysis of elastographic and B-Mode fea- tures at sonoelastography for breast tumor classification [ J ]. Ultrasound in Medicine and Biology, 2009, 35(11) :1794 - 1802.
  • 10NEWELL D, NIE K, CHEN J H, et al. Selection of diagnostic features on breast MRI to differentiate between malignant and benign lesions using computer-aided diagnosis : differences in lesions presenting as mass and nonmass-like enhancement [ J ]. European Radiology, 2010, 20(4) : 771 -781.

引证文献1

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部