期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于局部加权的Citation-kNN算法 被引量：8

Citation-kNN Algorithm Based on Locally-weighting
下载PDF
导出
摘要 Citation-kNN算法对传统的kNN算法进行了改进,使其可以应用于多示例学习问题,但其0-1决策方式具有一定的局限性,没有充分考虑样本的分布情况。为解决该问题,该文提出局部加权的Citation-kNN算法,综合考虑样本的分布情况,提出基于样本距离加权、基于样本离散度加权的方法,并对各种组合情况进行了实验。在标准数据集MUSK和乳腺超声图像数据库上的实验结果表明,该文提出的方法与Citation-kNN相比,性能有明显提高,并具有良好的适应性。 The Citation-kNN algorithm improves traditional kNN algorithm and can be applied to solve multi- instance learning issue. But its 0-1 decision strategy has some limitations. To overcome this issue, the locally-weighted Citation-kNN Mgorithm is presented in this paper. Considering distribution of the samples, the distance-based weighted method and the scatter-based weighted method are proposed. And their combinations are discussed. The method is applied to the standard database MUSK and the breast ultrasound image database. The results confirm that the method has higher accuracy comparing with that by using Citation-kNN algorithm.
作者 黄剑华 丁建睿 刘家锋 张英涛
机构地区 哈尔滨工业大学计算机科学与技术学院
出处 《电子与信息学报》 EI CSCD 北大核心 2013年第3期627-632,共6页 Journal of Electronics & Information Technology
基金 国家自然科学基金(61073128 61100097)资助课题
关键词 图像识别 多示例学习 Citation-kNN 样本分布 局部加权 Image recognition Multi-Instance Learning （MIL） Citation-kNN Distribution of samples Locallyweighted
分类号 TP391.41 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献1

二级参考文献48

  • 1Zhou Z-H, Zhang M-L. Solving multi-instance problems with classifier ensemble based on constructive clustering. Knowledge and Information Systems, 2006, in press.
  • 2Blockeel H, Page D, Srinivasan A. Multi-instance tree learning. In Proc. the 22nd Int. Conf. Machine Learning, Bonn, Germany, 2005.
  • 3Zhou Z-H, Xue X-B, Jiang Y. Locating regions of interest in CBIR with multi-instance learning techniques. Lecture Notes in Artificial Intelligence 3809, Zhang S, Jarvis R (eds.), Berlin: Springer, 2005, pp.92-101.
  • 4Dooly D R, Zhang Q, Goldman S A, Amar R A. Multipleinstance learning of real-valued data. Journal of Machine Learning Research, 2002, 3: 651-678.
  • 5Goldman S A, Scott S D. Multiple-instance learning of realvalued geometric patterns. Annals of Mathematics and Artificial Intelligence, 2003, 39(3): 259-290.
  • 6Weidmann N, Frank E, Pfahringer B. A two-level learning method for generalized multi-instance problem. Lecture Notes in Artificial Intelligence 2837, Lavrac N, Gamberger D, Blockeel H, Todorovski L (eds.), Berlin: Springer, 2003, pp.468- 479.
  • 7Scott S D, Zhang J, Brown J. On generalized multiple-instance learning. Technical Report UNL-CSE-2003-5, Department of Computer Science, University of Nebraska, Lincoln, NE, 2003.
  • 8Tao Q, Scott S, Vinodchandran N V, Osugi T T. SVM-based generalized multiple-instance learning via approximate box counting. In Proc. the 21st Int. Conf. Machine Learning, Banff, Canada, 2004, pp.779-806.
  • 9Tao Q, Scott S, Vino(ichandran N V, Osugi T T, Mueller B. An extended kernel for generalized multiple-instance learning. In Proc. the 16th IEEE Int. Conf. Tools with Artificial Intelligence, Boca Raton, FL, 2004, pp.272-277.
  • 10De Raedt L. Attribute-value learning versus inductive logic programming: The missing links. Lecture Notes in Artificial Intelligence 1446, Page D (ed.), Berlin: Springer, 1998, pp.1- 8.

共引文献11

同被引文献89

  • 1张海波,段会川,张曙光,刘弘.一种数字仪表显示值快速识别方法[J].计算机工程与应用,2005,41(4):223-226. 被引量：26
  • 2姜园,张朝阳,仇佩亮,周东方.用于数据挖掘的聚类算法[J].电子与信息学报,2005,27(4):655-662. 被引量：67
  • 3袁方,周志勇,宋鑫.初始聚类中心优化的k-means算法[J].计算机工程,2007,33(3):65-66. 被引量：152
  • 4边肇祺 张学工 等.模式识别[M].北京：清华大学出版社,2001..
  • 5Lauritzen S L. Graphical Models[M]. Oxford University Press,Oxford, U K, 1996: 21-31.
  • 6Manohar Shamaiah,Sang Hyun Lee, and Haris Vikalo.Graphical models and inference on graphs in genomics[J].IEEE Signal Processing Magazine, 2012, 29(1): 50-65.
  • 7Willsky A S. Multiresolution markov models for signal andimage processing[J], Proceedings of the IEEE, 2002, 90(8):1396-1458.
  • 8Srinivas Umamahesh and Yi Chen. Exploiting sparsity inhyperspectral image classification via graphical models [J].IEEE Geoscience and Remote Sensing Letters' 2013, 10(3):505-509.
  • 9Choi M J, Tan Vincent Y F, Anandkumar A, et al" Learninglatent tree graphical models [J]. Journal of Machine LearningResearch, 2011, 12: 1771-1812.
  • 10Chang J T and Hartigan J A. Reconstruction of evolutionarytrees from pairwise distributions on current species[C].Computing Science and Statistics: Proceedings of the 23rdSymposium on the Interface, Seattle, USA, 1991: 254-257.

引证文献8

二级引证文献22

电子与信息学报
2013年 第3期

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