全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种改进的AdaBoost算法——M-AsyAdaBoost

Keywords: M-Asy,AdaBoost,分类器,分类器集,Asymmetric,AdaBoost

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出一种AsymmetricAdaBoost改进算法——M-AsyAdaBoost.M-AsyAdaBoost算法通过新的样本权重分配方式可以确保训练过程不失败;分类器权重采用对正样本的分类错误率形成优化权重,突出对正样本的识别能力,提高检测概率;并且通过对加入分类器集的分类器的限制,使检测概率单调增加.该算法在较低虚警概率下,达到高检测概率.计算机仿真结果验证了算法的正确性.

References

[1]  Suncion A;Newman D J UCI machine learning repo sitory 2008
[2]  Shapley L;Grofman B,Optimizing group judgmental accuracy in the presence of interdependencies,Public Choice? ,1984, 43.
[3]  李闯,丁晓青,吴佑寿.-种改进的AdaBoost算法--AD AdaBoost[J].计算机学报,2007(01)
[4]  Fan Wei;Stolfo S;Zhang Junxin,Adacost:Misclassification cost-sensitive boosting,Bled,Slovena:[s.n.],1999.
[5]  Ma Yong;Ding Xiaoqing,Real-time rotation invariant face detection based on cost-sensitive AdaBoost,Spain:Barcelona,2003.
[6]  Viola P;Jones M,Fast and robust classification using asymmetric AdaBoost and a detector cascade,Cambridge,ma:the Mit Press,2002.
[7]  Viola P;Jones M J,Robust real-time object detection,Vancouver,Canada:[s.n],2001.
[8]  Freund Y. ;Schapire RE.,A DECISION-THEORETIC GENERALIZATION OF ON-LINE LEARNING AND AN APPLICATION TO BOOSTING,Journal of Computer and System Sciences?,1997, 55(1).

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133