Belle实验中神经元网络和Fisher判别方法应用于压制连续过程本底的比较(英文)  

Comparison between neural networks and Fisher discriminant for continuum background suppression at Belle

作　　者：刘超[1] 张子平[1] 

机构地区：[1]中国科学技术大学近代物理系,安徽合肥230026

出　　处：《中国科学技术大学学报》2011年第1期62-65,共4页JUSTC

基　　金：Supported by NSFC(10935008,10875115);the Doctoral Program of Chinese Education Ministry(20070358060)

摘　　要：在Belle实验B±→K±ω道的物理分析中,对神经元网络法和Fisher判别法在压制连续过程本底应用中的性能进行了比较研究.应用神经元网络法可以获得对BB信号事例42.3%的选择效率和99.2%的连续过程本底排除水平;应用Fisher判别法可以获得57.9%的信号事例选择效率和98.6%的连续过程本底排除水平.The neural networks method and Fisher discriminant method for continuum background suppression were applied to the analysis of B±→K±ω decay respectively.A comparison was conducted of the effects of the two methods.With neural network,42.3% of the B B events can be preserved while 99.2% of continuum background is rejected.With Fisher discriminant,57.9% of the signal can be preserved while 98.6% of the continuum background is rejected.

关 键 词：神经元网络法 Fisher判别法 Belle实验 B介子衰变 

分 类 号：O572.21[理学—粒子物理与原子核物理]