zoukankan      html  css  js  c++  java
  • 读文章论文

    论文

    Software defect association mining and defect correction effort prediction

    Type:缺陷预测

    Published in:Software Engineering, IEEE Transactions on (Volume:32 ,  Issue: 2) 

    Abstract:

    Much current software defect prediction work focuses on the number of defects remaining in a software system. In this paper, we present association rule mining based methods to predict defect associations and defect correction effort. This is to help developers detect software defects and assist project managers in allocating testing resources more effectively. We applied the proposed methods to the SEL defect data consisting of more than 200 projects over more than 15 years. The results show that, for defect association prediction, the accuracy is very high and the false-negative rate is very low. Likewise, for the defect correction effortprediction, the accuracy for both defect isolation effort prediction and defectcorrection effort prediction are also high. We compared the defect correction effort prediction method with other types of methods - PART, C4.5, and Naive Bayes - and show that accuracy has been improved by at least 23 percent. We also evaluated the impact of support and confidence levels on prediction accuracy, false-negative rate, false-positive rate, and the number of rules. We found that higher support and confidence levels may not result in higher prediction accuracy, and a sufficient number of rules is a precondition for high prediction accuracy.

    Authors:Qinbao Song ; Dept. of Comput. Sci. & Technol., Xi''an Jiaotong Univ., China ; Shepperd, M. ; Cartwright, M. ; Mair, C.

    Link:http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1599417

  • 相关阅读:
    从VS转MyEclipse的15天使用体验
    JSP标签
    cookie实现自动登录
    js中substring和substr的用法
    用原生sql查询返回实体对象的方法
    @Column
    event.keyCode用法及列表
    jQuery的选择器中的通配符[id^='code']
    struts2中<s:radio>标签设置默认选中项
    在Struts2中实现登陆后跳转到登录前页面
  • 原文地址:https://www.cnblogs.com/aappkkee/p/4521223.html
Copyright © 2011-2022 走看看