贝叶斯校正算法在软件估算模型COCOMOⅡ中的应用  

IMPLEMENTATION OF BAYESIAN CALIBRATION IN THE SOFTWARE ESTIMATE MODEL COCOMOⅡ

作　　者：丁岳伟[1] 马亦舟[1] 

机构地区：[1]上海理工大学计算机工程学院,上海200093

出　　处：《计算机应用与软件》2007年第1期151-153,159,共4页Computer Applications and Software

基　　金：上海市教委发展基金资助项目(03GK16)。

摘　　要：软件估算模型COCOMOⅡ的研究目标在于建立起一个能够适用于当前的软件开发并且每年更新的模型,使之能够估算软件开发活动中的成本、工作量及时间安排。为了提高COCOMOⅡ的估算精度,采用归纳性的分析方法———贝叶斯校正算法对其进行校正,在逻辑一致的基础上根据先验信息和样本信息作出推论,得到的后验结果能够较大幅度提高估算精度,是对COCOMOⅡ模型的进一步完善。The COCOMOⅡ research effort is concentrated on developing a model well-suited for the contemporary software development and then annually updating it for the forthcoming years,which allows one to estimate the Cost, effort, and schedule when planning a new software development activity. In order to improve the estimate accuracy of COCOMOⅡ, Bayesian calibration, one generalized analysis method, is adopted to calibrate the model. It arrives, on the basis of both prior information and sample information in a logically consistent manner, at the posterior result which can makes the estimate more aceurate in big degree and definitely improves the COCOMOⅡ Model.

关 键 词：软件成本估算 COCOMOⅡ 贝叶斯校正算法 多元回归算法 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]