计算机工程2012，Vol.38Issue(21)：36-39,4.DOI:10.3969/j.issn.1000-3428.2012.21.010
基于加权偏最小二乘回归的软件成本估算方法
Software Cost Estimation Method Based on Weighted Partial Least Squares Regression
摘要
Abstract
For the excessiveness of operating factors and multi-correlation of variables in software cost estimation, this paer proposes a software cost estimation method based on Partial Least Squares Regression(PLSR). After the variables are weighted, an integrated index named analogue deviation is defined to describe the approximation of data samples. Then an adaptive weight is assigned to sample according to the approximation, and the optimal partial least squares latent variables and weight parameters are calculated by traversal searching. Experimental results show that the prediction error is reduced by 73.61% and 32.34% than multiple linear regression and PLSR respectively.关键词
软件成本估算/偏最小二乘回归/相似离度/权重/信息熵/多重相关性Key words
software cost estimation/ Partial Least Squares Regression(PLSR)/ analogue deviation/ weight/ information entropy/ multi-correlation分类
信息技术与安全科学引用本文复制引用
刘海涛,魏汝祥,蒋国萍..基于加权偏最小二乘回归的软件成本估算方法[J].计算机工程,2012,38(21):36-39,4.基金项目
海军工程大学自然科学基金资助项目(HGDONJJ042) （HGDONJJ042）
