文章基本信息

标题：Evolutionary Computing Techniques for Software Effort Estimation
本地全文：下载
作者：Sumeet Kaur Sehra ; Yadwinder Singh Brar ; Navdeep Kaur 等
期刊名称：International Journal of Computer Science & Information Technology (IJCSIT)
印刷版ISSN：0975-4660
电子版ISSN：0975-3826
出版年度：2017
卷号：9
期号：2
页码：123
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Reliable and accurate estimation of software has always been a matter of concern for industry andacademia. Numerous estimation models have been proposed by researchers, but no model is suitable for alltypes of datasets and environments. Since the motive of estimation model is to minimize the gap betweenactual and estimated effort, the effort estimation process can be viewed as an optimization problem to tunethe parameters. In this paper, evolutionary computing techniques, including, Bee colony optimization,Particle swarm optimization and Ant colony optimization have been employed to tune the parameters ofCOCOMO Model. The performance of these techniques has been analysed by established performancemeasure. The results obtained have been validated by using data of Interactive voice response (IVR)projects. Evolutionary techniques have been found to be more accurate than existing estimation models
关键词：Machine Learning; COCOMO; MMRE; Evolutionary computing