期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：1
页码：316-318
语种：English
出版社：Ayushmaan Technologies
摘要：The ability to accurately estimate the time and/or cost taken fora project to come in to its successful conclusion is a serious problemfor software engineers. The use of a repeatable, clearly defnedand well understood software development process has, in recentyears, shown itself to be the most effective method of gaininguseful historical data that can be used for statistical estimation. Inparticular, the act of sampling more frequently, coupled with theloosening of constraints between parts of a project, has allowedmore accurate estimation and more rapid development times.Software effort estimation actually encompasses all estimation,risk analysis, scheduling, and SQA/SCM planning. However, inthe context of set of resources, planning involves estimation - yourattempt to determine how much money, how much effort, howmany resources, and how much time it will take to build a specifcsoftware-based system or product. In this paper we will studythe effciency of Neural Network based cost estimation modelwith the traditional cost estimation model like Halstead Model,Bailey-Basili Model, Doty Model. We conclude our result withthe proposal of Neuron based Model basis on Back propagationTechnique.
