期刊名称：Journal of Industrial Engineering and Management Science
电子版ISSN：2446-1822
出版年度：2018
卷号：2016
期号：1
页码：43-58
DOI：10.13052/jiems2446-1822.2016.003
语种：English
出版社：River Publishers
摘要：In the past, many software reliability models have been proposed by several researchers. Also, several model selection criteria such as Akaike’s information criterion, mean square errors, predicted relative error and so on, have been used for the selection of optimal software reliability models. These assessment criteria can be useful for the software managers to assess the past trend of fault data. However, it is very important to assess the prediction accuracy of model after the end of fault data observation in the actual software project. In this paper, we propose a method of optimal software reliability model selection based on the deep learning. Moreover, we show several numerical examples of software reliability assessment in the actual software projects. In particular, we discuss the optimal release time and total expected software cost in terms of the model selection based on the deep learning.
关键词：Software reliability model; optimal model selection; deep
learning; optimal release time; software cost
