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：4
页码：419-421
语种：English
出版社：Ayushmaan Technologies
摘要：In Software engineering, there are a plenty of prediction approaches used for several purposes like fault prediction, security prediction, effort prediction, correction cost prediction, reusability prediction, test effort prediction and quality prediction. These approaches help to minimize the cost of testing which minimizes the cost of the project. In this paper, we study software fault prediction techniques to find the software defects at an early stage of software development life cycle. The methods, metrics and datasets are used to find the fault-proneness of software. The various techniques like linear regression, logistic regression, negative binomial regression, fuzzy subtractive clustering, radial basis function (RBF) network, multilayer perceptron, support vector machine, artificial neural networks, instance-based reasoning, Bayesian-belief networks, decision trees, rule induction, multi-linear regression models, multivariate models, back propagation neural Network (BPN), probabilistic neural network (PNN), expert estimation and nearest neighbor are used to predict the fault proneness of the software. Each of these has its own advantages and disadvantages.
关键词：Statistical;Machine learning;Statistical and Machine learning; Statistical vs. Expert estimation;Nearest Neighbor
