Due to the rapid development of computers and their applications, early software quality prediction in software industry becomes more and more cruciaL Software quality prediction model is very helpful for decision-mak...Due to the rapid development of computers and their applications, early software quality prediction in software industry becomes more and more cruciaL Software quality prediction model is very helpful for decision-makings such as the allocation of resource in module verification and validation. Nevertheless, due to the complicated situations of software development process in the early stage, the applicability and accuracy of these models are still under research. In this paper, a software quality prediction model based on a fuzzy neural network is presented, which takes into account both the internal factors and external factors of software. With hybrid-learning algorithm, the proposed model can deal with multiple forms of data as well as incomplete information, which helps identify design errors early and avoid expensive rework.展开更多
基金Supported by the National Defense Pre-research Project
文摘Due to the rapid development of computers and their applications, early software quality prediction in software industry becomes more and more cruciaL Software quality prediction model is very helpful for decision-makings such as the allocation of resource in module verification and validation. Nevertheless, due to the complicated situations of software development process in the early stage, the applicability and accuracy of these models are still under research. In this paper, a software quality prediction model based on a fuzzy neural network is presented, which takes into account both the internal factors and external factors of software. With hybrid-learning algorithm, the proposed model can deal with multiple forms of data as well as incomplete information, which helps identify design errors early and avoid expensive rework.
