Applying software metrics for the mining of design pattern

Development of desired software in the present day scenario is becoming too much complex as the user requirements becoming complex day-by-day. Hence there is a need for developing the right methodology for solving complex problem. To solve various problems in design phase, a number of tools and techniques are available and one of them is known as the use of design pattern, which helps to find a better solution for the problems, which are recurring in nature. It is often desired to detect design patterns from the source code of similar category of software, as it improves maintainability of source code of a software. In this study, mining of design pattern technique has been presented, which is based on supervised learning techniques as well as software metrics. During the pattern mining process, metrics-based dataset is developed. Subsequently, machine learning techniques such as Layer Recurrent Neural Network and Random Forest are applied for the pattern mining process. For the critical examination of the proposed study, data from an open source software e.g., JUnit is considered for the mining of software patterns.