Reza Akbari

Nahid Hajizadeh, Peyman Jahanbazi, Reza Akbari

Software product line represents software engineering methods, tools and techniques for creating a group of related software systems from a shared set of software assets. Each product is a combination of multiple features. These features are known as software assets. So, the task of production can be mapped to a feature subset selection problem which is an NP-hard combinatorial optimization problem. This issue is much significant when the number of features in a software product line is huge. In this paper, a new method based on Multi Objective Bee Swarm Optimization algorithm (called MOBAFS) is presented. The MOBAFS is a population based optimization algorithm which is inspired by foraging behavior of honey bees. The is used to solve a SBSE problem. This technique is evaluated on five large scale real world software product lines in the range of 1,244 to 6,888 features. The proposed method is compared with the state-of-the-art, SATIBEA. According to results of three solution quality indicators and two diversity metrics, the proposed method, in most cases, surpasses the other algorithm.

Ahmad Hasanpour, Pourya Farzi, Ali Tehrani et al.

In recent years, defect prediction, one of the major software engineering problems, has been in the focus of researchers since it has a pivotal role in estimating software errors and faulty modules. Researchers with the goal of improving prediction accuracy have developed many models for software defect prediction. However, there are a number of critical conditions and theoretical problems in order to achieve better results. In this paper, two deep learning models, Stack Sparse Auto-Encoder (SSAE) and Deep Belief Network (DBN), are deployed to classify NASA datasets, which are unbalanced and have insufficient samples. According to the conducted experiment, the accuracy for the datasets with sufficient samples is enhanced and beside this SSAE model gains better results in comparison to DBN model in the majority of evaluation metrics.