A Combined Ant Colony Optimization and Simulated Annealing Algorithm to Assess Stability and Fault-Proneness of Classes Based on Internal Software Quality Attributes
Several machine learning algorithms have been used to assess external quality attributes of software systems. Given a set of metrics that describe internal software attributes (cohesion, complexity, size, etc.), the purpose is to construct a model that can be used to assess
external quality attributes (stability, reliability, maintainability, etc.) based on the internal ones. Most of these algorithms result in assessment models that are hard to generalize. As a result, they show a degradation in their assessment performance when used to estimate
quality of new software modules. This paper presents a hybrid heuristic to construct software quality estimation models that can be used to predict software quality attributes of new unseen systems prior to re-using them or purchasing them. The technique relies on two heuristics: simulated annealing and ant colony optimization. It learns from the data available in a particular domain guidelines and rules to achieve a particular external software quality. These guidelines are presented as rule-based logical models. We validate our technique on two software quality attributes namely stability and fault-proneness - a subattribute of maintainability. We compare our technique to two state-of-the-art algorithms: Neural Networks (NN) and C4.5 as well as to a previously published Ant Colony Optimization algorithm. Results show that our hybrid technique out-performs both C4.5 and ACO in most of the cases. Compared to NN, our algorithm preserves the white-box nature of the predictive models hence, giving not only the classification of a particular module but also guidelines for software engineers to follow in order to reach a particular external quality attribute. Our algorithm gives promising results and is generic enough to apply to any software quality attribute.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.thentic information.