Neural Network-Based Model for the Quality Assessment of Object-Oriented Software

Abstract

Software quality assessment is an important subject among the researchers in the software development domain. The quality assessment is generally done either at the design level through some of the design attributes or through code when the product is ready. These two types of software quality are referred to as design quality and product quality, respectively. Several techniques and tools are available that facilitate to assess the design as well as the product quality of software. In this paper, a neural network model is proposed for the assessment of quality of object-oriented software at the product level. The authors select a subset of existing object-oriented metrics that are normalized at three levels and used to find quality factors like understandability, reusability, flexibility, maintainability, reliability, extensibility, and modifiability for the model development. The model is validated by assessing quality levels of 33 open source object-oriented software of different design complexities and observing a high correlation between these quality levels in comparison with an existing model.