Predicting Reliability of Object-Oriented Systems Using a Neural Network

One of the most important quality attributes of computer systems is reliability, which addresses the ability of the software to perform its required function under stated conditions for a stated period of time. The paper aim is twofold. Firstly, the proposed approach explores how to define a metric to qualify the sub-aspects comprised in ISO 25010 regarding reliability as maturity and availability. Secondly, we investigate to what extent the internal structure of the system quantified by the Chidamber and Kemerer (CK) metrics may be used to predict reliability. The approach for prediction is a feed-forward neural network with back-propagation learning. The results indicate that CK metrics are promising in predicting reliability using a neural network method.