Predictive accuracy comparison of fuzzy models for software development effort of small programs
Journal of Systems and Software
Predicting Software Fault Proneness Model Using Neural Network
PROFES '08 Proceedings of the 9th international conference on Product-Focused Software Process Improvement
| Hi-index | 0.00 |
A novel neuro-fuzzy Constructive Cost Model(COCOMO) for software estimation is proposed. Themodel carries some of the desirable features of the neuro-fuzzy approach, such as learning ability and goodinterpretability, while maintaining the merits of theCOCOMO model. Unlike the standard neural networkapproach, this model is easily validated by experts andcapable of generalization. In addition, it allows inputs tobe continuous-rating values and linguistic values,therefore avoiding the problem of similar projects havingdifferent estimated costs. Also presented in this paper is adetailed learning algorithm. The validation, usingindustry project data, shows that the model greatlyimproves the estimation accuracy in comparison with thewell-known COCOMO model.