Download Now Free registration required
A relevant sub area of reverse engineering is identification of modules requiring re engineering, which focuses on predicting faulty modules. To this end, predicting faulty modules may use any available source of information such as source code and documentation. Similarly, the identified abstractions may take different forms such as module breakdown, structure-charts, entity-relationship diagrams, and software metric specifications. In this paper it is proposed to investigate the classification accuracy of random tree algorithms for software defect prediction.
- Format: PDF
- Size: 169.7 KB