A Comparative Evaluation of Feed Forward Back Propagation Neural Network Model Trained with Different Transfer Functions for the Software Development Effort Estimation
Roheet Bhatnagar1 and Vandana Bhattacharjee2
1Department of Computer Science & Engineering, Sikkim Manipal Institute of Technology, Majitar, Rangpo, East Sikkim, Sikkim, 737136, India.
2Department of Computer Science & Engineering, Birla Institute of Technology, BITEC Lalpur, Mesra, Ranchi, Jharkhand, 835215, India.
Estimating software development effort is an important task in the management of software projects. The task of effort estimation is challenging and is an important area of research in the field of Software Project Management. A number of estimation models exist for effort prediction. However, many newer models are still being proposed and reserached upon to obtain more accurate estimations. Neural Network as a soft computing technique is one such tool to predict the effort estimation and in this paper also we estimated the development time using Feed Forward Back Propagation (FFBP) neural network trained with different training functions. In this paper we have compared the FFBP outputs using standard effort evaluation criteria MRE (Mean Relative Error). We have used the standard NASA Project dataset for our experimental studies.
Keywords: Software development effort estimation, Neural network, Software project management, Effort estimation models.
Back to TOC