Performance Analysis of Software Effort Estimation Models Using Neural Networks
E. Praynlin, P. Swarna Latha · International Journal of Information Technology and Computer Science · 2013
Software Effo rt estimat ion involves the estimation of effort required to develop software.Cost overrun, schedule overrun occur in the software development due to the wrong estimate made during the initial stage of software development.Proper estimation is very essential for successful comp letion of software development.Lot of estimation techniques available to estimate the effort in which neural network based estimation technique play a pro minent role.Back propagation Network is the most widely used architecture.ELMAN neural network a recurrent type network can be used on par with Back propagation Network.For a good predictor system the difference between estimated effo rt and actual effort should be as low as possible.Data fro m historic pro ject of NASA is used for training and testing.The experimental Results confirm that Back propagation algorith m is efficient than Elman neural network.