Comparison of hard limiting and soft computing methods for predicting software effort estimation: In reference to Small Scale Visualization Projects

T M Kiran Kumar,M A Jayaram

doi:10.14419/ijet.v7i4.6.21195

Abstract

It is a well known fact that software effort estimation is exceptionally critical in every software industry, particular during the development of projects. It is hard to estimate the parameters involved due to ambiguity and uncertainty associated with the parameters. It is exactly here the hard limiting techniques, soft computing techniques comes to play. In this unique circumstance, this paper, presents an attempt to that compare the two paradigms for effort estimation. For this, we have considered fifty real time small visualization projects thrive by post graduate students. The prototype development involves following stages: i) Elicitation of seven novel parameters namely Lines of Code, Cumulative Grade Point Average, New and changed code, Reused code, Cyclomatic Complexity, Algorithmic Complexity and Functional Points. ii) Developing of hard limiting methods and soft computing methods for prediction of software effort involved in terms of duration in minutes.For the validation of the models error metrics namely: Mean Absolute Error (MAE), Mean Magnitude of Relative Error (MMRE), Mean of Magnitude of error Relative to the Estimate (MMER) and Root Mean Square Error (RMSE) have been used. The result showed that the models compared very well with marginal difference in terms of predict values of error matrix.

Highlights

Estimation of the effort is the way towards the effort enforced to build a model placed on deficient, vague or questionable guidance
In hard limiting techniques we have used two regression models and in soft computing method we have used neural network and fuzzy inference system with the development of the fuzzy predictive model on the proceeds of the real-time laboratory work performed by the fifty post graduate students
This paper presents the comparison approach adapted to predict software effort involved while developing fifty varied small visualization projects attempted by post graduation students in almost industry setting

Summary

Introduction

Estimation of the effort is the way towards the effort enforced to build a model placed on deficient, vague or questionable guidance. The literature survey revealed that the majority of the reported software endeavour reckoning models are based on public available data sets with input parameter not more than two-tothree [1].In huge number of cases the effort estimation model seemed to be regression type. It is common felling among the researcher in this domain that the varied complexity of the projects is the main cause for being unable to predicate a generic estimation model. The domain of projects ranged in the realms of science and engineering

Methods

Results

Conclusion