Class point based effort estimation of OO systems using fuzzy subtractive clustering and artificial neural networks

  • Authors:

  • S. Kanmani;Jayabalan Kathiravan;S. Senhil Kumar;Mourougane Shanmugam

  • Affiliations:

  • Pondicherry Engineering College, Puducherry, India;Cognizant, Chennai, India;Cognizant, Chennai, India;Tata Consultancy Services, Chennai, India

  • Venue:
  • ISEC '08 Proceedings of the 1st India software engineering conference
  • Year:
  • 2008

Quantified Score

Hi-index 0.01

Visualization

Abstract

Fuzzy Logic is a convenient way to map an input space to an output space. Class points have been accepted to estimate the size of Object Oriented (OO) products and to directly predict the effort, cost and duration of the software projects. Most estimation models in use or proposed in the literature are based on regression techniques. In this paper, we attempt on using Fuzzy Subtractive Clustering and Artificial Neural Networks to estimate the development effort of OO systems using class points. The estimation model uses class points as the independent variable and development effort as the dependent variable. The results show that the estimation accuracy is higher in Fuzzy Logic compared to the Neural Network model. This experiment is carried out using the data set found in the literature