Neural Network Approaches for Software Development Time Estimation: A Review

Abstract

Software effort estimation calculates the effort necessary to complete the project, in term of scheduling, acquiring resources, and meeting costs. The aims of researchers have been: first is to determine which technique has the greatest effort prediction accuracy and secondly to propose new or combined techniques that could provide better estimates. Most of the research has focused on the construction of formal models and the early models were typically statistical regression-based. This paper presents an Adaptive Neuro-Fuzzy Approach for Software Development Time Estimation. This proposed technique is aimed at building and evaluating a Neuro - fuzzy model for software project development time. The forty one modules were used as a data set. Our proposed approach is software development time estimation method show the proposed ANFIS model gives new approach and ideas as compared to different types of neural network models. In the proposed method accurate estimation of software development time will be done and the results of Neuro Fuzzy approach will be compared with different types of neural network models based upon various parameters such as Root Mean Squared Error (RMSE), Relative Standard Deviation (RSD), Magnitude of Relative Error (MRE), Mean Magnitude of Relative Error (MMRE), Balanced Relative Error (BRE) and Prediction (Pred).

Authors and Affiliations

Vidisha Agrawal, Vishal Shrivastava

Keywords

Related Articles

The Art of Business Relationships Through Social Media

Academic researchers have studied this issue using concepts and techniques such as social capital and social networks analysis. They have provided empirical as well as theoretical evidence of the value generated by diff...

Compressed Air Vehicle

This paper focuses on design, fabrication, testing of a vehicle that is powered by compressed air. As we all are aware that conventional fossil fuels obtained from natural oils and gases are depleting very rapidly, the...

Experimental Investigation for Performance Enhancement of Solar Still Using Solar Pond

Today fresh water demand is increasing continuously, because of the industrial development, intensified agriculture, improvement of standard of life and increase of the world population. Lack of fresh water is a prime f...

On Q* - Homeomorphisms in Topological Spaces

In this paper , we first introduce a new class of closed map called Q* - closed map . Moreover, we introduce a new class of homeomorphism called Q* - homeomorphism, which are weaker than homeomorphism. We also introduce...

Design and Implementation of Low Cost Maritime Boundary Identification System Using Fiber Optic Technology

Everywhere on this planet hair-thin optical fibers carry vast quantities of information from place to place. There are many desirable properties of optical fibers for carrying this information. They have enormous inform...

Download PDF file
  • EP ID EP19645
  • DOI -
  • Views 287
  • Downloads 4

How To Cite

Vidisha Agrawal, Vishal Shrivastava (2015). Neural Network Approaches for Software Development Time Estimation: A Review. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 3(3), -. https://europub.co.uk./articles/-A-19645