Interval Type-2 Fuzzy Logic for Software Cost Estimation Using TSFC with Mean and Standard Deviation

Hari, Ch. V. M. K.; P.V.G.D., Prasad Reddy; Jagadeesh, M.; Ganesh, G. SriRam

doi:10.1109/artcom.2010.40

Cited by 8 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The estimate is influenced by various factors known as cost drivers which lead to the uncertainty and nondeterministic nature of the process [2,3]. These uncertainties could be accounted for by making use of soft computing techniques such as genetic algorithms [4], Fuzzy logic [5,6], Particle Swarm Optimization (PSO), Neural Networks [11,15], etc. The stochastic nature of these techniques efficiently model's the uncertainties involved in the estimation process [7,14].…”

Section: Introductionmentioning

confidence: 99%

SEEPC: A Toolbox for Software Effort Estimation using Soft Computing Techniques

.CH.V.M.K¹,

Sethi²,

Jagadeesh.M³

2011

IJCA

View full text Add to dashboard Cite

Software Effort estimation is the process of gauging the amount of effort required to complete the project. With the proliferation of software projects and the heterogeneity in there genre, there is a need for efficient software effort estimation techniques to enable the project managers to perform proper planning of the Software Life Cycle activates. In this article, a new hybrid toolbox based on soft computing techniques for effort estimation is introduced. Particle swarm optimization and cluster analysis has been implemented to perform efficient estimation of effort values with learning ability. The main aim of the toolbox is to provide an efficient, flexible and user friendly way of performing the effort estimation task, by catering to the needs of both the technical and the nontechnical users. The toolbox also implements the COCOMO model to enable a comparative analysis of the proposed model. It was observed that the model when provided with enough training data gave better results when compared with the standard COCOMO values

show abstract