Details

Autor(en) / Beteiligte

• P, Rama Sree

Titel

Adaptive Neuro Fuzzy Inference System for Software Development Effort Estimation

Ist Teil von

• International journal of advanced research in computer science, 2012-11, Vol.3 (7)

Ort / Verlag

Udaipur: International Journal of Advanced Research in Computer Science

Erscheinungsjahr

2012

Link zum Volltext

Quelle

Free E-Journal (出版社公開部分のみ）

Beschreibungen/Notizen

• Software estimation such as cost estimation, effort estimation, quality estimation and risk analysis is a major challenge for Software Projects. The literature shows several algorithmic cost estimation models such as Boehm's COCOMO(Constructive Cost Model), Albrecht's' Function Point Analysis, Putnam's SLIM(Software Lifecycle Management), ESTIMACS(Macro Estimation Model) etc., where each model has its own pros and cons for estimation, there is still a need to find a model that gives accurate estimates. This paper is a modest attempt in explaining the soft computing models using Adaptive Neuro Fuzzy Inference System (ANFIS) which are designed to improve the performance of the network that suits to the COCOMO Model for software development effort prediction. ANFIS Models are created using Triangular, GBell, trapezoidal and Gauss membership functions. A case study based on NASA 93 projects compares the proposed models with the Intermediate COCOMO. In the results which were analyzed using five different criterions Variance Accounted For (VAF), Mean Absolute Relative Error (MARE), Variance Absolute Relative Error(VARE), Mean Balance Relative Error (Mean BRE) and Prediction ,it is observed that the proposed ANFIS models combined with the neural network adaptive capabilities and the fuzzy inference system indicate a high level of efficiency with an accuracy of 99% and particularly ANFIS Model using Triangular Membership function provided better results.