Improving the COCOMO model using a neuro-fuzzy approach

Huang, Xishi; Ho, Danny; Ren, Jing; Capretz, Luiz Fernando

doi:10.1016/j.asoc.2005.06.007

Cited by 106 publications

(64 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dave [18] showed that NNET in general is better than regression analysis and Radial Bases NNET (RBNN) is better than Feed Forward NNET (FFNN). Du [19] and Huang [20] Used Neuro-fuzzy techniques for improving COCOMO model. Support vector machines (SVR) [21] and data mining techniques [22]- [25] are also candidate techniques to tackle this problem.…”

Section: Resultsmentioning

confidence: 99%

Genetic Fuzzy System for Enhancing Software Estimation Models

Hamdy¹

2014

IJMO

View full text Add to dashboard Cite

Abstract-Imprecise estimation of software development cost is one of the major factors that contributes in the failure of software projects. Several algorithmic models have been devised for cost estimation; but they lack the ability to handle imprecision and uncertainties associated with the software project attributes. Embedding a fuzzy component in the algorithmic model enables it to deal with the imprecision and uncertainty problem; consequently improves its accuracy. However, the performance of any fuzzy system depends on the settings of its parameters. This paper proposes a genetic fuzzy model for effort estimation. Genetic algorithm is used in tuning the fuzzy sets of the model to optimize the estimation accuracy. MATLAB 2012 was used in implementing the proposed model. The model was evaluated using artificial datasets derived from COCOMONASA2 dataset. The experimental results showed that the accuracy and sensitivity of the proposed model is superior to COCOMO. It's note worthy to mention that the idea of the paper is not restricted to COCOMO; it could be applied to other algorithmic models.

show abstract

Section: Resultsmentioning

confidence: 99%

Genetic Fuzzy System for Enhancing Software Estimation Models

Hamdy¹

2014

IJMO

View full text Add to dashboard Cite

show abstract

“…On the other hand, References (Pendharkar et al, 2005;Papatheocharous and Andreou, 2007;Kumar et al, 2008;de Barcelos Tronto et al, 2008;Park and Baek, 2008;Attarzadeh and Ow, 2011;Idri et al, 2008Idri et al, , 2010Reddy et al, 2008;Shin and Goel, 2000) used neural network models such as MLP and RBFNN to predict software estimation. References (Azzeh et al, 2010(Azzeh et al, , 2011Huang and Chiu, 2006) used soft computing techniques with analogy based estimation, whereas References (Idri and Abran, 2000;Huang et al, 2007) used soft computing with algorithmic models. References (Ahmed et al, 2005;Papatheocharous et al, 2010) used fuzzy logic and fuzzy decision tree, respectively for software effort estimation.…”

Section: Related Workmentioning

confidence: 99%

Towards an early software estimation using log-linear regression and a multilayer perceptron model

Nassif

Ho²,

Capretz

2013

Journal of Systems and Software

Self Cite

162

160

View full text Add to dashboard Cite

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution and sharing with colleagues.Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. a b s t r a c tSoftware estimation is a tedious and daunting task in project management and software development. Software estimators are notorious in predicting software effort and they have been struggling in the past decades to provide new models to enhance software estimation. The most critical and crucial part of software estimation is when estimation is required in the early stages of the software life cycle where the problem to be solved has not yet been completely revealed. This paper presents a novel log-linear regression model based on the use case point model (UCP) to calculate the software effort based on use case diagrams. A fuzzy logic approach is used to calibrate the productivity factor in the regression model. Moreover, a multilayer perceptron (MLP) neural network model was developed to predict software effort based on the software size and team productivity. Experiments show that the proposed approach outperforms the original UCP model. Furthermore, a comparison between the MLP and log-linear regression models was conducted based on the size of the projects. Results demonstrate that the MLP model can surpass the regression model when small projects are used, but the log-linear regression model gives better results when estimating larger projects.

show abstract

“…Huang et al [16,17] proposed a software effort estimation model that combines a neuro-fuzzy framework with COCOMO II. The parameter values of COCOMO II were calibrated by the neurofuzzy technique in order to improve its prediction accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Software Effort Estimation Using Adaptive Fuzzy-Neural Approach

Mehdi

2017

IJCATR

View full text Add to dashboard Cite

Abstract-Software effort estimation is an important step in software development. It predicts the amount of effort and development time required to build a software system. It is one of the most important tasks and an accurate estimate is vital to the successful completion of the project. Building software effort estimation requires developing sound computational models. This paper investigates the use of fuzzy-neural systems in estimating software effort. A comparison is made with a radial basis neural network. Results obtained based on the China dataset indicates that a hybrid model that combine fuzzy inferencing with neural networks ability to learn from examples provided more accurate results than using neural networks alone.

show abstract

Improving the COCOMO model using a neuro-fuzzy approach

Cited by 106 publications

References 8 publications

Genetic Fuzzy System for Enhancing Software Estimation Models

Genetic Fuzzy System for Enhancing Software Estimation Models

Towards an early software estimation using log-linear regression and a multilayer perceptron model

Software Effort Estimation Using Adaptive Fuzzy-Neural Approach

Contact Info

Product

Resources

About