Soft computing based estimation of software development effort

Software development cost estimation is an important activity in the early software design phases. The input datasets are primarily taken from the promise repository. Data mining and soft computing techniques are used to assess the software development cost estimation. Each feature in the input dataset is divided, the linguistic terms along with the membership are identified using trapezoidal membership functions, and associative classification is adopted for generating rules. The large number of rules is filtered with respect to the support and confidence. Genetic algorithm is employed as an optimization tool for selecting the best rules. The example presented demonstrates the improvement in accuracy. The crisp efforts are presented after defuzzification of the output.

[1]  Colin J Burgess,et al.  Can genetic programming improve software effort estimation? A comparative evaluation , 2001, Inf. Softw. Technol..

[2]  Jing Ren,et al.  A soft computing framework for software effort estimation , 2006, Soft Comput..

[3]  Qing Hu,et al.  Software Cost Estimation Using Economic Production Models , 1998, J. Manag. Inf. Syst..

[4]  Martin J. Shepperd,et al.  Using simulation to evaluate prediction techniques [for software] , 2001, Proceedings Seventh International Software Metrics Symposium.

[5]  Uzay Kaymak,et al.  Fuzzy criteria for feature selection , 2012, Fuzzy Sets Syst..

[6]  Daniel Neagu,et al.  Improving analogy software effort estimation using fuzzy feature subset selection algorithm , 2008, PROMISE '08.

[7]  Magne Jørgensen,et al.  A review of studies on expert estimation of software development effort , 2004, J. Syst. Softw..

[8]  Magne Jørgensen,et al.  Forecasting of software development work effort: Evidence on expert judgement and formal models , 2007 .

[9]  Baowen Xu,et al.  A classification method of fuzzy association rules , 2003, Second IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2003. Proceedings.

[10]  Heejun Park,et al.  An empirical validation of a neural network model for software effort estimation , 2008, Expert Syst. Appl..

[11]  Tzung-Pei Hong,et al.  A Genetic-Fuzzy Mining Approach for Items with Multiple Minimum Supports , 2007, FUZZ-IEEE.

[12]  Peter I. Cowling,et al.  MMAC: a new multi-class, multi-label associative classification approach , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[13]  Peter I. Cowling,et al.  Improving rule sorting, predictive accuracy and training time in associative classification , 2006, Expert Syst. Appl..

[14]  Magne Jørgensen,et al.  A Systematic Review of Software Development Cost Estimation Studies , 2007, IEEE Transactions on Software Engineering.

[15]  Viljan Mahnic,et al.  On using planning poker for estimating user stories , 2012, J. Syst. Softw..

[16]  Chih-Yang Chen,et al.  Improving the performance of association classifiers by rule prioritization , 2012, Knowl. Based Syst..

[17]  Vikram Pudi,et al.  FACISME: Fuzzy associative classification using iterative scaling and maximum entropy , 2010, International Conference on Fuzzy Systems.

[18]  Magne Jørgensen,et al.  How does project size affect cost estimation error? Statistical artifacts and methodological challenges , 2012 .

[19]  Daryl Essam,et al.  Software project effort estimation using genetic programming , 2002, IEEE 2002 International Conference on Communications, Circuits and Systems and West Sino Expositions.

[20]  Elena García Barriocanal,et al.  Segmented software cost estimation models based on fuzzy clustering , 2008, J. Syst. Softw..

[21]  Yong-Ji Wang,et al.  Software Development Effort Estimation Using Fuzzy Logic - A Survey , 2008, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery.

[22]  Douglas Fisher,et al.  Machine Learning Approaches to Estimating Software Development Effort , 1995, IEEE Trans. Software Eng..

[23]  Tzung-Pei Hong,et al.  Genetic-fuzzy mining with multiple minimum supports based on fuzzy clustering , 2011, Soft Comput..

[24]  Silvio Romero de Lemos Meira,et al.  An evolutionary morphological approach for software development cost estimation , 2012, Neural Networks.

[25]  János Abonyi,et al.  Compact fuzzy association rule-based classifier , 2008, Expert Syst. Appl..

[26]  Frans Coenen,et al.  The effect of threshold values on association rule based classification accuracy , 2007, Data Knowl. Eng..

[27]  Jesús Alcalá-Fdez,et al.  A Fuzzy Association Rule-Based Classification Model for High-Dimensional Problems With Genetic Rule Selection and Lateral Tuning , 2011, IEEE Transactions on Fuzzy Systems.

[28]  Ricardo Massa Ferreira Lima,et al.  GA-based method for feature selection and parameters optimization for machine learning regression applied to software effort estimation , 2010, Inf. Softw. Technol..

[29]  Sérgio Soares,et al.  Hybrid morphological methodology for software development cost estimation , 2012, Expert Syst. Appl..

[30]  Magne Jørgensen,et al.  A Systematic Review of Software Development Cost Estimation Studies , 2007 .

[31]  Hisao Ishibuchi,et al.  Comparison of the Michigan and Pittsburgh approaches to the design of fuzzy classification systems , 1997 .

[32]  Kjetil Moløkken-Østvold,et al.  Using planning poker for combining expert estimates in software projects , 2008, J. Syst. Softw..

[33]  Sergio A. Alvarez,et al.  Chi-squared computation for association rules: preliminary results , 2003 .

[34]  Ayse Basar Bener,et al.  Feature weighting heuristics for analogy-based effort estimation models , 2009, Expert Syst. Appl..

[35]  Cornelio Yáñez-Márquez,et al.  Predictive accuracy comparison of fuzzy models for software development effort of small programs , 2008, J. Syst. Softw..