Machine Learning
Empirical Data Modeling in Software Engineering Using Radial Basis Functions
IEEE Transactions on Software Engineering
A tutorial on support vector regression
Statistics and Computing
Fundamentals of Computational Swarm Intelligence
Fundamentals of Computational Swarm Intelligence
Software Effort Estimation Using Machine Learning Techniques with Robust Confidence Intervals
ICTAI '07 Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence - Volume 01
Using Tabu Search to Estimate Software Development Effort
IWSM '09 /Mensura '09 Proceedings of the International Conferences on Software Process and Product Measurement
A shift-invariant morphological system for software development cost estimation
Expert Systems with Applications: An International Journal
Investigating the use of Support Vector Regression for web effort estimation
Empirical Software Engineering
Hybrid morphological methodology for software development cost estimation
Expert Systems with Applications: An International Journal
Search-based approaches for software development effort estimation
Proceedings of the 12th International Conference on Product Focused Software Development and Process Improvement
Using genetic algorithms to improve prediction of execution times of ML tasks
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part I
International Journal of Intelligent Information Technologies
Hi-index | 0.00 |
The precision of the estimation of the effort of software projects is very important for the competitiveness of software companies. Machine learning methods have recently been applied for this task, included methods based on support vector regression (SVR). This paper proposes and investigates the use of a genetic algorithm approach for simultaneously (1) select an optimal feature subset and (2) optimize SVR parameters, aiming to improve the precision of the software effort estimates. We report on experiments carried out using two datasets of software projects. In both datasets, the simulations have shown that the proposed GA-based approach was able to improve substantially the performance of SVR and outperform some recent results reported in the literature.