The job of software effort estimation is a critical one in the early stagesof the software development life cycle when the details of requirements areusually not clearly identified. Various optimization techniques help inimproving the accuracy of effort estimation. The Support Vector Regression(SVR) is one of several different soft-computing techniques that help ingetting optimal estimated values. The idea of SVR is based upon the computationof a linear regression function in a high dimensional feature space where theinput data are mapped via a nonlinear function. Further, the SVR kernel methodscan be applied in transforming the input data and then based on thesetransformations, an optimal boundary between the possible outputs can beobtained. The main objective of the research work carried out in this paper isto estimate the software effort using use case point approach. The use casepoint approach relies on the use case diagram to estimate the size and effortof software projects. Then, an attempt has been made to optimize the resultsobtained from use case point analysis using various SVR kernel methods toachieve better prediction accuracy.
展开▼
