Performance of Variable Selection Method for the Damage Level Prediction of Reshaped Berm Breakwater
2015
Selection of input parameters is one of the important issues in reducing the number of experiments. There are numerous variable selection methods available. The purpose of this paper is to explore the application of Principal Component Regression (PCR) analysis for the selection of variables. Data to perform the analysis was obtained from the experimental studies conducted to measure the damage level of the reshaped berm breakwater. For the analysis, damage level was considered as the output variable and the other influencing variables as input variables. From the study it can be concluded that PCR analysis is an effective tool in reducing the number of input variables without affecting the output. It can be used as a preliminary tool in determining the influencing input variables on the output which is damage level in the present case.
Mostrar más [+] Menos [-]Palabras clave de AGROVOC
Información bibliográfica
Este registro bibliográfico ha sido proporcionado por National Agricultural Library