A Nonlinear Multiregression Model Based on the Choquet Integral for Analyzing the Course Records
The score of the final examination of a student has some relation to the previous records, such as the average score of quizzes, the scores of tests, the number of incomplete homework, and the number of absent class meetings. The relation is usually nonlinear since there are some interactions among the inherent but covert contributions from these previous records towards the final examination. Regarding the score of the final examination as the objective attribute and the previous records as the predictive attributes, the nonlinear multiregression based on the Choquet integral with respect to a nonadditive measure is a proper tool to catch the interaction and, therefore, describe above-mentioned relation well. In this paper, a 2-interactive measure is used as the nonadditive measure to reduce the computational complexity.
KeywordsEducation nonadditive measures the Choquet integral multiregression genetic algorithm soft computing data mining
Unable to display preview. Download preview PDF.