Vol. 10 Issue 1
Year:2015
Issue:Jul-Sep
Title:A Modern Approach on Student Performance Prediction using Multi-Agent Data Mining Technique
Author Name:L.V. Reddy, K. Yogitha, K. Bandhavi, G. Sai Vinay, and G. Dinesh Kumar
Synopsis:
Among the evolving researches on data mining, one such field of interests is on the education. This emerging field of research in education is called Educational Data Mining, which means the data related to the field of education. One of the main concerns in educational field is the academic scores of a student, which helps in the growth of the student as well as the Institution. To predict a student's performance is a very important one in educational field. To maintain the scores and in order to increase the scores of a student the prediction of one's performance is necessary. To achieve this objective of predicting, the performance is fulfilled by the usage of data mining. A high prediction accuracy of the student's performance is more helpful to identify the slow performance students at the beginning of the learning process. Data mining techniques are used to analyze the models or patterns of data, and it is also helpful in the decision-making [19]. Boosting technique [21][22] is one of the most popular techniques for constructing classifier by ensemble to improve the classification accuracy. Adaptive Boosting (AdaBoost) is a generation of Boosting algorithm. It is applicable for the binary classification and not used in multiclass classification directly. Therefore, an extension for the AdaBoost is proposed which is SAMME boosting technique for the multiclass classification without reducing it to a set of sub-binary classification. In this paper, the authors have evaluated student's performance prediction system to predict the performance of the students based on their data with high prediction accuracy and provide help to the slow learning students by using optimization rules.
Year:2015
Issue:Jul-Sep
Title:A Modern Approach on Student Performance Prediction using Multi-Agent Data Mining Technique
Author Name:L.V. Reddy, K. Yogitha, K. Bandhavi, G. Sai Vinay, and G. Dinesh Kumar
Synopsis:
Among the evolving researches on data mining, one such field of interests is on the education. This emerging field of research in education is called Educational Data Mining, which means the data related to the field of education. One of the main concerns in educational field is the academic scores of a student, which helps in the growth of the student as well as the Institution. To predict a student's performance is a very important one in educational field. To maintain the scores and in order to increase the scores of a student the prediction of one's performance is necessary. To achieve this objective of predicting, the performance is fulfilled by the usage of data mining. A high prediction accuracy of the student's performance is more helpful to identify the slow performance students at the beginning of the learning process. Data mining techniques are used to analyze the models or patterns of data, and it is also helpful in the decision-making [19]. Boosting technique [21][22] is one of the most popular techniques for constructing classifier by ensemble to improve the classification accuracy. Adaptive Boosting (AdaBoost) is a generation of Boosting algorithm. It is applicable for the binary classification and not used in multiclass classification directly. Therefore, an extension for the AdaBoost is proposed which is SAMME boosting technique for the multiclass classification without reducing it to a set of sub-binary classification. In this paper, the authors have evaluated student's performance prediction system to predict the performance of the students based on their data with high prediction accuracy and provide help to the slow learning students by using optimization rules.
No comments:
Post a Comment