Learners Grouping in Adaptive Learning Systems Using Fuzzy Grafting Clustering

Quality of adaptive and collaborative learning systems is related to appropriate specifying learners and accuracy of separation learners in homogenous and heterogeneous groups. In the proposed method for learners grouping, researchers effort to improving basic clustering methods by combination of them and improving methods. This work makes the complexity of grouping methods increased and quality of result’s groups decreased. In this paper, new method for selection appropriate clusters based on fuzzy theory is proposed. In this method, each cluster is defined as a fuzzy set and the corresponding clusters are determined. So the best cluster is selected among each corresponding clusters. The results of an empirical evaluation of the proposed method based on two criteria: “Davies-Bouldin” and “Purity and Gathering” indicate that this method has better performance than other clustering methods such as FCM, K-means, hybrid clustering method (HCM), evolutionary fuzzy clustering (EFC) and ART neural network.