Topic Trend Prediction for Learning Objects Using Kernel Fuzzy C Means Clustering and Autoregressive Integrated Moving Average Model

摘要

Because of consistent improvement of World Wide Web, effective retrieval from web databases is becoming enormously popular. Proposed method considers the databases to the clustering and topic trend prediction process. Initial stage applying the stop word removal technique and considering the different key words to generate to resultant matrix, this contain the different keywords with documents. Then we use the Kernel-based Fuzzy C-Means (KFCM) clustering for cluster the documents. After clustering process the cluster documents topic are fed into Autoregressive Integrated Moving Average (ARIMA) modeling to train the trend for past few years and to predict the topic with year in future decades. Performance of the proposed technique is evaluated using precision, recall and F-measure and also, comparative analysis will be performed to prove the better performance of the proposed technique.