Adaptive Clustering of Embedded Multiple Web Objects for Efficient Group Prefetching

详细信息    查看全文

• 作者：Chithra D. Gracia ; S. Sudha
• 关键词：Hit rate ; Prefetch ; ART2 ; Silhouette ; Latency ; Adaptive ; Stability ; Plasticity
• 刊名：Arabian Journal for Science and Engineering
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：42
• 期：2
• 页码：715-724
• 全文大小：
• 刊物类别：Engineering
• 刊物主题：Engineering, general; Science, Humanities and Social Sciences, multidisciplinary;
• 出版者：Springer Berlin Heidelberg
• ISSN：2191-4281
• 卷排序：42

文摘

The resources in the World Wide Web are rising to large extent. Furthermore, the services and applications provided by the web are directly proportional to its growth. Hence, web traffic is large, and gaining access to these resources incurs user-perceived latency. Although the latency can never be avoided, it can be minimized largely. Web prefetching is identified as a technique to minimize this latency wherein it anticipates user’s future requests and fetches them into the cache prior to an explicit request made. Since web objects dispersed across the web are of various types, a new algorithm is being proposed that concentrates on prefetching embedded objects including audio and video files. Further, clustering is employed using Adaptive Resonance Theory2 neural network so as to prefetch embedded objects as clusters. For comparative study, the web objects are clustered using state-of-the-art clustering techniques and Adaptive Resonance Theory1. The clustering results confirm the supremacy of the adaptive ART2, and thereby prefetching web objects in clusters is observed to produce higher hit rate than all other techniques.