期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2013
卷号：49
期号：3
出版社：Journal of Theoretical and Applied
摘要：Peer-to-peer computing is emerging as a new distributed computing paradigm for many novel applications that involve exchange of information among a large number of peers with little centralized coordination. Scalability is without doubt the foremost requirement for a peer-to-peer system. To obtain a high factor of scalability, we partition network search space using a global ontology. Our proposed system takes the form of a semantic layer that can be superimposed on top of any P2P infrastructure. This layer is subdivided as semantic categories through a Hilbert curve which has the merit of good preservation of locality. We choose HyperCup structure to support semantic category in order to increase fault tolerance and overcome bottleneck problem. HyperCup was also selected, because of its efficient broadcast algorithm. Classification within a semantic category will be conducted through multidimensional data analysis. The classification process will be recursively repeated with ontology refinement. We use digital libraries to illustrate our system, and highlight the proposed techniques.
关键词：P2P; ontology; HyperCup; Semantic classification; multidimensional data analysis; Correspondence analysis.
