期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：1
页码：463-466
出版社：TechScience Publications
摘要：Ranking is a vital sequencing problem in many applications, like many information retrieval systems, language processors. The existing Manifold Ranking for Sink Points(MRSP) scheme have backlog problem of ranking without the specific terms. The MRSP makes a mark able ranking based on the highest weightage transactions (HWT), whereas the low level light level transactions are omitted throughout the ranking process. In our proposed method to overcome the Ranking for the lightweight, we propose the Vector Machine Domain Specific Search (VM-DSS) through which the whole process transactions are taken into considering without any loss of transaction limit. Every node is calculated throughout with the depth-first-search (DFS) concept. Through the first is taken from the bottom and every node is considered. Throughout transaction the whole data is taken and ranked and the exact results are developed on the basis of the ranking of the information.
关键词：manifold ranking with sink points; Ranking;Adaptation Module; Domain Adaptation; and Support Vector;Machines
