The Surfer Model with a Hybrid Approach to Ranking the Web Pages
Journal Title: Journal of Information Systems and Telecommunication - Year 2016, Vol 4, Issue 3
Abstract
Users who seek results pertaining to their queries are at the first place. To meet users’ needs, thousands of webpages must be ranked. This requires an efficient algorithm to place the relevant webpages at first ranks. Regarding information retrieval, it is highly important to design a ranking algorithm to provide the results pertaining to user’s query due to the great deal of information on the World Wide Web. In this paper, a ranking method is proposed with a hybrid approach, which considers the content and connections of pages. The proposed model is a smart surfer that passes or hops from the current page to one of the externally linked pages with respect to their content. A probability, which is obtained using the learning automata along with content and links to pages, is used to select a webpage to hop. For a transition to another page, the content of pages linked to it are used. As the surfer moves about the pages, the PageRank score of a page is recursively calculated. Two standard datasets named TD2003 and TD2004 were used to evaluate and investigate the proposed method. They are the subsets of dataset LETOR3. The results indicated the superior performance of the proposed approach over other methods introduced in this area.
Authors and Affiliations
Javad Paksima, Homa Khajeh
Keywords
Related Articles
- EP ID EP184076
- DOI 10.7508/jist.2016.03.008
- Views 126
- Downloads 0
A New Method for Detecting the Number of Coherent Sources in the Presence of Colored Noise
In this paper, a new method for determining the number of coherent/correlated signals in the presence of colored noise is proposed which is based on the Eigen Increment Threshold (EIT) method. First, we present a new app...
Fusion of Learning Automata to Optimize Multi-constraint Problem
This paper aims to introduce an effective classification method of learning for partitioning the data in statistical spaces. The work is based on using multi-constraint partitioning on the stochastic learning automata. S...
A new Sparse Coding Approach for Human Face and Action Recognition
Sparse coding is an unsupervised method which learns a set of over-complete bases to represent data such as image, video and etc. In the cases where we have some similar images from the different classes, using the spars...
Cyclic Correlation-Based Cooperative Detection for OFDM-Based Primary Users
This paper develops a new robust cyclostationary detection technique for spectrum sensing of OFDM-based primary users (PUs). To do so, an asymptotically constant false alarm rate (CFAR) multi-cycle detector is proposed a...
An Intelligent Algorithm for the Process Section of Radar Surveillance Systems
In this paper, an intelligent algorithm for clustering, intra-pulse modulation detection and separation and identification of overlapping radar pulse train is presented. In most cases, based only on primary features of i...