KaM_CRK: Clustering and Ranking Knowledge for Reasonable Results Based on Behaviors and Contexts

Changhong Hu, Shufen Liu, Ramana Reddy, Sumitra Reddy and Mingyang Liu

Mathematical Problems in Engineering, 2013, vol. 2013, 1-11

Abstract:

A model named KaM_CRK is proposed, which can supply the clustered and ranked knowledge to the users on different contexts. By comparing the attributes of contexts and JANs, our findings indicate that our model can accumulate the JANs, whose attributes are similar with the user’s contexts, together. By applying the KaM_CLU algorithm and Centre rank strategy into the KaM_CRK model, the model boosts a significant promotion on the accuracy of provision of user's knowledge. By analyzing the users' behaviors, the dynamic coefficient Behavior F is first presented in KaM_CLU. Compared to traditional approaches of K_means and DBSCAN, the KaM_CLU algorithm does not need to initialize the number of clusters. Additionally, its synthetic results are more accurate, reasonable, and fit than other approaches for users. It is known from our evaluation through real data that our strategy performs better on time efficiency and user's satisfaction, which will save by 30% and promote by 5%, respectively.

Date: 2013
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/MPE/2013/601528.pdf (application/pdf)
http://downloads.hindawi.com/journals/MPE/2013/601528.xml (text/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:601528

DOI: 10.1155/2013/601528

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().