Title: Performance of the three-layered knowledgebase and its representation models: an empirical evaluation
Authors: V. Hepsiba Mabel; Justus Selwyn
Addresses: School of Computing Science & Engineering, VIT University, Chennai 600127, TN, India ' School of Computing Science & Engineering, VIT University, Chennai 600127, TN, India
Abstract: A knowledge-based system or an expert system will require an intelligent knowledgebase which could share its computational overheads. Designing a knowledgebase would comprise knowledge units, logical entailments, unambiguous facts and rules, and storage level design and codification. These are pulled into a three-layered architecture of our proposed knowledgebase. We have four KR models proposed in our earlier works, and we have plugged them in our new KB. The performance efficiency of this KB model, in terms of throughput, entailment computation time etc., is validated by a series of experiments conducted using two case studies: EduNiversity and MES. The outcomes are very significant and exhibit that there is a substantial improvement in the measured attributes.
Keywords: knowledge engineering; music expert systems; representation models; knowledge-based systems; KBS; intelligent knowledgebase.
International Journal of Knowledge Engineering and Data Mining, 2015 Vol.3 No.3/4, pp.239 - 254
Received: 12 Dec 2014
Accepted: 09 Jul 2015
Published online: 05 Jan 2016 *