eCite Digital Repository

SaKEM: A Semi-automatic Knowledge engineering methodology for building rule-based knowledgebase


Ali, M and Hussain, M and Le, S and Kang, BH, SaKEM: A Semi-automatic Knowledge engineering methodology for building rule-based knowledgebase, Proceedings of the 16th International Symposium on Perception, Action, and Cognitive Systems (PACS2016), 27-28 October 2016, Seoul, Korea, pp. 63-64. (2016) [Conference Extract]


Copyright Statement

Copyright unknown

Official URL:


Knowledge engineering is one of the key research area to build knowledgebase for providing solutions to real-world problems. Due to rapidly increase of data growth rate, it is almost impossible to extract hidden knowledge with manual approach. Moreover, a number of methodologies have been proposed that focus on some specific aspect of the data mining process rather than end-to-end knowledge engineering methodology. Keeping in view these facts, a Semi-automatic Knowledge Engineering Methodology (SaKEM) is proposed that covers all major stages that are involved in Knowledge Discovery in Databases (KDD) process. For realization of SaKEM, a toolset called Data Driven Knowledge Acquisition Tool (DDKAT) is developed. The proposed methodology is designed for Mining Minds project but it can be utilized by other service-enabled platforms as well.

Item Details

Item Type:Conference Extract
Keywords:features selection, data preprocessing, decision trees, model translation, production rules, knowledge acquisition
Research Division:Information and Computing Sciences
Research Group:Distributed computing and systems software
Research Field:Mobile computing
Objective Division:Information and Communication Services
Objective Group:Information systems, technologies and services
Objective Field:Information systems, technologies and services not elsewhere classified
UTAS Author:Kang, BH (Professor Byeong Kang)
ID Code:113696
Year Published:2016
Deposited By:Engineering
Deposited On:2017-01-16
Last Modified:2017-08-31
Downloads:86 View Download Statistics

Repository Staff Only: item control page