Proceeding of the Electrical Engineering Computer Science and Informatics
Vol 4: EECSI 2017

Minimizing the Estimated Solution Cost with A* Search to Support Minimal Mapping Repair

Inne Gartina Husein (Universitas Telkom)
Benhard Sitohang (Institut Teknologi Bandung)
Saiful Akbar (Institut Teknologi Bandung)



Article Info

Publish Date
01 Nov 2017

Abstract

Incoherent alignment has been the main focus in the matching process since 2010.  Incoherent means that there is semantic or logic conflict in the alignment. This condition encouraged researches in ontology matching field to improve the alignment by repairing the incoherent alignment. Repair mapping will restore the incoherent to coherent mapping, by deleting unwanted mappings from the alignment. In order to minimize the impacts in the input alignment, repair process should be done as as minimal as possible. Definition of minimal could be (1) reducing the number of deleted mappings, or (2) reducing the total amount of deleted mappings’ confidence values. Repair process with new global technique conducted the repair with both minimal definitions. This technique could reduce the number of deleted mappings and total amount of confidence values at the same time. We proposed A * Search method to implement new global technique. This search method was capable to search the shortest path which representing the fewest number of deleted mappings, and also search the cheapest cost which representing the smallest total amount of deleted mappings’ confidence value. A* Search was both complete and optimal to minimize mapping repair size.

Copyrights © 2017






Journal Info

Abbrev

EECSI

Publisher

Subject

Computer Science & IT Electrical & Electronics Engineering

Description

Proceeding of the Electrical Engineering Computer Science and Informatics publishes papers of the "International Conference on Electrical Engineering Computer Science and Informatics (EECSI)" Series in high technical standard. The Proceeding is aimed to bring researchers, academicians, scientists, ...