Ontology Development for Classification: Spirals - A Case Study in Space Object Classification

Bin Liu, Li Yao, Junfeng Wu, Zheyuan Ding

2017

Abstract

Ontology-based classification (OBC) has been used extensively. The classification ontologies are the grounds of the OBC systems. It is an urgent call for a method to guide the development of classification ontology, to get better performances for OBC. A method for developing classification ontology named Spirals is proposed, taking the development of the ontology for space object classification named OntoStar as an example. Firstly, soft sensing data and hard sensing data are collected. Then, various kinds of human knowledge and knowledge obtained by machine learning are combined to build the ontology. Finally, data-driven evaluation and promotion is deployed to assess and promote the ontology. Experiments of the OBC system built upon OntoStar show that the data-driven evaluation and promotion in Spirals increases the accuracy of space object classification by 4.1%. OBC is more robust than baseline classifiers with respect to a missing feature in the test data. When classifying space objects with the feature “size” missing in the test data, OBC keeps its FP rate, while that of baseline classifiers increases between 3.9% and 35.5%; the losing accuracy of OBC is 0.2%, while that of baseline classifiers ranges from 1.1% to 69.5%.

Paper Citation

in Harvard Style

Liu B., Yao L., Wu J. and Ding Z. (2017). Ontology Development for Classification: Spirals - A Case Study in Space Object Classification . In Proceedings of the 13th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-246-2, pages 225-234. DOI: 10.5220/0006240002250234

in Bibtex Style

@conference{webist17,
author={Bin Liu and Li Yao and Junfeng Wu and Zheyuan Ding},
title={Ontology Development for Classification: Spirals - A Case Study in Space Object Classification},
booktitle={Proceedings of the 13th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2017},
pages={225-234},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006240002250234},
isbn={978-989-758-246-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 13th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Ontology Development for Classification: Spirals - A Case Study in Space Object Classification
SN - 978-989-758-246-2
AU - Liu B.
AU - Yao L.
AU - Wu J.
AU - Ding Z.
PY - 2017
SP - 225
EP - 234
DO - 10.5220/0006240002250234