Limits...
Harnessing ontology and machine learning for RSO classification

View Article: PubMed Central - PubMed

ABSTRACT

Classification is an important part of resident space objects (RSOs) identification, which is a main focus of space situational awareness. Owing to the absence of some features caused by the limited and uncertain observations, RSO classification remains a difficult task. In this paper, an ontology for RSO classification named OntoStar is built upon domain knowledge and machine learning rules. Then data describing RSO are represented by OntoStar. A demo shows how an RSO is classified based on OntoStar. It is also shown in the demo that traceable and comprehensible reasons for the classification can be given, hence the classification can be checked and validated. Experiments on WEKA show that ontology-based classification gains a relatively high accuracy and precision for classifying RSOs. When classifying RSOs with imperfect data, ontology-based classification keeps its performances, showing evident advantages over classical machine learning classifiers who either have increases of 5 % at least in FP rate or have decreases of 5 % at least in indexes such as accuracy, precision and recall.

No MeSH data available.


Description of 2009-041D in OntoStar
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5037103&req=5

Fig3: Description of 2009-041D in OntoStar

Mentions: Taking the RSO whose cospar_id is “2009-041D” as example, it will be shown how to describe RSO and record sources of the data by OntoStar. Firstly, an instance of SpaceObject is created in OntoStar named “2009-041D” (identified as 2009-041D in the following), data in NORAD_Catalog and UCS_Satellite about 2009-041D are used to describe the instance 2009-041D in OntoStar correspondingly. Then brightness datum about 2009-041D collected from calsy.com is used to fill the data property brightness of the instance 2009-041D. The description of the instance 2009-041D using the data from the three sources above is shown in Fig. 3.Fig. 3


Harnessing ontology and machine learning for RSO classification
Description of 2009-041D in OntoStar
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5037103&req=5

Fig3: Description of 2009-041D in OntoStar
Mentions: Taking the RSO whose cospar_id is “2009-041D” as example, it will be shown how to describe RSO and record sources of the data by OntoStar. Firstly, an instance of SpaceObject is created in OntoStar named “2009-041D” (identified as 2009-041D in the following), data in NORAD_Catalog and UCS_Satellite about 2009-041D are used to describe the instance 2009-041D in OntoStar correspondingly. Then brightness datum about 2009-041D collected from calsy.com is used to fill the data property brightness of the instance 2009-041D. The description of the instance 2009-041D using the data from the three sources above is shown in Fig. 3.Fig. 3

View Article: PubMed Central - PubMed

ABSTRACT

Classification is an important part of resident space objects (RSOs) identification, which is a main focus of space situational awareness. Owing to the absence of some features caused by the limited and uncertain observations, RSO classification remains a difficult task. In this paper, an ontology for RSO classification named OntoStar is built upon domain knowledge and machine learning rules. Then data describing RSO are represented by OntoStar. A demo shows how an RSO is classified based on OntoStar. It is also shown in the demo that traceable and comprehensible reasons for the classification can be given, hence the classification can be checked and validated. Experiments on WEKA show that ontology-based classification gains a relatively high accuracy and precision for classifying RSOs. When classifying RSOs with imperfect data, ontology-based classification keeps its performances, showing evident advantages over classical machine learning classifiers who either have increases of 5 % at least in FP rate or have decreases of 5 % at least in indexes such as accuracy, precision and recall.

No MeSH data available.