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.
Highlights
The resident space object (RSO) identification is a main focus of space situational awareness (SSA) (Linares et al 2014; Nebelecky et al 2014; Henderson 2014), and an important task for space agencies, where resident space objects (RSOs) classification plays an important role (Ruttenberg et al 2015)
Six features are extracted from photometric data of RSO in Howard et al (2015), and several machine learning classifiers are built on the data of the 6 features to classify RSOs; statistical values, size and attitude are extracted from narrow band radar in Wang et al (2012), and a KNN fuzzy classifier is learned from the extracted features
This paper presents a methodological framework for improving performances of classifying RSOs by harnessing ontology and machine learning techniques
Summary
The resident space object (RSO) identification is a main focus of space situational awareness (SSA) (Linares et al 2014; Nebelecky et al 2014; Henderson 2014), and an important task for space agencies, where RSO classification plays an important role (Ruttenberg et al 2015). In this paper the authors propose a method to construct an OBC system for RSO through integrating unordered machine learning rules and background knowledge. An ontology for RSO classification named OntoStar is built upon the background knowledge and unordered machine learning rules of RSO. To the best of our knowledge, this is the first attempt to classify RSOs using OBC, especially OBC that integrates unordered machine learning rules and background knowledge. It is the first exploration of extra awards of OBC, such as the traceable and comprehensible classification. “Related works” section discusses related work in OBC, together with background knowledge for RSO classification and unordered machine learning rules. The paper concludes with discussions on the contributions of the work and directions for future research in “Conclusions” section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
