Name
Abstract | ||
|---|---|---|
In the past few years, we have observed a trend of increasing cooperation between computer science and other empirical sciences such as physics, biology, or medical fields. This e-science synergy opens new challenges for the computer science and triggers important advances in other areas of research. In our particular case, we are facing an astroinformatics challenge of analysing stellar spectra in order to establish automated classification methods for recognizing different types of Be stars. We have chosen similarity search methods, which are effectively utilized in other domains like multimedia content-based retrieval for instance. This paper presents our analysis of the problematics and proposed a solution based on Signature Quadratic Form Distance and feature signatures. We have also conducted intensive empirical evaluation which allowed us to determine appropriate configuration for our similarity model. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1007/978-3-319-11988-5_21 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
similarity,SQFD,stellar spectra,feature signatures,astroinformatics,classification | Information retrieval,Computer science,Quadratic form,Stars,Artificial intelligence,Astroinformatics,Astronomical spectroscopy,Machine learning,Nearest neighbor search | Conference |
Volume | ISSN | Citations |
8821 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 7 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Martin Krulis | 1 | 76 | 13.27 |
| David Bednárek | 2 | 43 | 10.89 |
| Jakub Yaghob | 3 | 114 | 15.74 |
| Filip Zavoral | 4 | 119 | 19.01 |