The nearest neighbors (NNs) classifiers, especially the k-Nearest Neighbors (kNNs) algorithm, are among the simplest and yet most efficient classification rules and widely used in practice. It is a nonparametric method of pattern recognition. In this paper, k-Nearest Neighbors, one of the most commonly used machine learning methods, work in automatic classification of multi-wavelength astronomical objects. Through the experiment, we conclude that the running speed of the kNN classier is rather fast and the classification accuracy is up to 97.73%. As a result, it is efficient and applicable to discriminate active objects from stars and normal galaxies with this method. The classifiers trained by the kNN method can be used to solve the automated classification problem faced by astronomy and the virtual observatory (VO).
LI LiLi1,2,3, ZHANG YanXia1 & ZHAO YongHeng1 1 National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, China
With the development of network and the World Wide Web (WWW), the Internet has been growing and changing dramatically. More and more on-line database systems and different kinds of services are available for astronomy research. How to help users find their way through the jungle of information services becomes an important challenge. Although astronomers have been aware of the importance of interoperability and introduced the concept of Virtual Observatory as a uniform environment for future astronomical on-line resources and services, transparent access to heterogeneous on-line information is still difficult. SkyMouse is a lightweight interface for distributed astronomical on-line resources and services, which is designed and developed by us, i.e., Chinese Virtual Observatory project. Taking advantage of screen word-capturing technology, different kinds of information systems can be queried through simple mouse actions, and results are returned in a uniform web page. SkyMouse is an easy to use application, aiming to show basic information or to create a comprehensive overview of a specific astronomical object. In this paper current status of on-line resources and services access is reviewed; system architecture, features and functions of SkyMouse are described; challenges for intelligent in-terface for on-line astronomical resources and services are discussed.
CUI ChenZhouSUN HuaPingZHAO YongHengLUO YuQI DaZhi
