Astrophysics is evolving toward a more rational use of costly observational data by intelligently exploiting the large terrestrial and spatial astronomical databases. In this paper, we present a study showing the suitability of an expert system to perform the classification of stellar spectra in the Morgan and Keenan (MK) system. Using the formalism of artificial intelligence for the development of such a system, we propose a rules' base that contains classification criteria and confidence grades, all integrated in an inference engine that emulates human reasoning by means of a hierarchical decision rules tree that also considers the uncertainty factors associated with rules. Our main objective is to illustrate the formulation and development of such a system for an astrophysical classification problem. An extensive spectral database of MK standard spectra has been collected and used as a reference to determine the spectral indexes that are suitable for classification in the MK system. It is shown that by considering 30 spectral indexes and associating them with uncertainty factors, we can find an accurate diagnose in MK types of a particular spectrum. The system was evaluated against the NOAO-INDO-US spectral catalog.
展开▼
机译:通过智能地利用大型地面和空间天文数据库,天体物理学正在朝着更合理地使用昂贵的观测数据的方向发展。在本文中,我们提出了一项研究,该研究表明专家系统在Morgan and Keenan(MK)系统中执行恒星光谱分类的适用性。利用人工智能的形式主义来开发这样的系统,我们提出了一个包含分类标准和置信度等级的规则库,这些规则标准和置信度都集成在一个推理引擎中,该引擎通过一个层次决策规则树来模拟人类的推理,该决策树还考虑了与规则相关的不确定性因素。我们的主要目的是说明用于天体分类问题的这种系统的制定和开发。已收集了MK标准光谱的广泛光谱数据库,并用作确定适合在MK系统中分类的光谱索引的参考。结果表明,通过考虑30个光谱指标并将它们与不确定因素相关联,我们可以找到特定光谱的MK类型的准确诊断。根据NOAO-INDO-US光谱目录对系统进行了评估。
展开▼