• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Applications and Techniques in Cyber Intelligence >Automatic Classification of Dwarf Nova
【24h】

Automatic Classification of Dwarf Nova

机译：自动分类Dwarf Nova

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Dwarf nova is an abundant subtype of cataclysmic variable star with frequent eruptions. This binary star is a semi-close binary system consisting of a late dwarf secondary star with loch lobes and a White Dwarf host star. Finding more dwarf novae can help us to study the dynamic evolution of the system and many complex physical processes. Recently, deep learning plays an important role in the domain of signal processing. This paper focuses on dwarf nova classification on the basis of deep learning. As a classical technique of deep learning, Isomap preserves the nonlinear structure of high dimensional spectral data so as to facilitate the classification. The distance between the sample points of the dwarf nova spectrum is significantly smaller than the distance from other unknown stars, thus providing a good pretreatment for spectral classification. In this paper, Isomap technique is exploited to analyze the high-dimensional data structure of dwarf nova and to classify it. Computer simulations illustrate that the proposed technique has better accuracy and reliability in contrast to other existing means.
机译：Dwarf Nova是一种丰富的灾难性可变星亚型，频繁爆发。该二进制星是一个半关键的二元系统，由矮小的矮小二级明星组成，含有洛奇叶片和白色矮人宿主恒星。寻找更多矮人Novae可以帮助我们研究系统的动态演变和许多复杂的物理过程。最近，深度学习在信号处理领域发挥着重要作用。本文侧重于深度学习的矮人新星分类。作为深度学习的经典技术，ISOMAP保留了高维光谱数据的非线性结构，以便于分类。矮化Nova谱的样本点之间的距离显着小于与其他未知恒星的距离，从而为光谱分类提供良好的预处理。在本文中，利用ISOMAP技术来分析Dwarf Nova的高维数据结构并进行分类。计算机模拟说明了与其他现有手段相比，所提出的技术具有更好的准确性和可靠性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号