空间中的k均值:辐射敏感性评估K-Means in Space: A Radiation Sensitivity Evaluation |
|
课程网址: | http://videolectures.net/icml09_wagstaff_kmis/ |
主讲教师: | Kiri L. Wagstaff |
开课单位: | 加州理工学院 |
开课时间: | 2009-08-26 |
课程语种: | 英语 |
中文简介: | 航天器越来越多地利用机载数据分析来为更多的数据收集和优先级决策提供信息。然而,许多航天器在高辐射环境中操作,其中数据密集计算的可靠性是未知的。本文首次研究了k均值聚类的辐射灵敏度。我们的主要发现是:1)k表示数据结构的灵敏度不同,灵敏度不是由暴露的存储量决定的; 2)在数据集相关的辐射阈值以下不需要特殊的辐射保护,使得使用更快,更小在某些情况下,更便宜的板载内存,以及3)子采样略微提高了辐射容限,但不幸的是,使用kd树降低了容差。我们的结论可用于定制k装置,以备将来在高辐射环境中使用。 |
课程简介: | Spacecraft are increasingly making use of onboard data analysis to inform additional data collection and prioritization decisions. However, many spacecraft operate in high-radiation environments in which the reliability of data-intensive computation is not known. This paper presents the first study of radiation sensitivity for k-means clustering. Our key findings are that 1) k-means data structures differ in sensitivity, and sensitivity is not determined by the amount of memory exposed, 2) no special radiation protection is needed below a data-set-dependent radiation threshold, enabling the use of faster, smaller, and cheaper onboard memory in some cases, and 3) subsampling improves radiation tolerance slightly, but the use of kd-trees unfortunately reduces tolerance. Our conclusions can be used to tailor k-means for future use in high-radiation environments. |
关 键 词: | 航天器; 优先级决策; 数据结构 |
课程来源: | 视频讲座网 |
最后编审: | 2019-04-25:cwx |
阅读次数: | 84 |