Accurate and online abnormality detection in multiple correlated time series

多个相关时间序列的准确在线异常检测

• 批准号: DE130100911
• 负责人: Prof Jing He
• 金额: $ 24.83万
• 依托单位: Swinburne University of Technology
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Early Career Researcher Award
• 财政年份: 2013
• 资助国家: 澳大利亚
• 起止时间: 2013-04-29 至 2019-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DE130100911
• 关键词: Accurate; online; abnormality; detection; multiple

This study will develop a new kernel-based and online support vector regression method for real-time and correlated multiple time series and promote their use in critical applications, which will save money and lives. Examples include the detection of stock market crisis events and detection of patients' condition deterioration in the operating theatre.

这项研究将开发一种新的基于核的在线支持向量回归方法，用于实时和相关的多个时间序列，并促进其在关键应用中的使用，这将节省资金和生命。例如，检测股票市场危机事件和检测手术室中病人的病情恶化。