TSuNAMi: Time Series Network Animal Modelling

TSuNAMi：时间序列网络动物建模

• 批准号: DP200102961
• 负责人: Prof Michael Small
• 金额: $ 25.28万
• 依托单位: The University of Western Australia
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2020
• 资助国家: 澳大利亚
• 起止时间: 2020-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP200102961
• 关键词: TSuNAMi; Time; Series; Network; Animal

Our proposal is motivated by and based upon the successful representation of time series as a network (or graph). We construct an abstract representation of a system from measurements of its changing behaviour over time. Properties of that structure (the network) then allow us to infer diagnostic information of the system. Specifically, we propose to apply this to livestock welfare during transport. By measuring the biological and environment condition of the animal we construct a network representation of that system. Geometric features of that network can then be used to infer health or duress of the subject. This proposal will develop the generic mathematical machinery to connect geometric features of the network with system behaviour.

我们的建议是基于时间序列作为网络（或图）的成功表示而提出的。我们通过测量其随时间变化的行为来构建系统的抽象表示。然后，该结构（网络）的属性允许我们推断系统的诊断信息。具体来说，我们建议将其应用于运输过程中的牲畜福利。通过测量动物的生物和环境条件，我们构建了该系统的网络表示。然后，该网络的几何特征可以用来推断受试者的健康状况或受胁迫程度。该建议将发展通用的数学机制，将网络的几何特征与系统行为联系起来。