Large-scale spatio-temporal data hashing for efficient data analytics

大规模时空数据哈希以实现高效数据分析

• 批准号: DP180100966
• 负责人: Prof Chengqi Zhang
• 金额: $ 26.15万
• 依托单位: University of Technology Sydney
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2018
• 资助国家: 澳大利亚
• 起止时间: 2018-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP180100966
• 关键词: Large; scale; spatio; temporal; data

This project aims to systematically investigate the challenging problem of hash function learning for large-scale spatio-temporal data. The project will generate high quality hash codes for spatio-temporal data objects, enabling efficient similarity computation and thus supporting various data mining tasks and applications. The project expects to devise a series of learning frameworks by addressing the specific challenges of different types of spatio-temporal data, such as univariate and multivariate. The project will provide significant benefits to both academia and industry in massive spatio-temporal data analysing, for example traffic flow mining and optimisation, weather forecasting and financial fraud detection.

本项目旨在系统地研究大规模时空数据中哈希函数学习的挑战性问题。该项目将为时空数据对象生成高质量的哈希码，从而实现高效的相似性计算，从而支持各种数据挖掘任务和应用。该项目期望通过解决诸如单变量和多变量等不同类型时空数据的具体挑战来设计一系列学习框架。该项目将在海量时空数据分析方面为学术界和工业界带来重大好处，例如交通流量挖掘和优化、天气预报和金融欺诈检测。