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

点击翻译按钮获取中文摘要

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.