Hierarchical mining algorithm for high dimensional spatiotemporal big data based on association rules

The traditional data mining algorithm focuses too much on a single dimension of time or space, ignoring the association between and which leads to large amount computation low processing efficiency makes it difficult guarantee final effect. In response above problems, hierarchical based rules for high-dimensional spatio-temporal big is proposed. Based rules, after establishing data, be mined are cleaned redundancy. After selecting local linear embedding reduce dimensionality strategy developed realize by searching frequent predicates form transaction database. simulation experiment results verify that has high complexity can effectively volume, improve at least 56.26% compared with other algorithms.