Analysis of numeric data streams at different granularities

A novel method for analyzing time-series data and extracting time-correlations (time-dependent relationships) among multiple time-series data streams is described. The proposed method is the first online method that can detect and report time-dependent relationships among multiple time-series data streams. Time-correlations tell us the relationships among numeric variables whose values are recorded over the course of time and transmitted using time-series data streams. Each time-correlation rule explains how the changes in the values of one set of time-series data streams influence the values in another set of time-series data streams. Those rules can be stored digitally and fed into various data analysis tools for further analysis. Performance experiments showed that the described method is 95% accurate, and has a linear running time with respect to the amount of input data.