Accelerating time series data base queries using dictionary based representations

A method for accelerating time series data base queries comprising the steps of:

• segmenting an original time series of signal values into non-overlapping chunks, where a time-scale for each of the chunks is much less than the time scale of the entire time series;
• representing time series signal values in each chunk as a weighted superposition of atoms that are members of a shape dictionary, to create a compressed time series;
• storing said original time series and said compressed time series into a database,
• storing in compressed form additional time-series derived from said original time-series to speed up a specific query;
• representing squares of time series signal values in each chunk as a weighted superposition of atoms that are members of a squared shape dictionary, to create a compressed squared time series, wherein a variance of said original time series is calculated from said compressed time series and said compressed squared time series;
• determining whether a query is answerable using said compressed time series or said original time series, and whether answering said query using said compressed time series is faster;
• and
• if answering the query is faster using the compressed representation, executing the query on weight coefficients of the compressed time series to produce a query result, and translating the query result back into an uncompressed representation.