Similarity search of time series can be efficiently handled through a multi-resolution representation schemewhich offers the possibility to use pre-computed distances that are calculated and stored at indexing timeand then utilized at query time together with filters in the form of exclusion conditions which speed up thesearch. In this paper we introduce a new multi-resolution representation and search framework of timeseries. Compared with our previous multi-resolution methods which use first degree polynomials to reducethe dimensionality of the time series at different resolution levels, the novelty of this work is that it appliesHaar wavelets to represent the time series. This representation is particularly adapted to our multi-resolutionapproach as discrete wavelet transforms have the ability of reflecting the local and global informationcontent at every resolution level thus enhancing the performance of the similarity search algorithm, which iswhat we have shown in this paper through extensive experiments on different datasets.
展开▼
