Segmenting real-valued data, be it speech waveforms into words and phrases or temperature readings into environmental epochs, is a challenging, open problem. We introduce an unsupervised, domain-independent algorithm, RIP-TIDE, that discovers segments in real-valued time series data while constructing a hierarchy of segments. Our top-down approach begins with a coarse approximation of the input data, finds segment boundaries, and recursively considers discovered segments with a finer resolution. We demonstrate the drawbacks of an existing segmentation algorithm and the multiresolution capabilities of a discretization method for time series. © 2007 IEEE.
CITATION STYLE
Armstrong, T., & Oates, T. (2007). RIPTIDE: Segmenting data using multiple resolutions. In 2007 IEEE 6th International Conference on Development and Learning, ICDL (pp. 306–311). https://doi.org/10.1109/DEVLRN.2007.4354058
Mendeley helps you to discover research relevant for your work.