Back on the road...

[jay]

I'm about to head off to a meeting with FAA and NASA folks near Washington, DC tomorrow... just one night, then back in order to minimize the time spent away from patgreene in her currently-recovering state.

Otherwise... talked with Jeff S. about pattern-matching in time-series data... came up on the fly with a new approach. He promised me a footnote in his next paper ;-). A meeting with my boss was amiable, but led to more assignments for next week (a half-day review that I need to organize by next Tuesday). Our car was ticked by local police for not having current stickers on its license plates (dispute with the motor vehicles dept.). And I spent an hour in a 3rd-grade classroom this afternoon, discussing petrified wood and helping to dissect a cactus.

Comments

[daltong.livejournal.com]

I'm interested in the pattern-matching approach. Describe?

[brian1789.livejournal.com]

Looking at time series... if we non-dimensionalize and then try to compare them, looking for given patterns or for similarities that can be used to clasify them, how can we actually compare them? My thought was to discretize at different granularities (big slices, medium, and small slices) and then re-scan at each one, looking for patterns. Like taking music and trying to find a given three-note sequence, by first scanning it as a series of whole notes, then redoing it as all quarter notes, then sixteenths, etc., looking for the same three-note pattern at each level of detail. This would be used in classifying time-series Doppler-shifted astronomy data... seems reasonably simple to me.