Many practical time series, including pressure signals measured on roof-cor
ners of low-rise buildings in quartering winds, consist of relatively quies
cent periods interrupted by intermittent transients. The dyadic wavelet tra
nsform is used to detect these transients in pressure time series and a rel
atively simple pattern classification scheme is used to detect underlying s
tructure in these transients. Statistical analysis of the resulting pattern
classes yields a library of signal "building blocks", which are useful for
detailed characterization of transients inherent to the signals being anal
yzed.