7 ;;Quote: time series analysis should be linear in time and sublinear in space; use data reduction/transformation, indexing methods, and flexible similarity searching

9 ;;Quote: the easiest path wanders

28 ;;Quote: a few coefficients of the discrete Fourier transform capture most of the energy in pink (music), brown (stock), and black (ocean) noise

46 ;;Quote: piecewise aggregate approximation divides a time series into equal parts and records the average values; good for distance between series

61 ;;Quote: approximate a time series with singular value decomposition; good Euclidean distance; handles short bursts

61 ;;Quote: compare white noise by comparing to a sketch pool of random time series; sequences are similar if they are near to the same member of sketch pool

78 ;;Quote: the R-tree is a multi-dimensional index by bounding boxes; like the B-tree; efficient for points and regions

83 ;;Quote: a grid file guarantees multi-dimensional access in at most two I/O operations; the union of grid cells is a bounding box

103 ;;Quote: StatStream monitors 30,000 time series data streams for statistics and highly correlated pairs; use DFT and grid files; easily parallelized

106 ;;Quote: sliding window statistics by subdividing the window into basic windows; efficient elimination of old data and incorporation of new data