The repr_paa computes PAA representation from a vector.
Usage
repr_paa(x, q, func)
Arguments
x
the numeric vector (time series)
q
the integer of the length of the "piece"
func
the aggregation function. Can be meanC, medianC, sumC, minC or maxC or similar aggregation function
Value
the numeric vector
Details
PAA with possibility to use arbitrary aggregation function.
The original method uses average as aggregation function.
References
Keogh E, Chakrabarti K, Pazzani M, Mehrotra Sh (2001)
Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases.
Knowledge and Information Systems 3(3):263-286