Wavelet based data compression methods have demonstrated superior performan
ce over the conventional interpolative methods. However, the wavelet based
methods need thresholding on the wavelet domain coefficients. Since wavelet
coefficients are not commonly intuitive to engineers, significant a priori
knowledge of either the wavelet coefficients or process thresholds is requ
ired. So unless thresholds are pre-specified, this requirement makes wavele
ts unsuitable for on-line implementations. Furthermore, as the relation bet
ween the wavelet domain coefficients and the measures of the quality of com
pression [root mean square error (RMSE) and local point error (LPE)] is not
straightforward, it is difficult to achieve good control over the quality
of compression by specifying thresholds on the wavelet coefficients. In thi
s paper, an error based criterion is proposed for online wavelet data compr
ession. It uses semantically straightforward measures of the quality of the
result to be obtained to adaptively calculate the thresholds. Given a boun
d on time domain error limits like the RMSE and LPE, this technique adaptiv
ely computes the threshold values in wavelet domain. Experiments show that
the resulting algorithm gives superior compression as compared to other wav
elet based methods. Most importantly, it can be used on-line and provides a
n effective way of controlling LPE and RMSE. Finally, this method can easil
y be extended to other on-line wavelet applications such as data rectificat
ion and de-noising. (C) 2001 Elsevier Science Ltd. All rights reserved.