I have a question. A stationary point may be found at 4115226337 that locks down with 3160493827. Also the chart number 1001031215 presents opportunity. Can you recommend a channel that broadens this?
I really enjoy your content and it has been very helpful in my research. Thank you! I just have one question that would be great to get an answer to. If we now assume that the signal being analysed is non-stationary, is there a theoretical way of finding the "cutoff frequency" of the resulting wavelet convolution as a function of number of cycles used in the wavelet? As you point out in your video, there will be an averaging effect taking place if the stationarity assumption don't hold.
I think that info would be in the power spectrum of the wavelet. You could quantify the FWHM of the power spectrum to quantify the amount of spectral smoothing that gets imposed on the data.
Have been binging this lecture series. Thanks!
You rock, Ruben.
I have a question. A stationary point may be found at 4115226337 that locks down with 3160493827. Also the chart number 1001031215 presents opportunity. Can you recommend a channel that broadens this?
Super cool and informative lectures! Thanks!
You're welcome!
I really enjoy your content and it has been very helpful in my research. Thank you! I just have one question that would be great to get an answer to. If we now assume that the signal being analysed is non-stationary, is there a theoretical way of finding the "cutoff frequency" of the resulting wavelet convolution as a function of number of cycles used in the wavelet? As you point out in your video, there will be an averaging effect taking place if the stationarity assumption don't hold.
I think that info would be in the power spectrum of the wavelet. You could quantify the FWHM of the power spectrum to quantify the amount of spectral smoothing that gets imposed on the data.
I like number theory and would greatly appreciate an ave. Out of P and Q
Very nice and thanks