On Thu, Aug 24, 2017 at 7:07 AM, David Winsemius <dwinsemius at
comcast.net>
wrote:
>
> > On Aug 23, 2017, at 10:06 PM, Dhivya Narayanasamy <dhiv.shreya at
gmail.com>
> wrote:
> >
> > I have a vibration signal coming accelerometer. I converted this
signal
> from*
> > m/s^2* to *mm/s*. Now I am supposed to predict this vibration signal
in R
> > using historical data. (Please see the attached picture of vibration
> > signal).
>
> The dimensional analysis of the second sentence does not make scientific
> sense.
>
>
Not so! If you know the initial v and a(t) you can compute v(t) by
integration.
For example if you drop something then v(0)=0, a(t)=-g, then you can
compute v(t)
The question has been posted to Data Science Stack Exchange if anyone wants
to see the picture...
https://datascience.stackexchange.com/questions/22466/processing-the-vibration-signal-before-prediction
Barry
[[alternative HTML version deleted]]
