I have a time-series classification problem with IoT signals. The training dataset has seven target signals.
I used tsai as a fastai/torch library, and I achieved satisfying results. However, in a production environment, there is a larger number of incoming signals (at this moment, 200+ signals). So, I have to 'filter' them before my classification.
Since I have target signals, my idea was to search for the most similar signals in all incoming signals.
My questions are:
- what Python library would you suggest for such an approach (finding the signals which are the most similar to the seven target signals)
- would you suggest another approach (and library) to solve this problem?
- could you share/point to a similar solved example on GitHub or a similar source?
Thank you
