Converting Multiple Time-series Signals into One Spectrogram

user_16581206 0
Viewed 224

Is it possible to combine multivariate time series signals (from the same event) and convert them to the frequency domain to feed a spectrogram? I would like to convert these signals to the frequency domain so that I can perform a Convolutional Neural Network and predict classifications of events.

So far, I've only seen examples using just ONE (1) time series, not multidimensional. Such as pictured here below.

Time Series to Spectrogram enter image description here

As an example, let's assume (in the figure below) this is the data I collected in multiple time series for 1 day in the year. I've collected similar data for 30 other days. I want to combine the signals in a way to create a frequency spectrogram.

Multivariate enter image description here Can this be done? What are some ways to perform this operation?

data-science conv-neural-network machine-learning computer-science frequency
1 Answers

Can you please provide the code/github link of that one time series conversion

user_165840040
Related