I have frequency EEG data from fall and non-fall events and I am trying to incorporate it with accelerometer data that was collected at the same time. One approach is, of course, to use two separate algorithms and find the threshold for each. Then comparing the threshold of each. In other words, if the accelerometer algorithm predicts a fall (fall detected = 1) and the EEG algorithm detects a fall, based on the power spectrum (fall detected = 1), then the system outputs a "1" that a fall was truly detected. This approach uses the idea of a simple AND gate between the two algorithms.
I would like to know how to correctly process the data so that I can feed both types of data into one algorithm, perhaps a CNN. Any advice is really appreciated, even a lead to some literature, articles or information would be great.