Machine learning - time series

I have EMG signal data of hand gestures that has been labelled. I need a model to predict/forecast what hand gesture will be made as it is happening.

See the attached image to see what the data looks like. The data is set out as follows:

The first column is time in ms, then there are 8 channels for 8 sensors placed in various locations. The final column is the class of the row:
0 - unmarked data,
1 - hand at rest,
2 - hand clenched in a fist,
3 - wrist flexion,
4 - wrist extension,
5 - radial deviations,
6 - ulnar deviations,
7 - extended palm (the gesture was not performed by all subjects).

In your bid, please explain how you would approach this problem or it will be ignored.