Building the dataset with the Edge Impulse data forwarder tool

Any ML algorithm needs a dataset, and for us, this means getting data samples from the accelerometer.

Recording accelerometer data is not as difficult as it may seem at first glance. This task can easily be carried out with Edge Impulse.

In this recipe, we will use the Edge Impulse data forwarder tool to take the accelerometer measurements when we make the following three movements with the breadboard:

Figure 6.11 – Gestures to recognize – circle, cross, and pan

As shown in the preceding diagram, we should ensure that the breadboard is vertical, have our Raspberry Pi Pico in front of us, and make the movements that are shown by the arrows.

Getting ready

An adequate dataset for gesture recognition requires at least 50 samples for each output class. The three gestures that we've considered for this project are as follows:

• Circle: For moving the board clockwise...