I spent the majority of my time at the beginning of the week preparing and delivering the design review presentation. This was pretty stressful and I think there are a lot of things I would do differently, but it was fun to do a presentation like that for the first time.
My next main task for this period was to make sure we were receiving data from our IMU and formatting that data to look like what we wanted it to feed into our ML model and concatenate with the flex sensor readings. I found that the acceleration readings were a pretty all-encompassing way to capture orientation data. As explained in the previous report, adding up the components in the x, y, and z directions gives us the downward g force, so the breaking down of those components tells us exactly what angle our hand is at. I decided to quantize that data to the nearest .5 to simplify readings but also provide detailed measurements without potential model overfitting.