HolfordM_4
Today was all about perfecting the trembling algorithm. We have gotten to the point where we can rule out all sorts of daily tasks that seem similar to trembling: chopping vegetables, blowdrying hair, and typing (among others). These all leave subtle traces in the data that allow octave to distinguish them from trembling. As this is a public forum, I will not go into any further detail.
The last thing to sort out is how to distinguish shivering from trembling. This becomes quite difficult as the two are extremely similar motions. It is also difficult to capture genuine shivering data to run tests on. This is an issue I tend to address with research as opposed to comparing data. Although the motion is the same, there may be differences in duration or intensity that could be picked up.
Anyway, that is an issue for tomorrow. We have made such good progress on the algorithm and entire hardware system — I’m pretty pumped to present nonetheless.
-Mira
BME Design 