So, this week I decided to test the TinyDecisionTreeClassifier with my fan to see if it can recognize the 'broken' fan movement. 

Nothing fancy, one minute of training data for each state(ok/failure), then few seconds of training process, then it can magically recognize the state. Also, I had to increase the accel sampling frequency to 50 Hz. I used Nrf52840, but it should work with any Arduino-compatible MCU that has enough SRAM(like Esp32).