Detect and track worker falls with built-in ML

Detect and track worker falls with built-in ML

Arduino Team — September 7, 2022

Some industries depend on workers being able to reach high spaces through the use of ladders or mobile standing platforms. And because of their potential danger in the event of a fall, Roni Bandini had the idea to create an integrated system capable of detecting a fall and automatically reporting it in a wide variety of scenarios.

A fall can be detected by measuring changes in acceleration; therefore, Bandini opted for an Arduino Nano 33 BLE Sense board because of its built-in three-axis accelerometer. It also supports low power consumption, meaning a LiPo battery and accompanying TP4056 charging module can be added for completely wireless operation. Acceleration data was collected by taking multiple samples in Edge Impulse Studio and labeling them either "fall" or "hold" when no motion is present. Once tested, the resulting model was integrated into an Arduino sketch, which emits a Bluetooth® advertising packet whenever a drop is detected.

The collection of each of these packets is the responsibility of a central Raspberry Pi server. It runs a Python script that constantly checks for new BLE ad data and inserts a new record into its base file. given accordingly. All of this data can then be queried in a separate script and used to create a graph showing how many times each worker fell.

More details can be found in Bandini's project description and Edge Impulse's blog here.