hardware
The Arduino 33 BLE sensor
lead
Jump line
software
Edge pulse workshop
Arduino IDE
Circuit schematic diagram
The circuit diagram of cough detection using Arduino 33 BLE Sense is given below. The Fritzing part of the Arduino 33 BLE is not available, so I used the Arduino Nano because they have the same pins
Create a dataset for the cough detector
As mentioned earlier, we are using Edge Impulse Studio to train our cough detection model. To do this, we have to collect a dataset that contains data samples that we want to be able to recognize on Arduino. Since the goal is to detect coughs, you need to collect some of these samples and some other noise samples in order to distinguish coughs from other noise.
We will create a dataset with two categories: "cough" and "noise". To create the dataset, create an Edge Impulse account, verify your account, and start a new project. You can load samples using your phone, Arduino board, or import datasets into an edge pulse account. The easiest way to load the sample into your account is to use your mobile phone. To do this, you must connect your phone to Edge Impulse.
To connect your phone, click Devices and then Connect New Devices.
