Skip to content

Care Mask


Smart Factory, smart manufacturing

Using Azure IoT and Azure Sphere Board


By the research in Manufacturing statistics in Great Britain, 2020, we know that up to 15% of fatal injuries were caused by contact with machinery.

When an emergency happens, when will the machine stop? As we know, the machine stops when detecting it involves an abnormal object. When a machine involves abnormal objects, involvement might cause injuries that are already too late to stop the machine.

So, we decide to stop the machine immediately when emergence happens by using sensors and machine-learning techniques.

To stop the machine, we acknowledge that putting sensors on the machine makes difficulty high caused by different volumes of machines. So we change our target to humans because the relation of humans is an obvious signal to tell whether this person is in an emergency or not.


The fight-or-flight response is a physiological reaction that occurs in response to a perceived harmful event, attack, or threat to survival. [1]

The most known physical effects are

  • Acceleration of heart and lung action
  • Paling or flushing, or alternating between both
  • Inhibition of stomach and upper-intestinal action to the point where digestion slows down or stops
  • Constriction of blood vessels in many parts of the body
  • Dilation of blood vessels for muscles
  • Inhibition of the lacrimal gland (responsible for tear production) and salivation
  • Dilation of the pupil
  • Shaking



Besides detecting the signal of the physical effects caused by the fight-or-flight response, we need a reaction that generates fast enough to stop the emergency timely. In this case, we select the effect from the lung, which is breath.

Breath can be easily detected by the microphone. We designed a mask that contains a microphone and built a Deep-Learning model to detect the emergence by sound inside the mask.

Prototype of Care Mask
Prototype of Care Mask


Before building our model, we would have to make sure that breath is detectable from our microphone. By using Fourier transform, we could draw a spectrogram to visualize the composition of sound.

Spectrogram of sample sound
Spectrogram of sample sound

It could be seen that the feature is obvious, which means that detecting emergence is quite possible.


Input Data: Time series of 22050 values per second

Output Data: 4 categories (no breath, breath, cough, speak)

CareMask Model
CareMask Model

In the end, we used 11,128 parameters and achieved 95.778% accuracy.


  • [1]: