This TinyML powered baby swing starts automatically when crying is detected

This TinyML powered baby swing starts automatically when crying is detected

Arduino Team — October 6, 2022

No one likes to hear their baby cry, especially when it happens in the middle of the night or when parents are preoccupied with another task. Unfortunately, turning on a motorized baby swing requires physically standing up and pressing a switch or button, which is why Manivannan Sivan has developed one that can automatically turn on whenever a cry is detected thanks to the machine learning.

Sivan began his project by first gathering real-world samples of crying sounds and background noise from an Arduino Portenta H7 and Vision Shield before tagging them accordingly in Edge Impulse Studio. From there, he created a simple pulse that takes time-series audio data and generates a spectrogram that is then used to train a Keras neural network model. Once fully trained, the model could accurately distinguish between the two sounds about 98% of the time.

Beyond simply classifying sounds from the two built-in microphones, Sivan's custom program also sets a relay to activate for 20 seconds if crying is detected, after which it shuts off until until crying is recognized again. He hopes to use this project as a practical way to help busy parents with the difficult task of calming a crying baby without the need for constant manual intervention. You can read more about it here on the Edge Impulse blog.

This TinyML powered baby swing starts automatically when crying is detected
This TinyML powered baby swing starts automatically when crying is detected

Arduino Team — October 6, 2022

No one likes to hear their baby cry, especially when it happens in the middle of the night or when parents are preoccupied with another task. Unfortunately, turning on a motorized baby swing requires physically standing up and pressing a switch or button, which is why Manivannan Sivan has developed one that can automatically turn on whenever a cry is detected thanks to the machine learning.

Sivan began his project by first gathering real-world samples of crying sounds and background noise from an Arduino Portenta H7 and Vision Shield before tagging them accordingly in Edge Impulse Studio. From there, he created a simple pulse that takes time-series audio data and generates a spectrogram that is then used to train a Keras neural network model. Once fully trained, the model could accurately distinguish between the two sounds about 98% of the time.

Beyond simply classifying sounds from the two built-in microphones, Sivan's custom program also sets a relay to activate for 20 seconds if crying is detected, after which it shuts off until until crying is recognized again. He hopes to use this project as a practical way to help busy parents with the difficult task of calming a crying baby without the need for constant manual intervention. You can read more about it here on the Edge Impulse blog.

What's Your Reaction?

like

dislike

love

funny

angry

sad

wow