The runner-up team designed another social solution, presenting a mobile application that can identify a baby’s needs when crying and alert parents. The team used a data set as the cry translator for classification analysis.
The most challenging part of the prototype was removing the background noise so the AI agent could correctly identify a baby’s emotion.
- ReSpeaker which include I2S microphone array for Raspberry Pi, USB microphone array for Linux/Windows/macOS, standalone ReSpeaker Core v1.0 & v2.0.
- A mobile app allowing for signaling the parents and bin identification via QR code.
- Donateacry-corpus is used to train a feed forward and a convolutional neural network in Keras.
- API to interconnect Raspberry Pi with the ReSpeaker and communication with Android app.
- Nursery and childcare places