Idea
Imagine you come back home after a stressful day and you are feeling angry, sad, or hopefully happy.
It would be nice coming back to a place which feels like it’s emphatizing with you, adapts to your mood and tries to comfort you as best as possible.
Pyna is a device which can detect your mood and set the right atmosphere for you, through music, light and potentially much more.
Project history
This project started as a three day prototype for a hackathon, with the theme of creating a mood reader.
Despite being a team of all first year bachelor students, against older master students, we managed to win the hackathon and gain access
to a lab to further develop our idea over six months.
We then displayed our protoype at the Turin Maker Faire 2018, the project was a crowd favourite and gained us a boot at the much bigger and famous Maker Faire Rome 2018.
There we replicated our success and got noticed by the press which decided to interview us.
Project structure
The project had two main parts:
- locally, a Raspberry Pi with a camera and a speaker, enclosed in a 3d printed enclosure
- remotely, a private cloud server which managed interfacing with several APIs and processing
The phases
- the user is in proximity of the pyna device
- the user’s face is detected by a face detection algorithm, running continuously on the raspberry pi
- a picture of the face is sent to the private cloud server
- the server requests to a third party API to detect the mood of the user, from the face picture
- the mood metric is used to select a light color
- the mood metric is processed, along with information about the user’s preferred music genre, to choose the correct music from Spotify
- requests are sent to Spotify API and Philips Hue API to set the correct song and light color
- The user mood is logged and displayed on a dashboard
Details
Each user has the possibility to link its spotify account and choose some favourite genres, which allows for customisation: for somebody happy songs might come from ACDC, for others from Coldplay.
Songs are chosen from the whole spotify catalogue, allowing for infinite choices, based on the preferred genres and a metric we
designed.
The device would activate randomly during the day to try and capture the user expression automatically and
discreetly, this should allow continuous and unbiased monitoring.
If the detected mood was good, the device would have an easy job of keeping the mood joyful.
If instead the mood was bad, the device would start from choosing “sadder” colours and music
(for example indigo light and Summertime Sadness from Lana Del Rey), slowly shifting to “happier” colours and more joyful music (like yellow light and MrBrightside from the Killers).
The idea was that of walking alongside a friend who’s feeling bad, you would first try to understand their mood, emphatizing with him, then you would try to make him think of better things and be happier.
Disclaimer
Reading the mood through vision only may obviously be not very accurate in a real life scenario, however for the purpose of the hackathon it was the only thing we had at our disposal.
Also, our ideas about improving the user mood were not based on psychology research, don’t take them as serious advice :) .