Human centered design project in Nairobi Kenya focused on tackling stigma around reproductive health.
Make this yours. Add images, text and links, or connect data from your collection.
Make this yours. Add images, text and links, or connect data from your collection.
Usinisunde Nichapie
“Don’t hide from me, just tell me”
This movement empowers youth through collaboration and drama, giving under-served communities a louder voice to speak about SRH topics, effacing the stigma against allowing the youth free access to SRH facilities. The youth, woke and ambitious, produce and perform this profound story.
Our research began by speaking to clinicians, healthcare providers and adolescents to identify pain points preventing youth from accessing SRH facilities.
We identified that the primary barrier preventing youth from accessing SRH facilities is the stigma surrounding SRH issues.
We created a play guide which tackled key SRH pain points identified by the youths. Our concept is heavily inspired by the stories of the 25 young adolescents, shared in 4 different creative workshops where we got to know each of them personally.
Knock Knock
Machine Learning / UI & UX / Agriculture
Challenge
Solution
Team
How Might We help the food industry detect harmful foods?
Do you remember when your grandma knocked on watermelons to see if they were ripe? The subtle art of picking out fresh produce is a dying art.
Exploring sound diagnostics through everyday experience, Knock Knock is a mobile application concept that uses machine learning algorithms to discover the ripeness of fruits.
Interdisciplinary team of designers & engineers. Hanson Cheng, Bahareh Saboktakin Rizi, Fay Feng, and Hugo Richardson.
App Flow
Machine Learning
Image & Sound Data
Using image and sound data we would be able to determine the ripeness of a fruit.
Image Data
Fruits are classified by color, shape and size. We created an initial data set of labeled image data to then train the sound machine learning algorithm. We validated our idea by training a convolutional neural network model for real time object detection using Tensorflow.
Sound Data
We gathered a library of audio files from knocking on objects.
Using the API The Fast Fourier Transform (FFT) converts knocks of the collected audio files from time to the frequency domain.
This shows a promising pattern that could be used for further classification.