Samuel Donkor
email: sdamankwah@st.knust.edu.gh
department: Computer Science
Bio
I am a Computer Science student at Kwame Nkrumah University of Science and Technology interested in building efficient software systems to deliver social good. Currently, I'm working with Dr. Emmanuel Ahene to develop novel Deep Learning models and Privacy-preserving methods to consolidate and manage data to advance the health care domain.
In my free time , I develop and implement key algorithms and data structures targeted for analyzing real genomes and DNA sequencing datasets.
Projects
Some of my recent projects
Teaching
Courses, students, & mentorship
Entrepreneurship
Startups, initiatives, & innovations
Publications
My latest published research
News
2022
2021
Projects
I build impactful and efficient software systems to deliver social good. Here are a few of my most recent projects.
SignTalk - Sign Language Translation
SignTalk is sign language translation system that allows deaf and dumb patients to communicate effectively with their doctors by using the power of computer vision and deep learning. It is capable of both translation of speech-to-sign-language and sign-language-to-speech.
Healthcare acccessibility Map App
The healthcare accessibility map app computes the approximate travel time from every point to the nearest hospital (darker is longer) in Ghana.
Nonprofit Finder
This project connects donors and grantmakers to non-profit organizations. A platform to list verified NGOs/non-profit organizations in Ghana. The ultimate goals of this project is to verify NGOs operating in Ghana, expose verified NGOs to donors and volunteers looking, give donors/individuals conducting due diligence on a non-profit organization a way to do so seamlessly on the platform
English-Twi Translator
Twi translator is a machine translation app that generates translations of never-before-seen real-world input sentences from English to Twi. I implemented the model from scratch by training a sequence-to-sequence transformer in Python
Heart MRI Image Segmentation
The aim of this project is to build a predictive model that could classify each pixel in a cardiac MRI image based on whether the pixel is a part of the left ventricle (LV) or not. In medical imagery analysis it is often important to separate the pixels corresponding to different types of tissue, blood or abnormal cells so that we can isolate a particular organ. In this project I used the TensorFlow machine learning framework to train and evaluate an image segmentation network using a medical imagery dataset.
Land-Cover-Classification
This project introduces an example of a supervised land cover classification with Sentinel-2 data. The aim is to classify a Sentinel-2 image into four different land cover classes: water surfaces, artificial surfaces, low vegetation and tree cover.
Teaching & Leadership
In addition to research and building impactful projects, I am passionate about education and leadership, and strive to help and empower others to excel in their own pursuits.
Google Developer Student Clubs, Campus Lead
Organized and led 2-hour weekly sessions for 240+ college students that focused on exposure to programming through in-person events, study jams and hackathons
College of Science, School of Groups, Lead
Bridging the gap between theory and practice for students through weekly workshops and hackathons.
YouTube, Content Creator
I make videos on Youtube on topics that interest me, from Algorithms to AI to astrophotography
Google Explore ML, Facilitator
Teaching Machine Learning to members in my community and beyond, through high-impact workshops.
TechElevate, Instructor & Mentor 2021-Present
Offering programming workshops and mentorship to aspiring developers and students in Ghana, Africa.
HuggingFace, Student Ambassador
Teaching open-source machine learning to people from all kinds of backgrounds and showing my campus community how to build ML models with HuggingFace
Entrepreneurship
I am passionate about bringing breakthrough technological innovations that I create into the world, in order to positively impact our society and move humanity forward.
Chronos Health
A dedicated real-time engagement platform and remote patient monitoring mobile app that connects community health workers to health experts for medical advice and help doctors diagnose, treat and give proper medical advice to seniors, pregnant women, and mothers.
Publications
New publications coming soon !
Press
A collection of some of the news articles, TV interviews, and documentaries about my work