C-MAC Ghana C-MAC Ghana

Active Research Projects

Search, filter, and inspect C-MAC Ghana’s computational research projects, deep learning medical models, and precision agricultural telemetry systems.

Medical AI
Medical Computing

Multi-Architecture CNN for Anemia Screening

Deep learning model utilizing conjunctival micro-vasculature imagery for real-time pediatric iron deficiency screening.

Technologies:
PyTorch ResNet-50 FastAPI
Research Project
Data Analytics
Medical Analytics

Predictive Analytics

Creating machine learning models to predict disease progression and treatment outcomes.

Technologies:
Scikit-learn XGBoost Pandas
Data Modeling
Health DB
Systems

Secure Health Data Infrastructure

Designing compliant, offline-first database systems for rural health centers.

Technologies:
PostgreSQL Docker AES-256
Platform Dev
Precision Agriculture
Agro Analytics

Precision Agriculture

IoT-based systems for real-time monitoring of soil conditions, weather patterns, and crop health.

Technologies:
Arduino LoRaWAN ThingsBoard
IoT Systems
Crop Disease Detection Agro Tech
Agro Analytics

Crop Disease Detection

Computer vision algorithms for early identification of plant diseases using mobile devices.

Technologies:
OpenCV TensorFlow Lite MobileNet
Computer Vision
Agriculture
Agro Analytics

Yield Prediction

Machine learning models to predict crop yields based on historical data and environmental factors.

Technologies:
XGBoost Prophet GeoPandas
Data Modeling

Research Collaborations

Partnering with leading institutions for greater impact

KTU Logo

Koforidua Technical
University

Computer Science Department

GCTU Logo

Ghana Communications
Technology University

Computer Science Department

MUG Logo

Methodist University Ghana -
Accra

Department of I.T and Mathematical Sciences

Research Impact & Outcomes

Transforming research into real-world solutions

Healthcare Impact

Healthcare Impact

AI diagnostic tools deployed in 10+ healthcare facilities, improving early disease detection by 40%

Agricultural Impact

Agricultural Impact

Smart farming solutions increasing crop yields by 35% for 500+ smallholder farmers

Capacity Building

Capacity Building

Training 200+ African researchers in AI and data science methodologies

Innovation Labs & Infrastructure

State-of-the-art facilities driving groundbreaking research

AI Research Lab

AI Research Lab

  • NVIDIA DGX Systems
  • High-Performance Computing Cluster
  • Medical Imaging Workstations
Data Science Center

Data Science Center

  • Big Data Analytics Platform
  • Cloud Computing Infrastructure
  • Data Visualization Tools
Research Portfolio

Recent Publications

Explore the latest findings and technical reports published by Dr. Justice Williams Asare and the C-MAC Ghana team.

2026 • Engineering Reports

A Smartphone and Web‐Based Automated Platform for Segmenting Urinary Tract Infection Using a Deep Learning‐Based Approach

Developing an accessible mobile application backed by advanced deep learning techniques to rapidly and accurately diagnose urinary tract infections.

2026 • Communications in Computer and Information Science

A hybrid three-layer convolutional neural network architecture for detecting anemia using clinical images

Proposing a novel, highly accurate CNN architecture designed for the rapid classification and non-invasive detection of anemia using standard clinical imaging.

2026 • Journal of Electrical Systems and Information Technology

Application of artificial intelligence for okra leaf and other plant disease detection and diagnoses: a systematic literature review

A comprehensive review of how modern AI and computer vision models are transforming early disease detection in agricultural settings.

2024 • Informatics in Medicine Unlocked

Application of machine learning approach for iron deficiency anaemia detection in children using conjunctiva images

Evaluating machine learning pipelines that analyze eye conjunctiva images to estimate hemoglobin levels and detect anemia without invasive blood tests.

2023 • Engineering Reports

Iron deficiency anemia detection using machine learning models: A comparative study of fingernails, palm and conjunctiva of the eye images

A comparative study analyzing different bodily features to determine the most effective visual indicators for machine-learning-based anemia screening.

Want to see more research?

View All Publications on ResearchGate
Academic Reference

Cite Research Paper


      
✓ Copied to clipboard!