This research focused on advancing precision agriculture through deep learning-based disease detection for maize and tomato crops, utilizing the Edge Impulse platform for deployment on the Arduino Nano 33 BLE Sense. The maize dataset comprised 12,344 raw and 7,454 augmented color images, categorized into Blight, Common Rust, Gray Leaf Spot, Streak Virus, and Healthy classes. The tomato dataset included 16,947 images across five classes: Healthy, Leaf Blight, Leaf Curl, Septoria Leaf Spot, and Verticillium Wilt. Both datasets underwent preprocessing, including resizing, normalization, and augmentation techniques (rotation, flipping, and color adjustments), to ensure robust and diverse training data for improved model generalization.

Funders: UNESCO-TWAS program (Seed Grant for African Principal Investigators) financed by the German Federal Ministry of Education and Research (BMBF).

Duration: December 2022 - December 2024

Collaborating Institutions: 

• CSIR-Institute for Scientific and Technological Information (CSIR-INSTI)

• Kwame Nkrumah University of Science and Technology