<aside> 💡 Breakthrough Project

</aside>

2024 April

Contributed to a Research Paper on Convolutional Neural Network Model for Disease Detection in Corn Leaf at All Growing Stages

Abstract

In Ghana, corn is a critical crop vulnerable to various diseases that impact yields. This research developed a Convolutional Neural Network (CNN) model to accurately detect diseases in corn leaves at all growth stages. The model, deployed in a Flask web application, addresses limitations of previous studies by focusing on both early and mature-stage corn diseases. The custom CNN model, with three convolutional layers, three max pooling layers, three fully connected layers, and an output layer, achieved a testing accuracy of 94.76% and a validation accuracy of 89.89%, along with high precision and recall rates. This model enhances early disease detection, enabling timely interventions to mitigate adverse effects on corn crop yields.

Contributions

As the primary author, I conducted comprehensive research, analysed data, and authored the paper. I was responsible for:

• Formulating the research question and hypothesis.
• Designing the methodology and conducting experiments/surveys.
• Analysing the data and interpreting the results.
• Writing and revising the manuscript to ensure clarity and coherence.

Skills Demonstrated

• Research and Analysis

Conducted thorough literature reviews, data collection, and statistical analysis.

• Technical Writing and Documentation

Authored a well-structured and coherent research paper, adhering to academic standards.

• Critical Thinking and Problem-Solving

Developed innovative solutions and approaches to address the research question.