Mir Maruf Ahmed's picture
Real name: 
First Name: 
Mir Maruf
Last Name: 
Ahmed
Affiliation: 
Department of Computer Science, American International University-Bangladesh
Job Title: 
Student
Expertise: 
Machine Learning, Artificial Intelligence, Convolutional Neural Networks and Data Science
Short Bio: 
Mir Maruf Ahmed graduated from the American International University-Bangladesh (AIUB) with a Bachelor of Science degree in Computer Science and Engineering. A passion has marked his academic journey for learning new skills and technologies. He is a researcher focused on Machine Learning (ML), Artificial Intelligence (AI) and Data Science, with a particular interest in exploring neural networks and their applications in Deep Learning, including Convolutional Neural Networks (CNNs) and Artificial Neural Networks (ANNs). Throughout his academic career, Maruf has earned multiple honors and certifications, including being listed on the Dean’s List Honors for academic excellence. His areas of expertise include Cyber Security, IT support, Networking, Web Development, UI/UX Design, Software Quality Assurance and API Testing. He aims to contribute to the cybersecurity and digital media industries through his creativity, knowledge, and technical skills. His professional experience includes positions such as Junior Security Engineer at eTech Solution Ltd. and Customized OJS Plugin Theme Developer for AIUB Journal of Science and Engineering [AJSE]. His work has been published in journals such as IEEE Access, Springer and various Q1 and Q4 journals, highlighting his academic contributions. His notable projects include MOBDOG and AJSE, and his publications focus on topics like Leaf disease detection using convolutional neural networks and IoT-enabled models for enhancing food service operations in developing countries.

Datasets & Competitions

The potato plant disease detection dataset comprises 5,748 images of potato leaves categorized into six classes: Early Blight (1,000), Fungi (748), Healthy (1,000), Late Blight (1,000), Pest (1,000), and Virus (1,000). The dataset was collected from various open-access sources and integrated class-wise for comprehensive analysis. This dataset provides a robust foundation for training and evaluating convolutional neural networks in plant disease detection.

Categories:
276 Views