AKM K. Islam

Work place: North Carolina Agricultural and Techincal State University/Department of Computational Data Science and Engineering, Greensboro, NC, 27411, USA

E-mail: akislam@ncat.edu

Website:

Research Interests: Machine Learning, Deep Learning

Biography

Dr. AKM K. Islam is an Assistant Professor and Graduate Coordinator for the Department of Computational Data Science and Engineering at North Carolina Agricultural and Technical State University, USA. He holds B.S. in Computer Science and Engineering from Jahangirnagar University, Bangladesh, MPH in Computing and Informatics from Bournemouth University, M.S. and PhD in Computer Science from Georgia State University, USA. He is an investigational and experimental computer scientist in the field of data mining, machine learning, and computational biology, who likes to contrive novel real-world problems with practical solutions through interdisciplinary collaborations that can affect the existing world and paves the way for future. His research interest focuses on designing and implementing machine learning and deep learning algorithms for biomedical image processing and bioinformatics gene expression analysis.

Author Articles
Reduction of Misclassifications in Wildfire Detection: A Weighted Ensemble Deep Learning Approach

By Lawrence Owusu Robert B Eshun Leila Hashemi-Beni Ali AlQahtani Masud R Rashel AKM K. Islam

DOI: https://doi.org/10.5815/ijisa.2024.05.05, Pub. Date: 8 Oct. 2024

Governments worldwide are increasingly prioritizing early wildfire detection to safeguard lives, property, and the environment. Although CNN-based models have demonstrated exceptional performance in various computer vision applications, the evolving nature of wildfire images poses significant challenges for a single CNN-based model in wildfire detection. In this study, we addressed this issue by integrating and weighting the differential learning capabilities of three individual transfer learning models: InceptionV3, ResNet50, and VGG16. Experimental results show that the ensemble deep learning models significantly outperformed all single classifiers across all performance metrics. Both the ensemble and weighted ensemble deep learning models achieved 99.7% accuracy, 99.5% precision, 100% recall, 99.8% F1-score, 0.5%false positive rate, 0.0% false negative rate and 0.3% error rate. Additionally, these models reduced the error rate by 98%, 91%, and 40% compared to the error rates of ResNet50, InceptionV3, and VGG16 respectively. A false negative rate of 0% indicates that our proposed ensemble deep learning models identified and predicted all the wildfire instances present in the test set correctly without a single misclassification. This positions our proposed ensemble deep learning models as superior choices for reducing misclassifications in wildfire detection.

[...] Read more.
Other Articles