Rezoana Bente Arif
International University of Business Agriculture and Technology
Papers
1
Total Citations
60
H-Index
1
About
Rezoana Bente Arif is a researcher specializing in deep learning and computer vision, with a particular focus on the application of Convolutional Neural Networks (CNNs) to pattern recognition and image classification tasks. Her most notable contribution, the 2018 study "Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Convolutional Neural Network," has garnered 60 citations, reflecting its meaningful impact on the research community. In this work, Arif systematically investigated how architectural choices — specifically the number of hidden layers and training epochs — influence the accuracy of CNN-based handwritten digit recognition systems, providing valuable empirical insights for practitioners designing deep learning pipelines. Her research sits at the intersection of machine learning methodology and practical application, exploring how deep learning techniques can be optimized across diverse domains including medicine, engineering, natural language processing, and spam detection. For students and early-career researchers entering the fields of computer vision and neural network design, Arif's work serves as an accessible yet rigorous reference for understanding the sensitivity of model performance to fundamental architectural decisions.
Research Focus
Key Achievements
Top Papers
- 1