Browsing by Author "Rakin, Rubayed Ahmmad"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    An Effective Deep Learning Network for Detecting and Classifying Glaucomatous Eye
    (Institute of Advanced Engineering and Science (IAES), 2023-10-20) Ahmed, Md. Tanvir; Ahmed, Imran; Rakin, Rubayed Ahmmad; Akter, Mst. Tuhin; Jahan, Nusrat
    Glaucoma is a well-known complex disease of the optic nerve that gradually damages eyesight due to the increase of intraocular pressure inside the eyes. Among two types of glaucoma, open-angle glaucoma is mostly happened by high intraocular pressure and can damage the eyes temporarily or sometimes permanently, another one is angle-closure glaucoma. Therefore, being diagnosed in the early stage is necessary to safe our vision. There are several ways to detect glaucomatous eyes like tonometry, perimetry, and gonioscopy but require time and expertise. Using deep learning approaches could be a better solution. This study focused on the recognition of open-angle affected eyes from the fundus images using deep learning techniques. The study evolved by applying VGG16, VGG19, and ResNet50 deep neural network architectures for classifying glaucoma positive and negative eyes. The experiment was executed on a public dataset collected from Kaggle; however, every model performed better after augmenting the dataset, and the accuracy was between 93% and 97.56%. Among the three models, VGG19 achieved the highest accuracy at 97.56%.
  • Thumbnail Image
    Item
    E-Learning Emergence:
    (Daffodil International University, 2024-07-13) Rakin, Rubayed Ahmmad
    This study explores the growth of e-learning in Bangladesh, analyzing its socioeconomic, environmental, and sustainability implications using survey data. The analysis includes aspects like internet connectivity, device usage, study hours, course quality, efficacy, engagement, and affordability. This study applied seven machine learning classification models—Logistic Regression, Random Forest, K-Nearest Neighbors, Support Vector Machine, Gaussian Naïve Bayes, Decision Tree, and XGBoost. Random Forest notably outperformed with 78.22% accuracy in predicting the potential of online education to replace traditional methods. According to the findings, 98.8% of students had regular internet access, with 50% reporting extremely stable connections. 60.9% of respondents use smartphones as their primary device, highlighting the need for mobile-friendly learning systems. Approximately 50% of students spend less than five hours each week on online learning platforms such as YouTube and Zoom. 68% of students assess course quality positively, while 33.7% believe online classes are more effective than traditional methods. Despite these advantages, obstacles such as technological difficulties, a lack of desire, and feelings of isolation remain. To overcome these difficulties, the research advises increasing technical assistance, creating interesting material, and boosting teacher training. Furthermore, advancements in internet infrastructure and device accessibility are crucial to the sustained expansion of e-learning. The paper continues with recommendations for future research, emphasizing the importance of longitudinal studies to measure e-learning's long-term impact, as well as the potential benefits of hybrid learning models that blend online and traditional teaching approaches. All things considered, e-learning in Bangladesh has a lot of promise, but for it to grow sustainably, it must overcome current obstacles.