Browsing by Author "Hoque, Ariful"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    DenseNet based skin lesion classification and melanoma detection
    (BRAC University, 2021-06) Munaf, Arifuzzaman; Hoque, Ariful; Jawwad, Kazi Asif; Alam, Md. Golam Rabiul; Mostakim, Moin
    In the language of medical science, the most harmful variant of skin cancer that may develop in human cells is distinguished as melanoma. The principal reasons behind developing melanoma in human skin are still unknown. However, scientists assume that the risk of developing melanoma increases due to exposure to ultraviolet radiation emitting from the sun. The increased rate of melanoma cancer is now a threat to the medical sector to cope with the increasing number of patients. Many scientists have already researched and tried to develop different projects to identify melanoma efficiently. Skin lesions are the best approach to find the symptoms of melanoma and predict the possibility of cancer growing in the skin. In this research paper, the main objective is to classify different types of lesions and find melanoma from skin lesion images using DenseNet-121 which is a densely connected CNN-based algorithm. We evaluated on 5066 imbalanced test images from ISIC 2019 Challenge dataset for initial classification of lesion images. We also organized the dataset into a balanced dataset by over sampling and downsampling where 600 test images were used for validation. The evaluation of imbalanced and balanced datasets results in respectively 80% and 84% accuracy for lesion images classification. Moreover, we normalized the dataset into two different classes which consists of melanoma and non-melanoma lesion images to perform binary classification. In this stage, we executed our model on 2000 test images and got an accuracy of 89% for classifying melanoma accurately.
  • No Thumbnail Available
    Item
    Web Based Ed-Tech Platform
    (Daffodil International University, 2025-05-14) Hoque, Ariful; Ahmed, SM. Faisal
    This project describes the design and development of a Ed-Tech platform aimed at filling the gap between traditional and digital education systems, as it provides the overall modular and user-oriented learning experience. As the demand for remote education rises, our objective is to develop a web-type application in which the learners can study whenever and wherever they want using an internet connection alone. The platform has a vast number of learning features such as pre-recorded video classes, structured assessment, authentication of users, and future-ready AI-assisted learning. It is built upon Spring Boot (Java 17) for backend programming, PostgreSQL to guarantee secure storage of facts, and Docker for viable and containerized deployment. Keycloak is for secure and flexible identity management; IntelliJ IDEA Ultimate and other industry-standard tools are for the development work. It is designed in a modular manner and it is easily expandable and customizable in future. Even though the existing version is only used in a local environment and has not incorporated certain features such as real time AI integration and cloud deployment because resources are limited, it provides a strong base for an expansion. The corresponding functional testing provided reliability of the core features, while API and performance testing is left for future stages. During the project, we adhered to the engineering standards and the impacts of being ethical, social, and sustainable considered, highlighting inclusive and lifelong learning. All phases of the project are described in this report from problem identification and requirement analysing, through methodology, implementation, testing, and difficulties. Additionally, it gets into budget planning and project management strategies as mapped the work against complex engineering problem-solving criteria. By constantly supporting this platform, it has potential to integrate such advanced technologies as virtual reality, online exams modules, interactive code compilers, etc and even AI personalized teachers so that it redefines education delivery and access in the digital world.