http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/34 Fri, 17 Apr 2026 12:03:32 GMT 2026-04-17T12:03:32Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16880 Design and Implementation of e-learning Based Website: EduSell Samrat, Gazi Shahriar The online marketplace known as EduSell provides users with an innovative platform to conduct course purchases and sales between learners. By using the platform people can explore numerous educational opportunities before making secure transactions to access valuable content at times convenient for them. Among EduSell's features the platform provides a discussion forum that enables students to communicate with educators and classmates for improved learning outcomes as well as built-in software promotion tools that extend educators to present training materials or relevant applications to their courses. Learners benefit from this feature since it improves course value by providing them with essential resources. EduSell implements a rigorous review platform that permits users to evaluate courses and instructors while assisting fellow students with essential choices. The backend structure operates through Node.js with Express.js programming along with frontend development using React.js and DaisyUI for providing an intuitive user interface. The platform utilizes MongoDB as a storage system that efficiently manages data along with a safe payment processing gateway integrated for transactional operations. The system gives administrators access to a control panel that enables them to manage users alongside courses and promotions in addition to analyzing system performance. The development cycle of EduSell depends on user suggestions because it uses an iterative approach. This platform works to develop an all-inclusive digital learning space which smoothly unites teachers with students and educational software developers. Project Report Mon, 05 May 2025 00:00:00 GMT http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16880 2025-05-05T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16878 ProstadeNet: A High Accuracy Fine-Tuned CNN Model for Prostate Cancer Grade Detection from Enhanced Histopathological Images Kaif, Sheikh Prostate cancer is the leading malignancy within the bodies of men globally and it is also the fifth most common cause of male cancer mortality. Prostate cancer needs to be diagnosed early in order to reduce mortality and give better treatment to concerned individuals. Although traditional methods of diagnosing prostate cancer are time-consuming, computer-aided diagnosis systems provide a quicker diagnosis without any loss of accuracy. There is a very alarming need for fast, accurate, and economical diagnostic processes of this epidemic. The main goal of this research is to recommend an effective framework for grading classification of prostate cancer from histopathological images with six classes with fewer errors of classification. Various image augmentation preprocessing techniques have been utilized for improving the quality of images, and four different augmentation techniques to enhance the dataset size and reduce model overfitting problems. Finally, a novel ProstadeNet architecture which is a tuned CNN tuned in structure and hyperparameters by ablation study will be presented. The ProstadeNet model achieved an accuracy of 99.83%. To estimate the capacity of ProstadeNet, relative experiments with five typical transfer learning models will be conducted to find out its relative performance. K-fold validation will be used in measuring results. Various performance measurements have been used to show the robustness of the models. Project Report Wed, 14 May 2025 00:00:00 GMT http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16878 2025-05-14T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16871 Tomato Leaf Disease Detection and Classification using Deep Learning. Sharmin, Sabrina Tomato is also a profitable crop in Bangladesh and many other countries because of its high price and market value. But the development and productivity of tomato are constantly threatened by several kinds of leaf diseases, which rapidly damage these plants. The early diagnosis of plant illness and continuous monitoring of plant health are important for the removal of factors that affect crop yield. This work presents an automatic way to detect and recgnize tomato leaf diseases by a novel deep learning mechanism. For tomato forest-based diseases, we create the custom dataset which has 600 labeled images includes 150 images for Tomato Early Blight, 150 images for Tomato Late Blight, 150 images for Tomato Leaf Mold, and 150 images are healthy for leaves. These images were captured directly from local farm fields to be as practical as possible. Four pretrained CNN models VGG16, VGG19, ResNet50V2, and InceptionV3 were tested to find the optimum performing model based on transfer learning. VGG19 and InceptionV3 obtained the maximum accuracy of 97% from them. This technology can assist farmers to quickly and correctly identify crop diseases, make timely corrective measures, therefore enhancing the quality and yield of the crops, especially referring to remote rural areas where expert consultation is not easily accessible. Project Report Wed, 14 May 2025 00:00:00 GMT http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16871 2025-05-14T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16870 Attendance Management System Using Face Recognition Model Hassan, Mehedi In academical institutions, teachers are dependent on laborious, prone to mistakes, and easily misused methods, like fingerprint scanners or roll calls, to track attendance. This project offers a more suitable solution: a WEB-based facial recognition school management system. This technology takes students face data by a web cam or other camera connected to the system, checks them to match with the registered image, and automatically marks their attendance to provide a seamless and easy attendance system. This platform is so user-friendly as React and Django is used in frontend and backend. The features for the teachers are to select their assigned courses, to take attendance and of course to log in safely using JWT authentication. Each attendance record is linked with individual courses, so, the chance of duplication and proxy attendance is reduced. The system also provides the facility for downloadable attendance excel file and also have chances to make improvement like using as a mobile application and attendance-based research and monitoring Project Report Wed, 14 May 2025 00:00:00 GMT http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16870 2025-05-14T00:00:00Z