http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16702 2026-04-26T04:36:46Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16823 Diu E-Health System Rahman, Semonty The healthcare industry has undergoing significant digital transformations in recent years, with technology playing a very important role it transform also health industry, like improving patient care, improving administrative processes, and improving the overall healthcare experience. The DIU eHealth System has been developed as a comprehensive digital health platform is designed to address the healthcare needs of patients, doctors, and administrator. In this system have integrates various kinds of healthcare service such as including appointment scheduling, healthcare record management, prescription handling, blood donation and fund-raising with medical intents, into a unified platform or system. This integration means to improve accessibility, efficiency and quality of healthcare delivery and to reduce the administrative burden and improve communication between healthcare providers and patients. 1.1 Problem Statement Thesis 2025-09-11T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16822 Project and Thesis Management System – ProjectITM Zaman, Nusrat Project and Thesis Management System, ProjectITM is a web-based application which is designed and developed to handle final year projects and theses within department environments. This system addresses the challenges of managing multiple student projects by providing a centralized platform. This system will help supervisor to maintain student lists and project list. Supervisor and student can create, view, update, and/or delete any project or any details throughout the system. Thesis 2025-11-10T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16821 Anti-Diabetic Peptide Identification Using Deep Learning Approach Sarkar, Farzana Fartheha Mishu Background Anti-diabetic peptides (ADPs) are a potentially appealing therapeutic modality even with the slow progression of experimental discovery. We compiled a balanced dataset of 4,061 peptides (1,261 active; 2,800 inactive) and tested four families of sequence-derived features AAC, DPC, CKSAAP, and PseAAC. Objective Design an accurate, lightweight and interpretable ADP predictor (ADPpred) and identify the best generalizing feature-model combination. Highlight MCC and F1 as key measures, and report Accuracy, Sensitivity, Specificity and kappa. A five-fold stratified cross- validation (CV) and independent 20 percent hold-out test were used. Results Several feature sets were tested, with ResidualMLP showing the best performance CV across all (mean MCC = 0.919, F1 = 0.960, Accuracy = 0.959). In terms of features, CKSAAP remained the most dominant: CKSAAP + ResidualMLP had MCC = 0.986, F1 = 0.996, Accuracy = 0.993, Sensitivity = 0.992, Specificity = 0.998 in CV. The same configuration achieved Accuracy = 0.970, F1 = 0.961, MCC = 0.941, Sensitivity = 0.981, Specificity = 0.961; ROC AUCs on CKSAAP were ~0.987 on all model families, which shows good discrimination. ADPpred thus outperforms prior ADP-specific RF baselines and is similar in performance to PLM-based methods, but computationally efficient. Conclusion ADP pred, with focus on CKSAAP features and ResidualMLP classifier, yields high balanced performance and is generalizable to unseen peptides. Its ease of use, fastness and interpretability of the features make it a convenient tool to screen and design against- diabetic peptides. Thesis 2025-11-10T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/16809 Factors Influencing the Continued Usage Intention of AI-Powered Tools Among University Students Rahman, Maisha This study investigates the factors influencing the continued usage intention of AI-powered tools among university students in Bangladesh, utilizing an extended Theory of Planned Behavior (TPB) framework. The research integrates constructs such as trust inAI, perceived usefulness, interpersonal influence, social media influence, self-efficacy, and technological infrastructure to provide a comprehensive understanding of students’ adoption behaviors. A quantitative, cross-sectional survey was conducted with 250university students, employing stratified random sampling to ensure diverse representation. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) to test the hypothesized relationships. Thesis 2025-10-11T00:00:00Z