http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/36 2026-06-28T05:20:15Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17293 An Improved 4-Dimension Pixel Selection Method to Enhance Capacity in Image Steganography Haider, Tayeba Binte The use of social media and the internet has been rising and a lot of data is being exchanged as well. Vulnerability increases with the amount of data shared. It is essential and required that shared data be secure and private. Techniques like watermarking and cryptography are employed to ensure security. However, the ciphertext's accessibility instantly raises suspicions and attracts the attention of malicious people. This brings us to yet another technique steganography. The primary goal of steganography is to conceal the existence of secret communication rather than the content of it. Image steganography, which helps protect sensitive information, is similar to concealing secret messages in common photos. As a way to improve data concealment within images, an improved method for image steganography is introduced in this study. There are limits to how much data can be hidden using conventional methods like LSB substitution without sacrificing image quality. A 4-directional pixel selection method is proposed as a solution, methodically embedding data outward from the image center. By incorporating encryption more specifically, the RSA cryptosystem the technique improves data security. As experimental evaluations with Lena, Lake, and pepper images show, the suggested technique is developed by discretely embedding important data while preserving image quality. With its foundation for safely hiding significant amounts of data inside images, this technique offers a potential development in image steganography. Analysis has been used to measure the quality, and the value of the quality assessment matrices has produced improved results and retains a maximum of 1256 bytes of hidden data. Thesis Report 2025-02-11T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17274 Building Trust In Ai-Driven Skin Disease Diagnosis Through Explainable Ai Nahid, Beniamine Al This research focuses on developing an AI-based system for skin disease diagnosis that achieves high accuracy while ensuring interpretability and transparency. The proposed system leverages ResNet101 as the backbone model and achieved an impressive 98% accuracy across six skin disease categories: Acne, Carcinoma, Eczema, Keratosis, Milia, and Rosacea. To address the critical challenges of trust and usability in clinical settings, Explainable AI (XAI) techniques, such as LIME, were integrated. These techniques provide detailed visualizations of class-specific probabilities and regional contributions, enabling both patients and dermatologists to better understand and trust the model’s predictions. Extensive experiments were conducted, comparing the performance of ResNet101 against other pre-trained models, including VGG16, ResNet50, and EfficientNetB7. The results highlight the superior feature extraction capabilities and generalization performance of ResNet101, which outperformed other models in accuracy, precision, recall, and F1-score. This research underscores the importance of combining technical accuracy with explainability to enhance trust in AI systems, thereby supporting patient-centered care. By addressing the gap between advanced AI technology and practical healthcare applications, this study contributes to the broad-scale adoption of reliable and transparent AI systems in dermatology and other medical fields. Thesis Report 2025-01-15T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17273 A Colab-Integrated Hybrid Model For Effective Ransomware Detection Via Voting Classifier Techniques Eyashin, Md. Ransomware is a harmful malware that is designed to encrypt a victim's data or lock the victim's system, then demand a ransom for restoration or decrypting the data or unlocking the system, and it often causes significant financial and operational damage. Current ransomware detection methods are struggling to detect ransomware properly because most of the ransomware detection approaches follow dynamic analysis techniques which involve a complicated process, and also use only signature-based features, not use network or behavioral based features. This study proposed a ransomware detection hybrid model that is based on static analysis and uses signature- based features, network, or behavioral features. This study used three ML models for implementing hybrid models, models are Decision Tree, Random Forest, and K-Nearest Neighbors. This study proposed two hybrid models, where the hybrid model achieved highest detection accuracy 97.48% with a low false positive and false negative rate. Thesis Report 2025-01-11T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/17272 Automating Clinical Note Summarization Using LLM Arafat, Md. Yeasin The increasing volume of electronic health records (EHR) and the growing complexity of clinical documentation have highlighted the need for efficient and reliable summarization tools. This thesis explores the application of large language models (LLMs) in automating clinical note summarization, with the goal of reducing the cognitive and administrative burden on healthcare professionals while maintaining clinical accuracy and relevance. Leveraging state-of-the-art LLM architectures such as T5 and FLAN-T5, this research focuses on extracting key information from clinical notes, including patient diagnoses, treatment plans, and medical histories, and generating concise, structured summaries suitable for clinical workflows. The study evaluates the performance of fine-tuned LLMs on datasets such as MIMIC-III, MeQSum, and ProbSum using quantitative metrics like ROUGE and BERTScore, achieving a ROUGE F1 score of 0.95 and demonstrating high efficiency with a runtime of 2.35 seconds per note. Qualitative analysis confirms the generated summaries' clinical relevance, with outputs aligned to standard sections like diagnoses, imaging results, and treatments. Despite these strengths, challenges such as occasional hallucinated information, omitted secondary details, and inconsistent formatting are identified. Results from physician feedback underscore the practicality of LLMs in improving healthcare documentation, with models like LLaMA-Clinic achieving over 90% acceptance in a blinded review. Additionally, cost analysis reveals a 3.75-fold reduction in inference costs compared to proprietary alternatives, emphasizing the feasibility of open-source solutions. This research highlights the potential of LLMs to enhance clinical workflows, reduce diagnostic errors, and improve patient care. Future directions include expanding datasets for better generalizability, addressing hallucination issues, and ensuring seamless integration into healthcare systems through ethical and clinician-centered approaches. The findings reinforce the role of AI in advancing healthcare, promoting accessibility, and addressing global challenges in medical documentation and decision-making. Thesis Report 2025-01-15T00:00:00Z