http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/13847 2026-04-05T17:28:57Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/15934 Image Based Banana Leaf Disease Detection with Machine Learning Technique Khan, Shahrin; Modak, Anup Kumar; Elahe, Md. Ashik-E-; Amin, Abdullah Al-; Disha, Iffat Mehrin; Sharmin, Dr. Sadia Today, international trade has grown significantly in many countries. Many fruit products are imported from other countries, such as bananas and apples. Devastating economic losses and production losses are incurred all over the world due to fruit diseases. Little study has been done throughout the years for fruit disease detection to assist remote farmers technically. The bulk of these farmers require proper cultivation support, but little research has been done for this system. The use of one's eyes to visually inspect fruits and vegetables allows trained professionals to identify imperfect produce; however, this paper presents a lightweight machine-learning framework that integrates K-means clustering for image segmentation and a Random Forest classifier for disease recognition. A locally collected dataset of 422 banana leaf images from farms in Bangladesh was used, covering four classes: Cordana, Sigatoka, Pestalotiopsis, and Healthy. Images were preprocessed using RGB–to–Lab color conversion and resized for consistency before feature extraction based on color and texture descriptors. Among several tested classifiers, the Random Forest achieved the best performance with 96.25 % accuracy, 93.56 % precision, and 97.85 % specificity, outperforming the Decision Tree (95.28 %) and Naïve Bayes (89.27 %). Owing to its low computational cost and use of regionally collected images, this framework is suitable for real-time mobile or IoT- based agricultural systems, supporting smart and sustainable farming in resource-limited environments. Article 2024-11-27T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/15923 Low-Cost, High-Consistency Process Flow For Audio-Visual E-Learning Content Development For Foundational Computer Education On Youtube Ghosh, Apurba; Rahman, Mohammad Zahidur; Uddin, Md. Salah; Ghosh, Anindya; Hasan, Kazi Jahid Educators increasingly need a repeatable, budget-conscious workflow to produce YouTube-ready, audio-visual lessons without sacrificing technical quality or instructional clarity. This paper formalizes a low-cost, high-consistency process flow tailored to foundational computer education and the realities of a solo creator. This study details an end-to-end pipeline optimized for a screen-recording-first setup with affordable peripherals. The contribution is practical and reproducible: a role-agnostic flow with explicit inputs/outputs and quality gates; hardware/software stack mappings; export and archival presets; a YouTube-specific metadata checklist; and a risk register addressing common constraints. To support adoption at different budget levels, this study provides cost tiers with trade-offs and upgrade paths. A brief case snapshot demonstrates feasibility in a real production context, and all operational checklists and presets are presented within the main text. Article 2025-11-08T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/15922 An In-Depth Review Of Authentication Mechanisms In Microservice Architectures Momin, Md. Abdul; Hussain, M.M. Musharaf; slam, Md. Ezharul I Authentication in microservice architectures (MSA) is hard because services are spread out. Managing user identities is tricky. Keeping communication between services secure is important. Controlling access to APIs is also complex. It is more challenging than in traditional monolithic systems. The main goal of this study is to review and compare existing authentication mechanisms for microservices to identify effective and scalable solutions. This review uses a structured narrative method, analyzing recent research and technologies such as JSON Web Tokens (JWT), session-based authentication, Single Sign-On (SSO), passwordless, and biometric approaches. The findings show that token-based methods like JWT improve scalability and user experience but are vulnerable to token theft. Session-based systems offer stronger central control but struggle to scale in large networks. Passwordless and SSO solutions enhance usability but still require strong security controls. This review compares different authentication methods clearly. It describes the pros and cons of each system. It also explains how new trends like zero-trust, adaptive, and decentralized authentication may change the future. These trends help make microservice systems more secure and scalable Article 2025-11-11T00:00:00Z http://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/13849 Assessing protective interventions on cholera dynamics using a Caputo-Fabrizio fractional model. Adedeji, Joseph Adeleke; Olayiwola, Morufu Oyedunsi This study introduces a mathematical framework that incorporates fractional-order derivatives to investigate how effective protective interventions are in high-risk cholera populations. The model establishes disease-free and endemic thresholds, with stability analyzed using the Routh-Hurwitz criteria. A key insight is that determining the basic reproduction number provides deeper understanding of cholera transmission dynamics. Through normalized sensitivity analysis, the ingestion rate of Vibrio cholerae emerges as the most influential factor in transmission. Meanwhile, vaccination coverage and awareness of protective measures are recognized as crucial elements for cholera control and eradication. The model uses the Caputo-Fabrizio fractional- order approach and is proven to be well-posed through the fixed-point theorem. Using the Laplace Adomian Decomposition Method (LADM), the results demonstrate that high vaccination rates and widespread adoption of protective measures among susceptible individuals in high-risk zones significantly reduce susceptibility, increase protected populations, and strengthen overall public health resilience against cholera. 2025-07-18T00:00:00Z