Computer Engineering / Software
Permanent URI for this collection
Browse
Recent Submissions
- ItemAI-BASED CRACK DETECTION AND EVALUATION IN HISTORICAL BUILDINGS(An-Najah National University, 2026-01-25) Abu Shqair, LeenArtificial intelligence and computer vision techniques have emerged as powerful tools for automating crack detection in historical buildings. In the context of ensuring the structural integrity of historical masonry buildings, these techniques offer a robust solution. This task is important for safety and maintenance, where proactive detection of cracks can prevent damage and risks. However, detecting cracks within masonry structures remains a challenge. This thesis explores effective automated crack detection methods where three different computer vision approaches are studied. The first approach is focused on deploying a statistical-based model that depends on mathematical fixed formulations and local textural features to separate cracks from background. This approach is evolved into an enhanced ML-based model, where statistical and textural features are extracted to predict optimal detection thresholds. Finally, the third approach deployed deep learning models using transfer learning, leveraging pre-trained architectures to perform feature extraction. To support the data-intensive requirements of the deep learning model, the research involved extensive data collection conducted in the Old City of Nablus. Efforts were devoted to gathering data from multiple locations across the city to ensure diversity in structural conditions and crack patterns. In addition, pre-processing steps were implemented to standardize the dataset prior analysis. As a result, a dataset of 2794 images of masonry structures was constructed. All methods were evaluated on a consistent test set to ensure unbiased comparisons. The evaluation methodology was designed in collaboration with civil engineering experts to assess performance across two main dimensions: F1-Score, and detection rate. The F1-Score reflects the reliability and detection rate reflects safety assurance. The results demonstrated a clear hierarchy in performance. The statistical-based crack detection model achieved a baseline F1-Score of 0.4775. The ML-based model improved upon this with an F1-Score of 0.5151, confirming the advantage of data-driven parameter optimization. In the deep learning domain, the single class YOLOv8 model showed good reliability, achieving the highest F1-Score of 0.6116, effectively balancing precision with sensitivity. However, when evaluated on the detection rate, the single class Mask R-CNN proved superior performance, identifying 89.23% of all potential cracks.
- ItemStartUp Hub(2025) Gharam Hussein; Mais DwekatChapter 1 Abstract In today’s fast-paced world, startup owners face significant challenges in de- veloping their projects and achieving sustainable success. To address this need, we have developed a comprehensive platform aimed at helping project owners develop their ideas, providing the necessary resources for success, and introducing them to key success factors. In addition, the platform offers a space for showcasing their startup projects, enabling them to market their projects, access grants, enroll in specialized training courses, and attract investments. The platform also includes a section dedicated to ideas, where users can submit their personal ideas to gather feedback from others and discover the most popular and trending ideas in the market. Investors also play a vital role, as they can search for successful projects to invest in, evaluate ideas and projects, and engage with project owners. This platform aims to create an integrated support ecosystem, bringing together startup owners, investors, and individuals interested in starting their own businesses, contributing to the accelerated growth and mutual success of projects
- ItemHealthcare Management & Shopping System (HMSS)(2026) Mohammad Badawi; Ammar Mohammad AmmaThis project presents HMSS (Healthcare Management & Shopping System), a comprehensive and integrated digital platform developed for beauty centers, healthcare clinics, and educational academies. The system is built as a cross-platform solution with a React-based web frontend, a React Native (Expo) mobile application for iOS and Android, and a Django REST Framework backend with a MySQL database. HMSS adopts a role-based access control system supporting six user types: Admin, Secretary, Customer, Student, Worker (Specialist), and Teacher, each with tailored dashboards and permissions. The platform consolidates clinic operations, e-commerce, appointment booking, course management, payroll and HR, and a loyalty rewards system into a single unified ecosystem. Customers interact with a modern, responsive interface to browse products, book appointments through a multi-step wizard, enroll in courses, and manage orders. The e-commerce module supports product variants, attributes, categories, wishlist, cart, checkout with cash-on-delivery, and return/refund requests. The booking system offers real-time scheduling with worker availability tracking and supports both regular services and multi-session therapy treatments. Administrators and secretaries manage offices, sections, products, appointments, courses, complaints, and finances through dedicated dashboards. The system includes a full accounting module with income/outcome tracking, a notification system (in-app and SMS), and an AI-powered chat assistant that answers user queries about products, services, and courses. The web version provides optimized interfaces for desktop screens with data tables, advanced filtering, and comprehensive management tools. The mobile application mirrors the customer-facing features with a native experience including push notifications, theme customization (Light, Dark, and Luxury), multi-currency support, and bilingual content (Arabic RTL and English LTR). With its rich feature set — including intelligent appointment booking, e-commerce with variants, educational course management, loyalty points, AI-driven assistance, and secure role-based
- ItemDevForce(2025) Rasheed Hendawi; Mohammad AbuRehanThe goal of this graduation project is to design and implement a web-based platform for competitive programming, inspired by the widely-used Codeforces website. This platform will offer users the ability to participate in algorithmic problem-solving contests, submit code in multiple programming languages, receive instant feedback via a judging system, and engage with a community of developers through rankings, discussions, and virtual contests. The core functionality will include user registration and authentication, contest creation and management, problem submissions with automated judging, leaderboards, and user profiles. A responsive, modern user interface will be developed to ensure a seamless experience across both web and mobile devices. To achieve this, the project will utilize React for building a dynamic and interactive frontend, while ASP.NET Core will serve as the backend framework to handle API endpoints, authentication, and business logic. In order to extend the platform's reach to mobile users, a dedicated mobile application will be developed using React Native, ensuring a consistent user experience across Android and iOS. The system’s architecture will follow a micro services pattern where suitable, and all services will be containerized using Docker to ensure portability, scalability, and ease of deployment. Additional technologies such as PostgreSQL (or another relational database), Redis (for caching and queue management), and Nginx (as a reverse proxy and load balancer) may also be integrated as part of the infrastructure. This project aims not only to replicate essential features of platforms like Codeforces, but also to introduce enhancements in usability, user engagement, and educational tools for learners. By the end of the development cycle, CodeChallenge will represent a fully functional, scalable, and extensible system for online programming competitions and skill-building.
- ItemENHANCING RESOURCE UTILIZATION IN EDGE COMPUTING USING DEEP Q-NETWORK(جامعة النجاح الوطنية, 2026-01-18) Yazan JarrarThis thesis focuses on designing and evaluating machine learning techniques to enhance the scheduling process in an edge computing environment, especially for IoT applications, with the goal of maximizing the number of tasks executed within a specified window limit. Maximizing task completion within deadlines increases throughput and service quality, while missed deadlines can degrade system performance and render results unusable. This study investigates the two proposed algorithms, Simulated Annealing (SA) and Deep Q Network (DQN), to determine if they outperform the existing solutions for batch task scheduling in an edge computing environment. To validate the results, we used real world Augmented Reality (AR) and Internet of Vehicles data generated by the EdgeCloudSim simulator. The results clearly show that our proposed algorithms outperform others solutions, especially where the resources are strictly constrained. The results show that our simulated annealing-based algorithm achieved up to a 71% reduction in task failure rate compared with the baseline algorithm when tested in static environments using real IoT and AR data. They also show that our Deep Q-Network based scheduler consistently achieved the lowest failure rates across dynamic scenarios, especially under higher constraints. Moreover, the Deep Q-Network model evaluated in a dynamic environment required substantially less overhead time, under one-third of the simulated annealing algorithm’s runtime, while both algorithms outperformed other baseline algorithms by up to 10% in task failure rate. These findings support the thesis objective of maximizing the edge resource utilization while ensuring task batches complete within a specified window limit and highlight the efficiency of the Deep Q-Network based scheduling algorithm.