Computer Engineering / Software
Permanent URI for this collection
Browse
Recent Submissions
- 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.
- ItemAn-Najah National University Faculty of Engineering & Information Technology Computer Engineering Department Presented in partial fulfillment of the requirements for Bachelor degree in Computer Engineering 2025 Graduation Project 1 - Software PalHands(2025) Abeer Kharouf; Rand JohariThis project presents a mobile and web application designed to facilitate the process of offering and requesting services. Service providers can showcase the services they offer, while users can search for the desired service and select a suitable provider based on ratings and reviews from previous clients. The platform integrates an interactive map powered by GPS, enabling users to easily identify and choose the nearest provider. The system also allows users to view the provider’s availability schedule, book an appointment at a suitable time, and await confirmation. Notifications are sent to providers when a booking request is made, allowing them to review the requester’s details as well as feedback and ratings from other providers who previously worked with that user. Once a booking is either accepted or rejected, the user is promptly notified. Cancellations are supported under specific conditions: a request can be withdrawn freely if made at least two days prior to the appointment, whereas cancellations within two days require approval from the other party. After completing a service, both users and providers can submit reports or complaints about each other, ensuring accountability. Additionally, the platform supports suggestions for new services, which are reviewed by the administrator before approval to prevent misuse. For security and reliability, administrators have the authority to suspend or remove any user or provider account, along with all associated bookings, while notifying the relevant parties. Direct communication between providers and users is supported, as well as access to frequently asked questions and AI-powered assistance to guide users through the platform. Furthermore, providers can specify availability for emergency services, such as late-night or weekend requests, which can be booked at least two hours in advance. Overall, this system enhances service accessibility, reliability, and efficiency by connecting users with trusted providers in a secure and user-friendly environment.
- ItemDentify - A Comprehensive Dental Clinic Management System(2026) Ala’a Abdelrahim; Abdullah ShabibModern dental practices face significant operational challenges including inefficient ap- pointment management, fragmented patient records, and limited patient engagement. This project addresses these challenges through the design, development, and implementation of Dentify—a comprehensive, cloud-based dental clinic management system integrating web and mobile applications to streamline dental practice operations and enhance patient care delivery. The system was developed using a three-tier architecture with Node.js and Express for RESTful API implementation, PostgreSQL with Prisma ORM for data management, and Fire- base Firestore for real-time communications. The frontend comprises responsive web appli- cations built with React.js for patients, dentists, clinic administrators, secretaries, radiology centers and system administrators, complemented by cross-platform mobile applications devel- oped using React Native for patients, dentists and secretaries. A key innovation is the integration of Google Gemini 2.5 Flash AI to power an intelligent chatbot providing patient support and appointment booking through natural language interaction. Security measures include HTTPS encryption, bcrypt password hashing, JWT authentication, and role-based access control sup- porting six distinct user types. The implemented system successfully delivers nine core modules: authentication and user management, intelligent appointment scheduling with real-time availability, comprehensive treatment planning with visual dental charting, flexible payment processing, radiology inte- gration, AI-powered chatbot assistance, clinic management, administrative oversight, and real- time notifications. The system demonstrates significant advantages over traditional solutions through modern user interfaces, AI-enhanced patient engagement, integrated clinical and ad- ministrative workflows, real-time data synchronization, and cost-effective deployment using open-source technologies. The project validates that contemporary web technologies, cloud platforms, and artificial intelligence can effectively address complex healthcare management requirements while improving user experience and reducing costs compared to legacy commer- cial solutions
- ItemLiveSpot: A Real-Time Location-Based Social Networking Application(2026) Mohammad Hamdan; Momen AnaniThis project developed LiveSpot, a real-time location-based news tracking and verification platform designed to combat misinformation through location-verified community reporting and news aggregation. The platform addresses the growing problem of fake news and frag- mented information sources by creating a unified application where users can report real-time events, verify ongoing incidents, and access curated news from multiple external sources within their local communities. The application was implemented using Flutter framework for cross-platform compatibil- ity across Android, iOS, and web platforms, integrated with Firebase for real-time messaging and Django REST API for backend services. Key implemented features include GPS-based location verification for posts, community-driven honesty scoring system, intelligent threading that automatically groups related events, crowd-sourced event status verification through "still happening" votes, comprehensive news aggregation with external API integration, interactive mapping using OpenStreetMap, and AI-powered messaging suggestions using Google Gem- ini API. The system employs location-based authentication to ensure post authenticity and implements automatic content threading to enable collaborative event tracking. The development resulted in a fully functional news tracking and verification platform ca- pable of real-time event reporting with location verification, successful integration of multiple external news sources, implementation of community-based credibility systems, and deploy- ment across multiple platforms using a single codebase. The platform successfully demon- strates cross-platform functionality, real-time data synchronization, and effective integration of location services with news tracking features. Testing confirmed reliable performance across different devices and operating systems, with successful implementation of all core verification and aggregation features. Keywords: Misinformation detection, Location-based authentication, Flutter cross-platform development, Real-time event verification, Community-driven journalism GitHub Repository: https://github.com/momenmac/livespot
- ItemFood Guard(2025) Dima Shanti; Masa AnaniThe world today faces a growing problem of food waste, which negatively impacts food security, the environment, and the economy. This project presents a practical digital initiative aimed at reducing household food waste through the development of an intelligent application called Food Guard. The application enables users to track food products and their expiry dates, receive smart notifications when items are about to expire, and analyze consumption behavior over time—helping them make more conscious decisions about food usage and storage. The system is built using modern technologies, including Flutter for mobile application development, Django with a PostgreSQL database for a secure and robust backend, and Firebase for enabling real-time notifications. Additionally, artificial intelligence is integrated to provide smart storage tips and suggest recipes based on available in- gredients. The application also offers a comprehensive system for managing food donations, whether surplus items or ready-made meals. Food Guard is expected to make a tangible impact on raising food awareness and reducing waste, based on the comprehensive technical solutions it provides and the user-friendly experience it offers. The platform also holds promising potential for fu- ture expansion to support communities and connect them through smart cooperation networks.