Information and Computer Science
Permanent URI for this collection
Browse
Recent Submissions
- ItemPredicting Type 2 Diabetes Risk and Identifying its Risk Factors through a Machine Learning Model(2024-02-07) Ghaith MaqboulAbstract As one of the most prevalent chronic conditions worldwide, diabetes, particularly type 2 diabetes, poses a significant health challenge affecting millions of individuals and placing a considerable global economic burden. Our goal was to develop predictive models aimed at identifying universal risk factors for type 2 diabetes. The intention is to advance early diagnosis and intervention strategies and also reduce medical costs. The dataset started with 441,456 participants and 330 features. After preprocessing and cleaning, it was narrowed down to 42,340 participants and 18 features, incorporating 10,348 type 2 diabetes cases from the 2015 Behavioral Risk Factor Surveillance System (BRFSS), a survey conducted by the U.S. Centers for Disease Control and Prevention (CDC). This binary classification project strategically selected features to inform a comprehensive analysis for public health strategies. Employing multiple machine learning models, such as AdaBoost, Neural Network, Logistic Regression, Decision Tree, K Nearest Neighbors, Naive Bayes, and Random Forest, we delved into feature importance, with the Random Forest classifier scrutinizing risk factors associated with type 2 diabetes. Our study evaluates various predictive models for type 2 diabetes, all demonstrating notable performance with an AUC range of (74.7%-79.2%). AdaBoost excels with the highest test accuracy (78.2%), with sensitivity (33.5%), and specificity (92.7%). Neural Network and Logistic Regression also perform well. K Nearest Neighbors prioritizes specificity (92.8%), while Naive Bayes showcases notable sensitivity (57.8%), Random Forest had the highest sensitivity (72.9%), this classifier has been used to evaluate the importance of features associated with type 2 diabetes, identifying the top five significant contributors: Age (14.4%), Income (12.1%), MentalHealth (8.3%), Education (8.2%), and PhysicalHealth (7.7%). Among 7 models, including Neural Network, AdaBoost, and Logistic Regression, a convergence is seen with (77.4%-78%) accuracy, sensitivity (32%-34.6%), and (91.2%-92.7) specificity, yielding a closely aligned AUC of (78.7%-79.2%). Notably, Random Forest excels in sensitivity at 72.9%, despite a 71.7% accuracy, it is crucial for feature importance, and it is preferred for type 2 diabetes initial screening due to its balanced overall results.
- ItemTourpulse Explore, Plan, and Administer Tours Website(2024-02-05) Ghazal Masri; Sameh Essa; Motasem AyyashAbstract "Tourpulse: Explore, Plan, and Administer Tours" is a Website that acts as an intermediary between travel agencies and travelers, it is designed to give the Agency the ability to offer their Tour packages and to provide the user with a Gallery of all Tours that have been offered, and it allow the user to review his experience which delivers feedback that helps the agency to improve it services, and give the other user a good ideas to know what to choose. Tourpulse is an intelligent website, we added a recommendation system that provides the user with the most suitable tour picks for him according to his interaction with the website.
- ItemByteMentor(2024-02-05) Abdallah Yahya; Mohamad AbdelhaqAbstract Byte Mentor is a user-friendly website that designed to bridge the gap between Information Technology students and internships. Developed using the MERN stack (MongoDB, Express.js, React, and Node.js) and Python to make the site work smoothly and efficiently. This setup allows ByteMentor to handle lots of users, from students to companies. we built a python/flask custom application to handle the training opportunities, that suggests the best internships for each student based on what they like and need. This system makes finding the right internship easier and faster. ByteMentor focuses on keeping user data safe and updating its features to keep up with the changing tech world. It's a great tool for anyone looking to grow their career in technology.
- ItemSDN-Addressless IPv6 model for securing web servers.(2024-02-05) Saba’a Imad Hussein; Hala Thafer MalhasThe Internet is affecting and driving the world we live in. All the services used nowadays are becoming more Internet-dependant. Which makes the security of Internet-driven services a crucial part. Many studies focused on securing publicly available servers either by improving its availability and hard- ening its security. Addressless servers[1] is an example for such studies. This is done by generating a new address for the server’s for each connection, which hides the acctual server’s identifier and makes it difficult to attack. However, addressless solutions require repeated connections by the client which introduces an increased overhead. This study proposes ”SDN-addressless model for IPv6” to overcome those limitations. This is done by employing Software-Defined Networking (SDN) and HTTP redirection to alleviate network overhead. The proposed method focuses on establishing a streamlined, addressless model utilizing SDN principles for dynamic routing decisions and incorporating HTTP redirection to optimize communication between clients and servers. In this model, the need for predefined static IP for each server is eliminated, and addresses are dynamically allocated based on SDN-controlled decisions. SDN provides centralized control over network configurations, making it possible for an intelligent load- based routing choices that enhance resource utilization, while achieving its main target of providing secure server operation and minimizing latency.
- ItemPAL EVENT(2024-02-05) motasem kharouf; subhi Eid; Abdallah abu asbahThe software specified in this document aims to streamline the party organization process for Pal Event. Its purpose is to provide a robust platform for efficiently managing and coordinating LED screens, lighting setups, dance floors, and corridors. The software facilitates automation of tasks related to party planning and execution, ensuring a seamless and memorable experience for both clients and attendees.