Communities in DSpace
Select a community to browse its collections.
Now showing 1 - 2 of 2
Recent Submissions
Item
Self-driving Car
(2023) Abdallah Adas; Mohammad Zaied
The major goal of development the self-driving cars has been driven by the desire to improve
road safety, reduce traffic congestion, and provide mobility to those who are unable to drive.
Self-driving cars rely heavily on image processing to perceive and understand the driving environment.
Image processing involves collecting data from cameras and other sensors installed
on the car, and then analyzing that data to extract information about the surroundings. This
information is then used by the car to make driving decisions. Pictures will be taken sequentially
by a Raspberry Pi camera connected with Raspberry Pi 4, and then these images will be
processed by the OpenCV library and machine learning and used Arduino UNO to control the
motor driver(H-bridge).
The car was able to recognize road lines, drive between these lines, and recognize some traffic
signs such as stop signs, green and red traffic lights. Also, the car will be able to detect and
overcome obstacles.
Item
Package4U
(2024) Abdallah Adas; Mohammad Zaied
Package delivery is important because it facilitates trade, provides convenience and simplifies the process of sending and receiving packages. It provides an efficient and convenient way for users to track their shipments and receive real-time updates on the status of their packages. This transparency helps build trust, provides peace of mind for both senders and recipients, creates job opportunities for a wide range of drivers, warehouse workers and employees, and greatly impacts our daily lives, the operation of businesses and economies. It continues to evolve to meet the changing needs of consumers and businesses in an interconnected world.
The package delivery company project includes building a mobile application for customers, drivers, and the manager, and a website for employees and administrators. At the end of this project, the application was able to provide many services, the most important of which are: tracking packages, creating financial reports, auditing financial accounts, and distributing packages on a daily basis to drivers according to the line. The driver's route (his work area), and determining the driver's location on the map so that the company manager can monitor the drivers while driving.
Item
Automated Sample Preparation System
(2023) Jenan Abualrub; Yaqout Salameh
Analytical chemistry occupies a crucial role in the medical field
for being the deterministic
criteria in diagnosis. It primarily relies on performing chemical laboratory tests on patients’
samples , which are widely done manually and vulnerable to errors . In light of these challenges ,
the development of an automated sample preparation system (ASPS) provides a viable
alternative to overcome the flaws of the manual process. The ASPS eliminates the need for
manual intervention from the la boratory technician, as a needle would move automatically
towards the samples and the reagents based on the selected test. The needle would then sense the
substance and precisely dispense the required amount for the test in the reaction cup .
Simultaneously , a syringe would help draw ing in and expelling the substances. Throughout the
test, the needle is cleaned to prevent any contamination. Additionally , the laboratory technician
has the ability to schedule up to 4 tests, which the system would perform seque ntially . The ASPS
was developed using Arduino mega, motors, and a sensing circuit built upon capacitance
manipulation.
Item
Customizable Service Provider Platform
(2024) Shahd Lubbadeh; Yaqout Salameh
The Customizable Service Provider Platform is a versatile solution comprising a mo-
bile application and a website tailored to empower a wide range of service providers,
whether they are established companies or individual freelancers. This project aims
to streamline the service request process for clients and enhance e ciency for ser-
vice providers, addressing complexities across various domains such as homecare,
gardening, electrical services, maintenance, and more. The platform integrates fea-
tures from existing platforms, o ering a uni ed and highly customizable space for
service providers to personalize their o erings. Noteworthy functionalities include
service categorization, pricing, and request management for providers, along with a
straightforward booking process for customers. The application facilitates commu-
nication through a noti cation system and chat functionality. Di erent user types
enjoy varying privileges, with administrators having full control over customization.
The platform's signi cance lies in its ability to cater to the diverse needs of service
providers and clients in a uni ed manner, acknowledging the varied structures of ser-
vice providers, be they companies or freelancers. With a focus on customization and
e ciency, the project responds to market demands for a comprehensive, adaptable
service provider solution that accommodates the nuances of di erent organizational
types. The platform is developed using modern tools and technologies. React was
used for web front-end development, React Native for mobile app development, and
Spring Boot for the robust back-end infrastructure.
Item
Predicting Type 2 Diabetes Risk and Identifying its Risk Factors through a Machine Learning Model
(2024-02-07) Ghaith Maqboul
Abstract
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.