Recently, particularly following the COVID-19 pandemic and the beginning of people’s re- liance on Internet applications primarily to facilitate their lives, from requesting household needs online to medical consultations. It has been observed that fraud cases have increased due to people’s ignorance of these technologies, including (SMS) messaging applications, as banks and government agencies regard them as their official platforms for sending important messages to users. This platform also drew the attention of marketers because of its simplicity of use and low cost, which allowed them to send many messages, which became a nuisance and a waste of time. This study aims to create an application that can restore confidence and tranquility to (SMS) messages by comparing between types of supervised machine learning in an attempt to reach the highest possible rate of accuracy. The logistic regression model showed the highest accuracy in categorizing (SMS) messages with an accuracy rate of 88.33%. Developed a web- page where consumers can check out the message.
13/06/2023
There are many types of date fruit, each with similar physical properties and slight differ- ences in color,shape and fleshiness among other characteristics.It can be challenging and time consuming for an individual to distinguish between the different types of dates due to the myriad of attributes to consider.The objective of this study was to employ the Deep Learning technology the You Only Look Once (YOLO) algorithm, for image detection,classification and provision of nutritional information about date fruits.Subsequently,the YOLO object detection model was trained using the YOLOv5,YOLOv7 and YOLOv8 algorithms on Google Colaboratory’s cloud service,utilizing the Kaggle dataset, which comprises 1735 images of 9 different types of date fruit. An accuracy analysis of these three algorithms was conducted based on Recall,Precision and F1-score metrics the results were subsequently compared.The experimental results demon- strate that YOLOv8 achieves IoU between [0-1],an mAP@0.5 and mAP@[0.5:0.95] of 0.99%,a Recall of 0.997% and a Precision of 0.991%.
13/06/2023
Lung cancer is one of the dangerous and life taking disease in the world. However, early diagnosis and treatment can save life. But it is difficult for doctors to identify the cancer at initial stages from CT scan images. Therefore, computer aided diagnosis can be helpful for doctors to identify the cancerous cells accurately. Many computer aided techniques using image processing approaches have shown impressive results in various fields and deep learning has been researched and implemented. It is possible to construct a sustainable prototype model for the treatment of lung cancer using the current developments in computational intelligence. This research deals with two areas related to lung cancer, the first is to review a group of models that help in detecting and diagnosing lung cancer, mentioning its most prominent strengths and gaps within it, and comparing and evaluating the accuracy of those models, or false positive. Deep learning was used to suggest an approach that helps in diagnosing lung cancer. The research touched on introducing deep learning fields and understanding its most prominent characteristics and benefits, specifically in the health sector and healthcare field. This work contributes to the development of existing frameworks for early lung cancer detection, which will enhance the ability to provide solutions more efficiently. Our research provides critical analysis of previous and current lung cancer detection and prognosis approaches, and we aim to make proposals that achieved an impressive 98.38%, while the validation accuracy reached 98.26%. In the future, this will help improve the accuracy of current models for accurate and early diagnosis of diseases, increased treatment options, and reduced symptoms.
11/06/2023
Restaurant owners and investors requires a wise judgment to deal with the increasingly higher expectations and market competitiveness. This study proposes a tool to help the decision- making process of restaurant managers by developing an interactive dashboard based on four square reviews. The collected data was processed using data mining tools to visualize a dash- board that provides value for restaurants owners and investors by analyzing geographical, pric- ing and rating data. Such dashboard was evaluated by restaurant management experts, which provided positive feedback, highlighting in particular the time saved in the decision-making process.
11/06/2023
The recent monkeypox outbreak has become a public health concern due to its rapid spread in more than 40 countries outside Africa. Early diagnosis of monkeypox is challenging due to its similarity to chickenpox and measles. The use of computer-assisted detection of monkeypox lesions could prove beneficial for the surveillance and rapid identification of suspected cases. If sufficient training examples are available, deep learning methods have been found to be effec- tive in the automated detection of skin lesions. To improve the diagnosis of monkeypox using mobile applications, we utilized MobileNet and ShuffleNet which are types of Fully Connected Convolutional Neural Networks.
11/06/2023
Weeds are among the major problems in agriculture for crop production; they appear every- where randomly in the fields and compete with sunlight, water, fertiliser, and space. Detecting weeds have become a major concern for producers. Controlling weeds early is especially im- portant in order to prevent yield losses. Nowadays, by using intelligent technology, smart agriculture has become imperative due to its ability to accurately determine weeds distribution in the field, perform weeds control tasks in specific areas, and thus enhance the efficacy of her- bicides as well as the economic benefits of agricultural products. In this study, we conducted a comparative analysis of four different models of YOLO (YOLOv5s, YOLOv6, YOLOv7, and YOLOv8s) using standardized hyperparameters on a corn dataset consist of 1268 images. We evaluated the models based on precision, recall, and mean average precision (mAP). In general, all the models achieved a good accuracy for detecting weeds. The detection accuracy on corn dataset in terms of mAP@0.5 ranged from 0.963 obtained by Yolov6 to 0.992 by Yolov7. The results showed that YOLOv7 achieved the highest detection accuracy. Then we examined the performance of YOLOv7 on different image sizes, including 415, 640, and 800. The evaluation indicated that image resolution of 640-pixels was the optimal image size for achieving the best results. Furthermore, we expanded our analysis by presenting a new dataset consisting of 950 images of three classes (okra, eggplant and weeds) collected from farms in Saudi Arabia. When evaluating the performance of the model on this dataset, it achieved an mAP@0.5 of 0.88, in- dicating its effectiveness in accurately detecting and classifying objects in the context of weeds detection in okra and eggplant fields.
11/06/2023
Nowadays, most people use ride-hailing apps to go from one place to another. Users have adopted famous apps like Uber and Careem for their daily needs instead of driving their cars, Whether they don’t have access to a private vehicle due to excessively high costs, whether it feels uncomfortable to drive that day, or if they suffer from a fear of driving. Ride-hailing apps continue to evolve to new variations every day with new features. However, these new devel- opments come at a cost, this is why we need a way to lower the cost of fuel, ease traffic, and improve environmental sustainability. Carpooling has become an option to solve these issues. This is why we have developed a group ride-hailing app that is focused on the region of Riyadh Saudi Arabia. The app will serve two types of users, the first is the drivers who own cars and are willing to use them to pick up other people. The other type of user is a group of passengers who need to go from one place (or more than one place) to another. Since the app is group focused it has many distinctive features such as sharing payments where the higher the number of passengers, the lower the fare, unlike usual ride-hailing apps where the passenger would have to pay the full amount. The app also provides some services, such as the option for passengers to choose the gender of their driver, to make the trip more comfortable. It also optimizes safety for our customers by providing an SOS option for emergencies. And it also has accessibility options for passengers with special needs. The application also has a better procedure for the option of cancellation, as it guarantees the rights of both the passenger and the driver, as some laws and instructions will be applied in the cancellation. For example, a passenger can cancel the trip if the driver does not travel half the distance, and the driver has the right to cancel the trip if it does not exceed 5 minutes from the request.
11/06/2023
If a seller wishes to sell a product online, they typically have two pricing options. They can sell the product at a fixed price, similar to how products are sold on sites like Amazon, or they can put the product up for auction and let customer demand drive the final sales price, similar to how products are sold on sites like eBay. Both options have advantages and disadvantages. An alternative option for deciding on a final sales price for the product is to enable negotiation on the product. A increasing number of negotiations are taking place via electronic media, al- lowing for more flexibility and adding a dynamic nature to the price. Customers can negotiate the price with sellers, allowing the final sales price to change over time. Using software agents to automate customer and seller negotiations. The system is analyzed using stakeholders’ interviews and existing systems observations. More- over, the system is subsequently designed using several designing tools, including Data Flow Diagram (DFD), Entity Relationship Diagram (ERD), and Relational Schema. The system will be implemented, tested and evaluated in the next semester.
11/06/2023
Traffic congestion is a growing concern in urban areas around the world, resulting in in- creased travel time, decreased productivity, and negative environmental impacts. To address this problem, various strategies, such as Intelligent Transportation Systems (ITS) and Advanced Traveler Information Systems (ATIS), have been proposed and implemented. This project aims to analyze the impact of these strategies on reducing traffic congestion and to evaluate the effec- tiveness of different traffic congestion mitigation approaches. A comprehensive literature review was conducted to provide an overview of previous studies and their findings on this topic and to identify areas for further research. The project provides practical solutions to reduce traffic congestion in urban areas, and reduce traffic congestion for Saudi government sectors using the application of predictive modeling based on schedule, it contributes to the development of more effective and sustainable approaches to address the traffic problem.
11/06/2023
The protection of data requires the implementation of security and privacy measures. A computer system’s first line of defence is user authentication. Authentication mechanisms in- clude a variety of mechanisms, and one of the newest and most sophisticated is biometric authentication. By using their biometrics, such as a face scan, fingerprint, voice recognition, gait recognition, and eye movement, biometric authentication uses the unique characteristics of each individual to verify and authenticate them. This project focuses on eye movement. In addition to being robust against spoofing, continuous authentication, and authentication un- conscious without specific action by the user, eye movement has other advantages as well. To identify individuals, this project developed an authentication model based on eye movement features.
18/05/2023
Student advising is a time consuming and important aspect of academic life. Academic advising has been implemented to bridge the gap between students and the academic routine by automating the advising, complaining, evaluating, and suggesting systems. The goal of this project is to create an automated mechanism for academic advising in the university system. This project provides an overview of the design and implementation of a new web-based model of e-Academic Advising System. The proposed model aims to create a model in which students and advisors can communicate with each other easily. The advisor can see the students regis- tered with him, their absences, and their academic record, and communicate with them in the way he and the students prefer. The department head can receive end of semester reports on the level of students and the mentor’s communication with the student throughout the term. Moreover, students can see their academic record, a map of the college’s classes, and commu- nicate with their academic advisor. This project aims to develop and implement a system that assists academic advisors in their efforts to provide time and high quality, accurate and con- sistent advising services to their students. We talked about the required methodologies used in the development of the academic advising system, demonstrated that academic advising is a process rather than a final product or system, and provided a technical vision for the academic advising system.
15/05/2023
Nowadays, the tendency of universities to take advantage of modern technologies is consid- ered a good practice, facilitating their services and raising the level of accuracy. This project develops an automated system for measuring learning outcomes for academic programs. The system measures the learning outcomes of each course and program based on the students’ performance. The system is analyzed using stakeholders’ interviews and existing systems observations. More- over, the system is subsequently designed using several designing tools, including Data Flow Diagram (DFD), Entity Relationship Diagram (ERD), and Relational Schema. Additionally, the system is a web-based one that is implemented using various technologies, e.g. PHP and MySql. Finally, the system is tested and evaluated with considerations on its units, and the entire system functions integration.
05/05/2023