RAYANA K. ANTAR
Software Developer. Computer Science Researcher. IT/AI Expert.
About me
I'm an IT Specialist & front-end developer with 15 years of professional experience.
I'm interested in all kinds of visual communication, but my major focus & interests lie at the intersection of mathematics, computer science, optimization, machine learning, deep structured learning & federated learning. I also have skills in other fields like Cloud computing or IoT.
My research interests focus on topics in Deep Learning, Computer Vision, Machine Learning, and Image processing and detection.
They include:
Download the CV
I'm interested in all kinds of visual communication, but my major focus & interests lie at the intersection of mathematics, computer science, optimization, machine learning, deep structured learning & federated learning. I also have skills in other fields like Cloud computing or IoT.
My research interests focus on topics in Deep Learning, Computer Vision, Machine Learning, and Image processing and detection.
They include:
- In Neural Networks, comparing and developing first, and second-order online learning methods in terms of derivatives.
- An optimizer technique to minimize the random noise.
- Regularization concept to further improve the generalization of the model.
- Big data analysis utilizing descriptive-analytical approaches and statistical analysis.
- Recognition system for images and edge detection techniques.
- Horizontal projection in image segmentation, masking technique to locate and separate the region of interest.
Download the CV
Education
Master of Computer Science (Artificial Intelligence)
UMM Al-Qura University 2 Years Course | GPA 3.97 out of 4 GRADUATING IN SEPTEMBER 2022
Bachelor's of Science in (Information Technology & computing)
Arab Open University 4 Years Course | GPA 3.68 out of 4 | with First Class Honours GRADUATING IN FEBRUARY 2018
Secondary School Certificate (Scientific Field)
Government School 3 Years Course | GPA 96.71%. GRADUATING IN NOVEMBER 2006
WORK
IT Specialist
Advanced Smart Integration Co,Ltd Jeddah Feb 2018 – May 2025
- Designed and implemented an AI-powered predictive maintenance system that reduced equipment downtime by 35% and maintenance costs by 20%.
- Developed and deployed machine learning models for customer behaviour analysis, resulting in a 28% increase in targeted marketing effectiveness.
- Led the implementation of IT security systems and policies that decreased security incidents by 40% over two years.
- Managed a team of 8 IT professionals, improving team productivity by 25% through implementation of agile methodologies.
- Optimised cloud-based machine learning infrastructure, reducing processing time by 30% and cloud computing costs by 15%.
- Conducted regular security audits and risk assessments, ensuring 100% compliance with data security policies and regulations.
Personal Officer
Global Tracks Co, Jeddah July 2011 – Jan 2018
- Assisted management in implementing HR policies, managing employee records, and handling government relations, including sponsorship transfers and residency renewals.
- Oversaw payroll processing, attendance tracking, and vacation scheduling for over 70 employees.
- Managed medical insurance, petty cash auditing, and employee performance documentation.
- Prepared customs and legal documents for imported goods and coordinated with government authorities on compliance matters.
- Issued bank guarantees and letters of credit for both local and international suppliers.
- Supported the study and evaluation of new projects and prepared required documentation for tender submissions.
- Organised department meetings, tracked follow-ups, managed internal correspondence, and maintained a structured filing system.
WORK
Executive Secretary
Dr. Abdulrahman Bakhsh Hospital, Jeddah July 2007 - June 2011
- Processing letters to banks concerning letters of Guarantee, Letters of credit & other confidential correspondence with various financial institutions.
- Checks are processed for employees & vendors to be logged in and sent to the management for different approval levels & to be signed.
- Process letters to the bank for salary transfers of loaners staff & Hospital trainee staff.
- Answer vendors' inquiries on their payments & prepare all the legal documents for customs clearance for importing goods.
Administrative Coordinator
Dr. Abdulrahman Bakhsh Hospital, Jeddah May 2006 - June 2007
Served as a key coordinator in the Health Care Department of the hospital, managing operations across multiple functions including:
- Staff Coordination: Oversaw scheduling and coordination for staff nurses, doctors, physiotherapists, and ambulance services.
- Patient Accounting: Acted as an accountant for patient-related billing and documentation.
- Claims Management: Handled internal and external claims as a secretary for the Home Care Department, ensuring timely and accurate processing.
PROJECTS
Full Assets Management
A project that allows an organization to manage assets' full lifecycle utilizing barcodes, count asset inventories, control transfers, depreciation, disposals, as well as maintenance and warranty records. by a cutting-edge mobile application allowing the company to manage the fixed assets on locations with efficient tags, scans, and enters data of each item that has to be tracked.
Staff E-Services (SES)
Design and implement a solution model that allows employees to access the company's human resource information system named (SES). The SES is an Employees Management Software that allows employers to easily keep track of all information. The administrator can use the program to modify employees, add new ones, transfer, promote, & terminate employees according to Saudi labor law.
RESEARCH
RESEARCH & PUBLICATION
Analyze and Predict Divorce in Saudi Society Using Machine Learning Techniques
The aim and the scope of this research were to collect data from divorced and married couples via a survey, to uncover the most essential elements that affect divorce in Saudi society. Machine Learning and data mining techniques were used to extract, analyze, and find correlated features, for prediction and classification.
Under Process
Submitted in December 2022
Abstract
When we look at the Saudi community's divorce rates, we can observe that it is growing yearly. This emphasizes the importance of adopting scientifically supported procedures and policies to examine the issue of divorce and avoid it. The scope of this research is to collect data from divorced and married couples via a survey conducted with the assistance of the Al Mawaddah Association for Family Development also, to uncover the essential elements that affect divorce, as well as those that keep a marriage together. Machine Learning and data mining techniques are used to extract, analyze, and find correlated features, for the prediction and classification part, 7 algorithms of Machine learning and two Artificial Neural networks were created, and selected the best hyperparameters through tuning technique, mentioned the number of inputs, hidden, output layers, types of activation function, the optimizer technique to minimize the random noise, and a regularization idea utilized to increase the model's generalization; with justification for which method is better than the others. The performance was measured via evaluation metrics, including the proposed models' accuracy. The results revealed that Random Forest and Logistic Regression got a similar accuracy ratio of 97\% amongst the classifiers for predicting divorce. However, the enhanced architecture of the Neural Network outperforms Machine Learning in terms of performance by 99.52\%. At the end of this research, a comparison between Machine Learning models and Neural Network performance, some solutions, and suggestions are offered to assist the community in reducing divorce cases and maintaining marital relationships.
Read the manuscript
Under Process
Submitted in December 2022
Abstract
When we look at the Saudi community's divorce rates, we can observe that it is growing yearly. This emphasizes the importance of adopting scientifically supported procedures and policies to examine the issue of divorce and avoid it. The scope of this research is to collect data from divorced and married couples via a survey conducted with the assistance of the Al Mawaddah Association for Family Development also, to uncover the essential elements that affect divorce, as well as those that keep a marriage together. Machine Learning and data mining techniques are used to extract, analyze, and find correlated features, for the prediction and classification part, 7 algorithms of Machine learning and two Artificial Neural networks were created, and selected the best hyperparameters through tuning technique, mentioned the number of inputs, hidden, output layers, types of activation function, the optimizer technique to minimize the random noise, and a regularization idea utilized to increase the model's generalization; with justification for which method is better than the others. The performance was measured via evaluation metrics, including the proposed models' accuracy. The results revealed that Random Forest and Logistic Regression got a similar accuracy ratio of 97\% amongst the classifiers for predicting divorce. However, the enhanced architecture of the Neural Network outperforms Machine Learning in terms of performance by 99.52\%. At the end of this research, a comparison between Machine Learning models and Neural Network performance, some solutions, and suggestions are offered to assist the community in reducing divorce cases and maintaining marital relationships.
Read the manuscript
Employees Attrition Analysis based on different factors using various machine learning techniques
This paper considers the prediction and analysis of employee attrition using machine learning models. Applying on IBM dataset, five main tests were conducted to predict employee attrition using classifiers. The dataset was tested on random examples for unknown cases. Then, increasing the size of the minority class while decreasing the size of the majority class. In terms of performance evaluation metrics, the proposed approach outperforms other studies, according to the results of the experiment.
Under Process
Submitted in October 2022
Abstract
Machine Learning (ML) has the ability to explore the algorithms that can learn from and make predictions on a given data. Organizations, due to their strategic demands, invest much time and effort in workforce hiring. When employee’s attrition, the companies not only lose a productive staff member but also the resources and funds, in particular, the efforts of HR staff by hiring and selecting certain staff members and training them for their related tasks is invested in them. This paper considers the prediction and analysis of employee attrition using Machine Learning models. Applying on IBM dataset, five main tests were conducted to predict employee attrition using classifiers such as k Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) classifiers, and Multilayer Perceptron (MLP). The dataset was tested on random examples for unknown cases. Then, increasing the size of the minority class while decreasing the size of the majority class. For the MLP model, providing the details of the Neural Network (NN) model, mentioning the number of inputs, hidden, output layers, types of activation function and the optimizer technique. In terms of performance evaluation metrics, the proposed approach outperforms the aforementioned classifiers, according to the results of the experiment
Read the manuscript
Under Process
Submitted in October 2022
Abstract
Machine Learning (ML) has the ability to explore the algorithms that can learn from and make predictions on a given data. Organizations, due to their strategic demands, invest much time and effort in workforce hiring. When employee’s attrition, the companies not only lose a productive staff member but also the resources and funds, in particular, the efforts of HR staff by hiring and selecting certain staff members and training them for their related tasks is invested in them. This paper considers the prediction and analysis of employee attrition using Machine Learning models. Applying on IBM dataset, five main tests were conducted to predict employee attrition using classifiers such as k Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) classifiers, and Multilayer Perceptron (MLP). The dataset was tested on random examples for unknown cases. Then, increasing the size of the minority class while decreasing the size of the majority class. For the MLP model, providing the details of the Neural Network (NN) model, mentioning the number of inputs, hidden, output layers, types of activation function and the optimizer technique. In terms of performance evaluation metrics, the proposed approach outperforms the aforementioned classifiers, according to the results of the experiment
Read the manuscript
Automatic Number Plate Recognition of Saudi License Car Plates
In this paper, 50 images were collected to detect Saudi car plates. The canny edge method to detect the car edges and different threshold techniques were used to reduce noise. The horizontal projection was applied in the segmentation process to split the plate. After that, a masking technique was utilized to locate and separate the region of interest in the image. Finally, rendering of the results of text on images down the plate regions took place.
Abstract
Automatic license plate recognition has become a significant tool as a result of the development of smart cities. During the experiment studied in the current paper, 50 images were used to detect Saudi car plates. After the preprocessing stage, the canny edge method to detect the car edges and different threshold techniques were used to reduce noise. Horizontal projection was applied in the segmentation process to split the plate. After that, a masking technique was utilized to locate and separate the region of interest in the image. OCR was applied to the processed images to read the characters and numbers in English and Arabic separately. Then, combining the English and Arabic text, after using the re-shaper for the Arabic letters. Finally, rendering of the results of text on images down the plate regions took place. The canny algorithm with projection technique with a proper preprocessing for images produces results with accuracy of 92.4% and 96% for Arabic and English language respectively.
Read the paper
Published in April 2022
Journal
Journal
Abstract
Automatic license plate recognition has become a significant tool as a result of the development of smart cities. During the experiment studied in the current paper, 50 images were used to detect Saudi car plates. After the preprocessing stage, the canny edge method to detect the car edges and different threshold techniques were used to reduce noise. Horizontal projection was applied in the segmentation process to split the plate. After that, a masking technique was utilized to locate and separate the region of interest in the image. OCR was applied to the processed images to read the characters and numbers in English and Arabic separately. Then, combining the English and Arabic text, after using the re-shaper for the Arabic letters. Finally, rendering of the results of text on images down the plate regions took place. The canny algorithm with projection technique with a proper preprocessing for images produces results with accuracy of 92.4% and 96% for Arabic and English language respectively.
Read the paper
Heart Attack Prediction using Neural Network and Different Online Learning Methods
This paper evaluated neural network models for heart attack predictions. Several online learning methods were investigated to predict heart attacks automatically and accurately. An optimizer technique was used to minimize the random noise and the regularization concept was employed to further improve the generalization of the models.
Abstract
Heart Failure represents a critical pathological case that is challenging to predict and discover at an early age, with a notable increase in morbidity and mortality. Machine Learning and Neural Network techniques play a crucial role in predicting heart attacks, diseases and more. These techniques give valuable perspectives for clinicians who may then adjust their diagnosis for each individual patient. This paper evaluated neural network models for heart attacks predictions. Several online learning methods were investigated to automatically and accurately predict heart attacks. The UCI dataset was used in this work to train and evaluate First Order and Second Order Online Learning methods; namely Backpropagation, Delta bar Delta, Levenberg Marquardt and QuickProp learning methods. An optimizer technique was also used to minimize the random noise in the database. A regularization concept was employed to further improve the generalization of the model. Results show that a three layers’ NN model with a Backpropagation algorithm and Nadam optimizer achieved a promising accuracy for the heart attach prediction tasks.
Read the paper
Published in June 2021
Journal
Journal
AbstractHeart Failure represents a critical pathological case that is challenging to predict and discover at an early age, with a notable increase in morbidity and mortality. Machine Learning and Neural Network techniques play a crucial role in predicting heart attacks, diseases and more. These techniques give valuable perspectives for clinicians who may then adjust their diagnosis for each individual patient. This paper evaluated neural network models for heart attacks predictions. Several online learning methods were investigated to automatically and accurately predict heart attacks. The UCI dataset was used in this work to train and evaluate First Order and Second Order Online Learning methods; namely Backpropagation, Delta bar Delta, Levenberg Marquardt and QuickProp learning methods. An optimizer technique was also used to minimize the random noise in the database. A regularization concept was employed to further improve the generalization of the model. Results show that a three layers’ NN model with a Backpropagation algorithm and Nadam optimizer achieved a promising accuracy for the heart attach prediction tasks.
Read the paper
Skin Image Processing in Convolutional Neural Network Approach
A survey Paper
Abstract
Skin cancer is one of the significant contributors to the cause of death over the world. Melanoma is a well-known kind of skin cancer, which usually is the most malignant lesion compared to other skin lesion types. Classification and diagnosis of skin cancer in medical science field are challenging task due to the amount of data. Skin cancer images or dataset are usually coming in different format. Identification of data involves incredible efforts for preprocessing before the auto-diagnostic work. In this report, Deep Learning (Convolutional Neural Network) is represented to build a model for predicting new cases of skin cancer. In this paper, reviewing several attempts to diagnose skin cancer cases using Deep Learning techniques, such as Convolutional Neural Network CNN for diagnosing melanoma lesions. Basic clinical images were preprocessed to reduce image illumination, then images fed to Convolutional Neural Network models. In the end, the result of each study to differentiate between malignant and benign images in CNN models.
Read the Survey
Abstract
Skin cancer is one of the significant contributors to the cause of death over the world. Melanoma is a well-known kind of skin cancer, which usually is the most malignant lesion compared to other skin lesion types. Classification and diagnosis of skin cancer in medical science field are challenging task due to the amount of data. Skin cancer images or dataset are usually coming in different format. Identification of data involves incredible efforts for preprocessing before the auto-diagnostic work. In this report, Deep Learning (Convolutional Neural Network) is represented to build a model for predicting new cases of skin cancer. In this paper, reviewing several attempts to diagnose skin cancer cases using Deep Learning techniques, such as Convolutional Neural Network CNN for diagnosing melanoma lesions. Basic clinical images were preprocessed to reduce image illumination, then images fed to Convolutional Neural Network models. In the end, the result of each study to differentiate between malignant and benign images in CNN models.
Read the Survey
PUBLICATIONS
R. Antar, S. Alghamdi, J. Alotaibi, and M. Alghamdi, “Automatic number plate recognition of Saudi license car plates,” Engineering, Technology & Applied Science Research, vol. 12, no. 2, pp. 8266–8272, 2022.
R. K. Antar, S. T. ALotaibi, and M. AlGhamdi, “Heart attack prediction using neural network and different online learning methods,” International Journal of Computer Science & Network Security, vol. 21, no. 6, pp. 77–88, 2021.
R. K. Antar, S. T. ALotaibi, and M. AlGhamdi, “Heart attack prediction using neural network and different online learning methods,” International Journal of Computer Science & Network Security, vol. 21, no. 6, pp. 77–88, 2021.
COURSES
AI Ready Program - By Zaka | Microsoft
This webinar is a 3-month series, which introduces to fundamentals and concepts of data science, machine learning, AI, and cloud computing. Its activities are focused on bridging classroom experience to industry practice by engaging students in the necessary tools and know-how for market-ready skills!
22/03/2021Google Technologies
Fighting toxic comments in social media with deep learning
17/06/2020Google Technologies
Introduction to Natural Language Processing
14/06/2020Google Technologies
Understand & interpret machine learning model decisions
12/06/2020AWARDS
Saudi Council of Engineer
Information Technology Specialist
AI Ready Competition
By Zaka | Microsoft
High Performance Computing
Docker Inc. & Saudi Aramco
First Class Honor
The Open University - UK
My skills
96%
Javascript
100%
PHP
92%
HTML/CSS
90%
Bootstrap
95%
Python
91%
Machine Learning
95%
Technical Writing
93%
Problem-solving
96%
Data Analysis & big data
100%
Data processing
98%
Project Managment
97%
