Haya Rabih Alsulami
هيا رابح السلمي
Professional information
Data Science | Data Mining | Big Data | Arabic Natural Language Processing
Education
Computer Science
Expected 2024
Doctor of Philosophy (PhD) in Computer Science, King Abdul Aziz University, Jeddah, Saudi Arabia.
Language
Arabic: Native
English: Very Good
Data Science
2018-2019
Master of Science in Data Science, Lancaster University, Lancaster, United Kingdom.
Computer Science
2010 - 2014
Bachelor of Science in Computer Science, King Abdul Aziz University, Jeddah, Saudi Arabia.
Work experience
Teaching Assistant.
2016 - present
University of Jeddah, Jeddah, Saudi Arabia.
Teaching several courses such as internet applications, system analysis, and design and programming.
Programming
Apache Hive SQL
Java
Matlab
Oracle SQL
Python
R
Software
Archibus
Autocad
iClone
2010 - present
IT specialist
2015 - 2016
Innovation Source Est, Jeddah, Saudi Arabia.
Working on three-dimension animation and modelling for Arabic sign language.
2010 - present
Project
An Advanced Database Project
2022
King AbdulAziz University, Jeddah, Saudi Arabia.
In this project, I worked on designing a variety of database types to identify the suitable category for each problem. This project includes Enhanced Entity-Relationship (EER) Modeling and Object-Relational Databases (ODB). Furthermore, it covers all the required transaction processing and concurrency control protocols
Deep analysis of Distributed Database (DDB) Project
2022
King AbdulAziz University, Jeddah, Saudi Arabia.
This project includes many critical analysis aspects of distrusted databases, such as fragmentation principles. Additionally, designing the Global Conceptual Schema (GCS) for the DDB includes schema translation, schema matching, schema integration, and schema mapping to produce a unified system that accumulates all the databases.
Designing a Component-based Distributed System Project
2022
King AbdulAziz University, Jeddah, Saudi Arabia.
This project aims to design a distrusted system based on component-based methodology, which achieves several quality attributes such as portability, availability, and interoperability. Furthermore, the distributed system contains many heterogeneous and homogenous competent.
Designing a Testing System for Given Requirements Project
2022
King AbdulAziz University, Jeddah, Saudi Arabia.
In this project, I plan to investigate the correctness of a system by designing both black-box testing tasks, and white-box testing tasks.
Designing an Agent-based System Project
2021
King AbdulAziz University, Jeddah, Saudi Arabia.
The project analyzes the basic need of a client to design a stationary and parallel mobile agent-based architecture for collecting the metadata of existing components in the distributed system.
Applied Data Mining Project
2019
Lancaster University, Lancaster, United Kingdom.
In this project, I was involved in Native Language Identification (NLI) using a subset of an Arabic Learner Corpus (ALC). It used the corpus written by Chinese, Urdu, Malay, French, and English learners. The Logistic Regression algorithm is used to classify Arabic text into the author’s native language utilising the following five features: Arabic function words, normalised Arabic function words, part-of-speech (POS) tagging, average token length, and average sentence length.
Big Data Project
2019
Lancaster University, Lancaster, United Kingdom
In this project, I was involved in installing and configuring Hadoop and running a Hadoop cluster in the pseudo-distributed mode. This also included configuring and installing Apache Hive, building a database using Hive commands, and inserting datasets with millions of tuples into the database. I also engaged in data pre- processing, analysis, and post-processing of larger datasets using Python programming language, and MapReduce in Hadoop.
Data Mining Project
2018
Lancaster University, Lancaster, United Kingdom
I was involved in the implementation of data mining techniques in multiple datasets. The techniques included pre-processing, clustering, and classification. The pre-processing stage included handling missing values, the problem of imbalanced data, and outlier values. The clustering stage followed the K-means and Hierarchical algorithms. Logistic Regression, Support Vector Machine, Naive Bayes, and K-Nearest Neighbours algorithms were used for the supervised classification task.
An Android Application Project
2014
King AbdulAziz University, Jeddah, Saudi Arabia
This was an Android application. In the implementation part: I used JAVA, and XML for the programming part, and iClone for animation. The application had one input that was Arabic speech or text, and the output was a simulation of Arabic sign language.
Certificate and Conference
Effective Personal Productivity Certificate
2018
University of Jeddah, Jeddah, Saudi Arabia.
Effective Personal Productivity, Leadership Management International (LMI).
International Exhibition and Conference on Higher Education
2015
Riyadh International Convention & Exhibition Centre, Riyadh, Saudi Arabia
I participated in King Abdulaziz University’s sixth scientific forum as a student and was placed second.
Sixth Scientific Forum
2015
King Abdulaziz University, Jeddah, Saudi Arabia
I participated in King Abdulaziz University’s ninth demo day and was placed third.
Demo Day 9
2014
King Abdulaziz University, Jeddah, Saudi Arabia
I participated in King Abdulaziz University’s ninth demo day and placed third.
Course
Speaking To Persuade: Motivating Audiences With Solid Arguments And Moving Language
2021
University of Washington, Seattle, Washington, United States
This course provided the basics of persuasive speech: developing a persuasive argument, introducing the structure of persuasive speech, arguing for the use of strategic and motivational language, and other techniques for a good persuasive speech.
Deep Learning and Natural Language Processing
2020
Phi Science Institute, Amman, Jordan
This course covered an advanced concept of deep learning in the field of Natural Language Processing (NLP): the fundamentals of neural networks and deep neural networks in NLP, implementation of deep learning (RNN and LSTM) using Python, and explanation of the convolutional neural network, which included an implantation on Arabic text translation, and Arabic text classification in terms of sentiment analysis.
Writing for Publication in Scientific Journals 2020
UElectv, Edinburgh, UK
The course covered the main steps to publishing a scientific paper such as determining its publication purpose and selecting a suitable journal, writing style and language, and article structure.
Neural Network and Deep Learning 2020
Deeplearning.ai
This course afforded an overview of neural networks and deep learning, introducing the fundamentals of neural networks and deep neural networks. Additionally, it involved an implantation of a deep neural network by logistic regression using Python.
Volunteering
Natural Language Processing (NLP) and its Applications
2023
Saudi Data community, Saudi Arabia
The lecture introduced the major definition of NLP and its applications. It illustrated the challenges in processing Arabic text.
Using Data Science to Improve The Quality of Life in Saudi
2022
Google Developer Community, Saudi Arabia
The lecture introduced the major definition of data science and the quality of life. It illustrated the quality of life concept by arguing some of Saudi Vision 2030 projects, as well as the different applications of data science in several fields such as Smart Bracelet at Al-hajj, and the Saudi Genome Program.
Data Science and its Application in Different Fields
2022
Attaa digital, The Ministry of Communication and Information, Saudi Arabia
The basic concept of data science was explained, including data science definition and processes pipeline, Furthermore, it argued the different applications of data science in several fields such as manufacturing, healthcare and computing.
Speech Clustering for Commonly Used Words in Arabic Sign Language
2021
Data Science Special Interest Group, Saudi Arabia.
I worked with a team to create an Arabic speech corpus for the most commonly used words in Arabic sign language. First, a story was recorded using the 200 frequently used words in Arabic sign language. It yielded five records, with one record from each member. The records were spoken using the Saudi dialect. Second, each of the records was split into single words. Finally, all the words were examined to group similar words together. Besides word grouping, features extraction and clustering algorithms were used to investigate the ability of machine learning algorithms in clustering Arabic speech.
Data Science and its Application in Different Field Learning
2020
Data Science Special Interest Group, Saudi Arabia
The basic concept of data science was explained, including data science definition and processes pipeline, as well as the different applications of data science in several fields such as manufacturing, healthcare and computing.