👋 Hi! I'm Alaa Erfan, a recent Computer Science and Information Systems graduate from Helwan University. I have a passion for machine learning, data science, and software development. I thrive on solving real-world problems using cutting-edge technologies and am constantly looking to expand my knowledge and skills.
- Python
- SQL
- TensorFlow
- Keras
- OpenCV
- Pandas
- NumPy
- Scikit-learn
- Data Visualization: Matplotlib, Seaborn, Plotly
- Machine Learning & Deep Learning
- Natural Language Processing (NLP)
- Data Analysis & Preprocessing
- Software Development
- English
- Arabic
- Description: This project aims to ease the reading of Egyptian medical prescriptions and provide an alternative drug for each drug mentioned in the prescription through the scientific name.
- Technologies: Python, OpenCV, TensorFlow, Huggingface, Doxapy, Solt
- Details:
- The project contains three main pipelines (preprocessing - English - Arabic) with more than 8 models performing different tasks, including classification for preprocessing functions, handwritten OCRs for English and Arabic languages, autocorrection, and spelling correction NLP algorithms.
- Responsibilities:
- Conducted data exploration and analysis, including data collection and data cleaning.
- Manually collected and constructed medical data.
- Found the most optimal combination of models to be used in pipelines.
- Finetuned T5 for autocorrection.
- Applied error functions to prepare the data for T5.
- Applied transfer-learning techniques for OCR models to improve model performance and make better use of limited resources.
- Trained YOLO on custom data for line segmentation and used different functions for line segmentations.
- Researched and tested common NLP algorithms for spelling corrections to find the suitable algorithm.
- Description: Detects whether a person is wearing a face mask using MobileNetV2 CNN.
- Technologies: Python, Pandas, NumPy, Matplotlib, OpenCV.
- Description: A chatbot developed to support individuals with mental health issues using NLP techniques.
- Technologies: Python, Numpy, Pytorch, NLTK.
- Description: Analyzes customer churn in the telecommunications industry using various data science techniques.
- Technologies: Python, Pandas, NumPy, Seaborn.
-
AI Engineer at Dorra Group
- Developed AI solutions for complex business challenges.
-
AI and Data Analytics Intern at ASDC (Remote)
- Worked on data analytics projects including customer segmentation and COVID-19 visualization.
-
Software Engineer Intern at Dorra Group
- Developed a web application to digitize inventory management and automated tasks to enhance productivity.
-
NLP R&D Intern at Smsm | Artificially Intelligent Agency
- Collected data and fine-tuned models for translation tasks.
- Artificial Intelligence Analyst Mastery Award - IBM
- Google Data Analytics Professional Certificate - Coursera
- Machine Learning Specialization - Deeplearning.AI (Coursera)
- Digital Marketing and Project Management Professional Certificates - Google (Coursera)
I'm always open to discussing new projects, collaborations, or job opportunities. I am also open to freelancing projects in the data field. Feel free to reach out to me!