I am a Data Scientist with expertise in AI, machine learning, and data analysis. With a strong background in predictive modeling and deep learning, I enjoy turning data into actionable insights to help businesses thrive.
Learn more about meHighlighting proficiency in Data Science, AI, and related technologies
Expertise in data preprocessing and manipulation using Pandas, NumPy, and SQL.
Deep Learning, CNNs, NLP, TensorFlow, Keras, PyTorch, Scikit-Learn, OpenCV, Regression, Classification, Anomaly Detection, Anaconda
Proficient in visualizing complex data insights with Matplotlib, Seaborn, and PowerBI.
Skilled in AWS deployment, Docker containerization, and using Git for version control.
Python, C, C++, HTML, CSS, XML, JavaScript, React, Angular, PHP, Node.js
Microsoft Office, MobaXterm, JSON, MongoDB, MySQL, Visual Studio Code, Jupyter Notebook, GitHub
A snapshot of my professional journey.
Barco - Kortrijk, Belgium | 02/2024 - 07/2024
Thomas More De Nayer - Sint-Katelijne-Waver, Belgium | 09/2021 - 01/2024
Armentekort - Antwerpen, Belgium | 06/2022 - 12/2022
We begin by selecting the relevant features for our time series model, ensuring the input data is preprocessed appropriately.
The baseline model is constructed to establish a benchmark for model performance, offering a point of comparison for more complex models.
We develop a simple linear model as an initial step, observing the initial improvements over the baseline model.
The dense neural network adds complexity by introducing multiple layers, enhancing the model's ability to capture intricate patterns.
A Convolutional Neural Network (CNN) is applied to capture spatial hierarchies in the time series data, further improving predictions.
We employ a Recurrent Neural Network (RNN) for sequential data modeling, which effectively captures temporal dependencies.
Finally, we compare the performance of each model to the baseline to determine the best approach for the problem.
A showcase of my recent work in AI and Machine Learning.
This project demonstrates the development of a powerful retrieval-based question-answering system using LangChain and Hugging Face. The system leverages state-of-the-art language models to provide accurate and contextually relevant answers to user queries.
The Automated Image Captioning with AI project is designed to automatically generate descriptive captions for images extracted from a given website URL or a local folder. Leveraging state-of-the-art machine learning models, this project provides an interactive web interface using Gradio, making it easy for users to input a URL or select images from a folder, generate captions, and save the results.
An advanced text-based adventure game powered by Large Language Models (LLMs) that demonstrates the practical application of AI/ML in interactive entertainment. The game features dynamic quest generation, intelligent NPC interactions, and content safety validation.
This project aims to predict earthquake magnitudes and locations by analyzing seismic data to identify patterns and trends. The goal is to provide valuable insights for earthquake preparedness and mitigation.
This project aims to classify images of an industrial product from a QA dataset provided by the AI4IM project. The dataset consists of QA images of injection-moulded products taken by four different cameras from four different directions.
This is a AI classification project using PyTorch and 2 classes. Used trained model in a Flask application and showed the AI classification prediction results on web page. Also using two Docker containers with base images from Nvidia's nvidia/cuda from Docker hub.
In this project, I share the results and implementations of building a powerful retrieval-based question-answering system using LangChain and Hugging Face. I walk you through the process step-by-step, leveraging the capabilities of state-of-the-art language models. For this project, I used markdown files from the Weights & Biases documentation as the data source.
Technologies: LangChain, Hugging Face, Python
Practical Applications: Enhanced information retrieval, improved user experience, and efficient knowledge management.
The Automated Image Captioning with AI project is designed to automatically generate descriptive captions for images extracted from a given website URL or a local folder. Leveraging state-of-the-art machine learning models, this project provides an interactive web interface using Gradio, making it easy for users to input a URL or select images from a folder, generate captions, and save the results in any format to enable modifying later as well.
Development Process:
Technologies: Gradio, Hugging Face, Python
Practical Applications:
Technologies:
AI/ML Implementation:
Deployment:
Deployment Details:
docker-compose --env-file .env up --buildhttp://localhost:7860aws ecr get-login-password | docker login --username AWSkubectl apply -f kubernetes/This project demonstrates transfer learning using ResNet18 for image classification. The model was trained on a dataset of hymenoptera images and deployed using a Flask application.
Technologies: Python, PyTorch, ResNet18, Flask, Docker
Practical Applications: This project showcases the use of transfer learning to create a scalable image classification model. By leveraging a pre-trained ResNet18 model and fine-tuning it on a custom dataset, the project demonstrates how to achieve high accuracy in image classification tasks. The deployment of the model in a Flask application provides a user-friendly interface for image classification, making it accessible to a wide range of users.
Problem we are trying to solve: To build a Machine Learning model, that can evaluate images as good or bad, enabling the company to use the model for quality control purposes. This is a project to classify images from QA dataset from the AI4IM project.
Challenge => To build a single class classifier that has trained on enough good images so that it can detect bad images by only looking at them as seeing they are not good images, so that classify them as 'not good'='bad' images
Technologies: CNNs, Transfer Learning, Python
Practical Applications: Enhanced quality control, improved product consistency, and efficient defect detection.
Used machine learning to predict earthquake magnitudes with an MAE of 0.39.
Technologies: Machine Learning, Python, Jupyter Notebook
Practical Applications: Enhanced earthquake prediction, improved disaster preparedness, and efficient risk mitigation.
Methods: Random Forest Regression, Gradient Boosting Regression, Support Vector Regression (SVR) (regression version of Support Vector Machine (SVM)), Neural Networks using TensorFlow/Keras, XGBoost Regression
Data: The project uses earthquake data from Turkey, including features like date, location, latitude, longitude, magnitude, depth, and more. The dataset is available in the data directory and in dataset location: Turkey 20 Years Earthquakes CSV. Please unzip the dataset and place it in the root directory.
Formal training, hands-on experience, and educational-theoretical background.
Thomas More University of Applied Sciences - Sint-Katelijne-Waver, Belgium | 2021 - 2024
HYF - Brussels, Belgium | 2019 - 2020
Turkish State University - Ankara, Turkey | 2010 - 2014
Contributing to the community through various initiatives.
The EGG Brussels | 17/10/2019 – 19/10/2019
Read more: Medium Article
Open Knowledge Belgium |Gent - De Krook | 15/01/2020 – 29/02/2020
View the project: GitHub Repository
New Platform: Welcome to My Garden
Ongoing
What I enjoy in my free time.
Feel free to reach out for any queries or collaborations.
