Chawki Hjaiji

Built a classifier for brain tumor image classification with an accuracy of 90% to test the impact of data augmentation. Generated synthetic data resembling real medical images using recent approaches such as GAN-based models. Injected different percentages (15%, 35%, 50%, and 80%) of synthetic images into the original dataset. Evaluated the adopted approaches using the Brain Tumor Detection MRI dataset, which consists of 3000 MRI images of brain tumors.

Worked on a sustainable energy management project, including the development of smart metering tools such as the electrical meter Voltix. Analyzed the state of the art in electrical energy disaggregation and identified relevant approaches. Implemented various models to predict the energy consumption of individual appliances with an accuracy of 92%. Utilized a diverse range of publicly available datasets, such as the REDD dataset, which contains 13 million samples of electrical energy measurements.

Top school in Tunisia with including an acceptance rate of only 50 students out of 5000 applicants each year. Courses: Data Science, Machine Learning, Optimization, Probability and Statistics, Stochastic Processes, Operational Research.

University studies preparing for the national engineering school entrance exam. Courses: Linear Algebra, Applied Mathematics, Physics, Chemistry, Python, SQL. Two years in a row: top 0.01% Nationally: top 0.01%