Traveling Salesman Problem with Genetic Algorithms

In this project, I used a genetic algorithm to solve the Traveling Salesman Problem (TSP) and optimized its performance by learning Julia. The focus was on developing and fine-tuning genetic operators like selection, crossover, and mutation to minimize travel distance. I gained a solid understanding of genetic algorithms and Julia's efficiency in handling large datasets, while also learning key lessons in algorithm design and problem-solving.

Enhancing Free-Throw Skill Acquisition with Intelligent Psychomotor Systems

This project introduced me to intelligent psychomotor systems for improving basketball free-throw performance using the SMDD framework. I learned how to analyze data from video and accelerometers to identify key factors influencing shot success. The experience highlighted the challenges of working with limited datasets and reinforced the importance of data quality in modeling. It also deepened my understanding of movement analysis and the potential of targeted feedback for skill improvement.

Correction of Rainfall Prediction for the Iberian Peninsula with ML Techniques

Through this project, I learned how to leverage deep learning to enhance precipitation forecasts from the GEFS system for the Iberian Peninsula and the Balearic Islands. I gained experience in handling meteorological data, selecting relevant predictors, and developing models that improve accuracy using metrics like root mean square error and Pearson’s correlation. This work also taught me the challenges of correcting numerical weather predictions and the importance of choosing appropriate evaluation metrics.