youssef ermadi

- Developed and optimized C++ algorithms for surface calculation in the QMC123 magnetic clamping system, reducing execution time from ~7 minutes to ~5 seconds. - Automated graphical and non-graphical tests using QtTest and GoogleTest, integrated into a CI/CD pipeline with Docker and Azure DevOps. - Fixed critical bugs (software crashes, version compatibility issues) and improved robustness (refactoring with double precision, better encapsulation). - Enhanced software logic and display for proximity sensor coverage and special mold cases (holes, pockets, smaller molds). - Contributed to software validation by implementing unit tests, debugging, and integrating new mold files into the automated test pipeline.

Context: Development of a real-time pipeline for license plate recognition and vehicle detection (YOLOv5) and use of OCR (Tesseract/ResNet). - Automatic license plate recognition (LPR). - Deployment via Flask API, preprocessing, and segmentation with OpenCV. - Recognition rate improvement of +15%. - Recognition rate improved by +15%.

- Designed and implemented a medical device using a PIC18F877A microcontroller (simulated with Proteus). - Controlled stepper motor speed with a PID controller implemented on Arduino. - Gained hands-on experience in automation and control systems applied to biomedical engineering.