Patricio Alejandro Rojas-Carrasco is a Civil Electronic Engineer and researcher. He is currently pursuing a Ph.D. in Systems and Control Engineering at UNED (Spain). He holds a Master’s degree in Mathematical Engineering and Computing. He has over 20 years of academic experience in engineering and computer science education.
His research focuses on embedded artificial intelligence, TinyML, and the efficient deployment of machine learning models on resource-constrained platforms. He is particularly interested in the comparative analysis of lightweight models (e.g., logistic regression, MLP, and CNN) across embedded systems such as ESP32 and Raspberry Pi devices, with metrics including accuracy, latency, and memory footprint.
In parallel, he explores integrating artificial intelligence, digital twins, and immersive technologies to support engineering education. He has participated in applied research and innovation projects, including initiatives in AI adoption in higher education and embedded systems development.
He has authored and supervised multiple engineering projects. He contributes to the development of reproducible experimental frameworks and promotes open science practices through public datasets and code repositories. His work aims to bridge the gap between theoretical machine learning and real-world deployment in constrained environments.
Patricio Alejandro Rojas-Carrasco is a Civil Electronic Engineer and researcher. He is currently pursuing a Ph.D. in Systems and Control Engineering at UNED (Spain). He holds a Master’s degree in Mathematical Engineering and Computing. He has over 20 years of academic experience in engineering and computer science education.
His research focuses on embedded artificial intelligence, TinyML, and the efficient deployment of machine learning models on resource-constrained platforms. He is particularly interested in the comparative analysis of lightweight models (e.g., logistic regression, MLP, and CNN) across embedded systems such as ESP32 and Raspberry Pi devices, with metrics including accuracy, latency, and memory footprint.
In parallel, he explores integrating artificial intelligence, digital twins, and immersive technologies to support engineering education. He has participated in applied research and innovation projects, including initiatives in AI adoption in higher education and embedded systems development.
He has authored and supervised multiple engineering projects. He contributes to the development of reproducible experimental frameworks and promotes open science practices through public datasets and code repositories. His work aims to bridge the gap between theoretical machine learning and real-world deployment in constrained environments.