Federico Delrio is currently a PhD student in Electrical, Electronic, and Communication Engineering at the Neuronica Lab research group at Politecnico di Torino.
He earned a master’s degree in Astrophysics at the University of Turin, with the thesis “Bounds on ultra-light axions from the neutral hydrogen auto-correlation function”. The aim of this thesis is to set limits on certain aspects of dark matter by assuming that a part of it is composed of ultra-light axions (ULAs).
His current line of research involves using machine learning/deep learning and artificial intelligence methods to improve the analysis of medical data.
The main research topics Federico Delrio is working on are as follows:
- Non-Invasive Arterial Blood Pressure Estimation from Electrocardiogram and Photoplethysmography Signals Using a Conv1D-BiLSTM Neural Network: This research consists of finding a non-invasive method for measuring arterial blood pressure using neural networks starting from ECG and possibly PPG as inputs.
- Enhancing ECG Analysis with a Hybrid Deep Learning Approach: Automatic Detection of Significant Features: This research aims to use neural networks to identify the main features of the ECG, such as the length of the QRS complex, P wave, and T wave.
- Transformer interpretability: The interpretability of artificial intelligence models is still an open problem; therefore, this research is aimed at developing a new type of Transformer that is more easily interpretable.