Design of an intelligent system for fatigue assessment based on physiological data

Identifier:  TFG:9493

Handle: https://hdl.handle.net/20.500.11797/TFG9493

Authors:  Sánchez Álvarez, Mario

Abstract:
Project that develops an intelligent system capable of predicting the level of fatigue from electrocardiogram signals using a convolutional neural network. The signal is transformed into spectrograms using STFT and classified into five levels of fatigue. The model, based on the VGG architecture, achieves more than 90% accuracy and is validated with internal and external data. Includes a mobile application for real-time monitoring.