Implementación de aprendizaje automático en un modelo arquitectónico de software para la detección de convulsiones en pacientes con epilepsia

Abstract

Epilepsy is a disease that, as of 2019, affected about 50 million people worldwide, making it one of the most common neurological disorders. This is the reason that working on projects that bring benefits on this disorder have a great impact. Today there are many technological and computational tools that can be used to mitigate the impacts of diseases such as epilepsy. One of those tools is Machine Learning, which, from data, allows the construction of models to detect or even predict epilepsy attacks. The objective of this work is the construction of a model that allows the detection of epilepsy seizures from the signals thrown by an electroencephalogram (EEG). For the implementation of this model, a software architecture will be designed that allows the reception of signals from EEG, classify them in the model and return a response with said classification. This response can be interpreted by any IoT device that is connected to the internet and has access to the classification service