Neurological & cognition disorders
Tool to extract biomarkers from electroencephalogram signals
Through the extraction of electroencephalogram signals and the use of artificial intelligence and machine learning techniques, the SignalEEG tool is responsible for the treatment, processing and modeling of signal data, especially wearable and EEG signals, in order to build predictive models for the detection of different mental health diseases: brain, neurological and cognitive disorders.
Specifically, the group has developed and implemented these techniques in different scenarios: schizophrenia prognosis, alcoholism, stress detection and emotion recognition. In the case of the latest, the aim is to detect negative emotions of people through brain changes, which are measured through EEG signals, to prevent the emergence of mental health problems.
The tool interface is user-friendly, easy to use and multiprocess, with functionalities for all steps of data mining: noise filtering, windowing, feature extraction, feature selection, shaping, data balancing, validation methods, visualization, among others.
This technology has been used in the development of several projects, such as SERAS (in collaboration with a private company), with the aim of improving the living conditions of patients with epilepsy through early crisis detection.
PI: María Beatriz López Ibáñez
COPI: Òscar Raya i Casanova
Research group: Smart IT Engineering and Services (SITES)
Institution: Universitat de Girona (UdG)
Project website here.
Research group website here.
For further information contact us.