RT info:eu-repo/semantics/article T1 Effect of time windows in LSTM networks for EEG-based BCIs A1 Gómez González, José Francisco A1 Martín Chinea, Kevin A1 Ortega Rodríguez, Jordan A1 Pereda de Pablo, Ernesto A1 Toledo Carrillo, Jonay Tomás A1 Acosta Sánchez, Leopoldo A2 Ingeniería Industrial K1 EEG K1 LSTM K1 Brain–computer interface K1 Machine learning K1 Deep learning K1 Artificial neural network AB People with impaired motor function could be helped by an effective brain–computer interface (BCI) based on a real-timeelectroencephalogram (EEG) and artificial intelligence algorithms. However, current methodologies for interpreting patientinstructions from an EEG are not accurate enough to be completely safe in a real-world situation , where a poor decisionwould place their physical integrity at risk, such as when traveling in an electric wheelchair in a city. For various reasons,such as the low signal-to-noise ratio of portable EEGs or the effects of signal contamination (disturbances due to usermovement, temporal variation of the features of EEG signals, etc.), a long short-term memory network (LSTM) (a type ofrecurrent neural network) that is able to learn data flow patterns from EEG signals could improve the classification of theactions taken by the user. In this paper, the effectiveness of using an LSTM with a low-cost wireless EEG device in realtime is tested, and the time window that maximizes its classification accuracy is studied. The goal is to be able toimplement it in the BCI of a smart wheelchair with a simple coded command protocol, such as opening or closing the eyes,which could be executed by patients with reduced mobility. Results show a higher resolution of the LSTM with anaccuracy range between 77.61 and 92.14% compared to traditional classifiers (59.71%), and an optimal time window ofaround 7 s for the task done by users in this work. In addition, tests in real-life contexts show that a trade-off betweenaccuracy and response times is necessary to ensure detection. SN 1871-4099 YR 2022 FD 2022 LK http://riull.ull.es/xmlui/handle/915/39046 UL http://riull.ull.es/xmlui/handle/915/39046 LA en DS Repositorio institucional de la Universidad de La Laguna RD 11-mar-2025