Long Short-Term Memory Employed for Classifying P300-Based BCI

Designed to help patients with motor impairments such as “locked-in” syndrome, a brain-computer interface (BCI) is a device that uses brain signals for communication. This method, which focuses on neuromuscular illnesses in particular, depends on accurate and consistent detection of brain signals. In devices such as the P300 Speller, where it is used to choose desired alphabets, the P300 brain wave is essential. Because of its spatiotemporal nature, poor signal-to-noise ratio, and complexity, the P300 signal is difficult to recognize. In contrast to other options like convolutional neural networks (CNNs), this study investigates the use of long-short term memory (LSTM) as a deep learning technique for P300 signal recognition. In terms of managing and predicting spelling data, the results show that both CNN and LSTM models work well, with equivalent accuracy in P300 paradigm identification.