Temporal-spatial cross attention network for recognizing imagined characters

• Published in: Scientific reports Vol. 14; no. 1; pp. 15432 - 11
• Main Authors: Xu, Mingyue, Zhou, Wenhui, Shen, Xingfa, Qiu, Junping, Li, Dingrui
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 04.07.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 631/1647; 631/1647/48; Attention; Attention - physiology; Biochips; Brain; Brain - physiology; Brain-Computer Interfaces; Computer applications; Deep Learning; EEG; Electroencephalography - methods; Environmental law; Firing pattern; Humanities and Social Sciences; Humans; Imagination - physiology; Implants; multidisciplinary; Neural networks; Neural Networks, Computer; Science; Science (multidisciplinary); Signal Processing, Computer-Assisted; Spatial discrimination learning; Temporal variations

Previous research has primarily employed deep learning models such as Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) for decoding imagined character signals. These approaches have treated the temporal and spatial features of the signals in a sequential, parallel, or singl...