Conducting research on patient-specific electroencephalography-based epilepsy seizure prediction methods enables early identification of seizure risk, providing a basis for timely intervention and treatment. However, existing methods fail to simultaneously account for the dynamic temporal feature differences of electroencephalography signals and the spatial correlations between leads when representing spatio-temporal features, limiting the representation of preictal electroencephalography features and consequently affects prediction performance. To address this issue, this paper proposes a patient-specific electroencephalography seizure prediction method based on global dynamic multi-scale spatio-temporal features. By designing a dynamic temporal attention (DTA) branch, it captures instantaneous dynamic features through convolutional extraction of feature differences between adjacent sampling points, and by designing a multi-scale spatial attention (MSSA) branch, it represents multi-scale spatial features among channels using receptive fields of convolution kernels of different sizes. Furthermore, considering the limited local receptive field of convolution operations, attention modules are introduced into the aforementioned branches to represent global information. Finally, a feature fusion (FF) branch is used to represent global dynamic multi-scale spatio-temporal features, aiming to achieve high-precision epilepsy seizure prediction. The accuracy on two public epilepsy electroencephalography datasets reached 95.36% and 72.98%, with sensitivities of 94.08% and 66.40%, and specificities of 96.91% and 79.55%, respectively. Experimental results indicate that the proposed global dynamic multi-scale spatio-temporal features can effectively characterize the dynamic temporal variations and inter-channel spatial correlations of electroencephalography signals, providing strong support for early warning of epileptic seizures.
Aiming at the limitations of clinical diagnosis of Parkinson’s disease (PD) with rapid eye movement sleep behavior disorder (RBD), in order to improve the accuracy of diagnosis, an intelligent-aided diagnosis method based on few-channel electroencephalogram (EEG) and time-frequency deep network is proposed for PD with RBD. Firstly, in order to improve the speed of the operation and robustness of the algorithm, the 6-channel scalp EEG of each subject were segmented with the same time-window. Secondly, the model of time-frequency deep network was constructed and trained with time-window EEG data to obtain the segmentation-based classification result. Finally, the output of time-frequency deep network was postprocessed to obtain the subject-based diagnosis result. Polysomnography (PSG) of 60 patients, including 30 idiopathic PD and 30 PD with RBD, were collected by Nanjing Brain Hospital Affiliated to Nanjing Medical University and the doctor’s detection results of PSG were taken as the gold standard in our study. The accuracy of the segmentation-based classification was 0.902 4 in the validation set. The accuracy of the subject-based classification was 0.933 3 in the test set. Compared with the RBD screening questionnaire (RBDSQ), the novel approach has clinical application value.
The effective classification of multi-task motor imagery electroencephalogram (EEG) is helpful to achieve accurate multi-dimensional human-computer interaction, and the high frequency domain specificity between subjects can improve the classification accuracy and robustness. Therefore, this paper proposed a multi-task EEG signal classification method based on adaptive time-frequency common spatial pattern (CSP) combined with convolutional neural network (CNN). The characteristics of subjects' personalized rhythm were extracted by adaptive spectrum awareness, and the spatial characteristics were calculated by using the one-versus-rest CSP, and then the composite time-domain characteristics were characterized to construct the spatial-temporal frequency multi-level fusion features. Finally, the CNN was used to perform high-precision and high-robust four-task classification. The algorithm in this paper was verified by the self-test dataset containing 10 subjects (33 ± 3 years old, inexperienced) and the dataset of the 4th 2018 Brain-Computer Interface Competition (BCI competition Ⅳ-2a). The average accuracy of the proposed algorithm for the four-task classification reached 93.96% and 84.04%, respectively. Compared with other advanced algorithms, the average classification accuracy of the proposed algorithm was significantly improved, and the accuracy range error between subjects was significantly reduced in the public dataset. The results show that the proposed algorithm has good performance in multi-task classification, and can effectively improve the classification accuracy and robustness.