The attention mechanism of the Transformer has the advantage of extracting feature correlation in the long-sequence data and visualizing the model. As time-series data, the spatial and temporal dependencies of the EEG signals between the time points and the different channels contain important information for accurate classification. So far, Transformer-based approaches have not been widely explored in motor-imagery EEG classification and visualization, especially lacking general models based on cross-individual validation. Taking advantage of the Transformer model and the spatial-temporal characteristics of the EEG signals, we designed Transformer-based models for classifications of motor imagery EEG based on the PhysioNet dataset. With 3s EEG data, our models obtained the best classification accuracy of 83.31%, 74.44%, and 64.22% on two-, three-, and four-class motor-imagery tasks in cross-individual validation, which outperformed other state-of-the-art models by 0.88%, 2.11%, and 1.06%. The inclusion of the positional embedding modules in the Transformer could improve the EEG classification performance. Furthermore, the visualization results of attention weights provided insights into the working mechanism of the Transformer-based networks during motor imagery tasks. The topography of the attention weights revealed a pattern of event-related desynchronization (ERD) which was consistent with the results from the spectral analysis of Mu and beta rhythm over the sensorimotor areas. Together, our deep learning methods not only provide novel and powerful tools for classifying and understanding EEG data but also have broad applications for brain-computer interface (BCI) systems.

No abstract

Background:Hepatitis E Virus (HEV), a zoonotic pathogen, uses several species of animal as reservoirs. Swine is considered as the major reservoir for HEV infection in humans. Genotype 4 HEV is the dominant cause of hepatitis E disease in humans in China.Objectives:Although many researches revealed that genotype 4 HEV is the main genotype that prevalent in eastern China, few researches have done to study the subtype of HEV in this area. Thus, this study aimed to investigate the subtype of HEV prevalent in eastern China.Materials and Methods:A total of 125 anti-HEV IgM positive human serum and 290 swine fecal samples were subjected to reverse transcription polymerase chain reaction (RT-PCR) screening of HEV RNA. Positive PCR products were sequenced and phylogenetically analyzed.Results:From a total of 125 human serum samples, 19.2% (24.125) were positive, while 9.66% (28.290) of the 290 swine fecal samples were positive for HEV RNA. Phylogenetic analysis based on partial capsid gene showed that the 51 HEV strains in the current study all belonged to genotype 4, clustering into 6 different subtypes. Our results also revealed that some of HEV isolates prevalent in the human and swine populations were classified into the same clusters.Conclusions:Genotype 4 HEV in eastern China shows subtype diversity and some HEV isolates are involved in cross-species transmission.

No abstract