Search

Emotion recognition is one of the most important research directions in the field of brain–computer interface (BCI). However, to conduct electroencephalogram (EEG)-based emotion recognition, there exist difficulties regarding EEG signal processing; moreover, the performance of classification models in this regard is restricted. To counter these issues, the 2022 World Robot Contest successfully held an affective BCI competition, thus promoting the innovation of EEG-based emotion recognition. In this paper, we propose the Transformer-based ensemble (TBEM) deep learning model. TBEM comprises two models: a pure convolutional neural network (CNN) model and a cascaded CNN-Transformer hybrid model. The proposed model won the abovementioned affective BCI competition's final championship in the 2022 World Robot Contest, demonstrating the effectiveness of the proposed TBEM deep learning model for EEG-based emotion recognition. [ABSTRACT FROM AUTHOR]

In this study, extended-spectrum β-lactamase (ESBL) Escherichia coli were isolated from five dairy farms in three areas of northern Xinjiang, China. Molecular biological techniques were used to systematically analyze drug resistance phenotypes and genotypes, virulence genes, phylogenetics, biofilm formation (BF), and pulsed field gel electrophoresis (PFGE) typing of isolated ESBL E. coli strains. A total of 766 samples were collected from five dairy farms in Shihezi, Urumqi and Yili, from which 149 (19.5 %, 95 % CI: 16.65 %–22.25 %) ESBL E. coli strains were isolated. Their distribution and contamination levels varied from region to region, with 16.2 % (68/419) in Urumqi, 22.4 % (60/268) in Shihezi, and 26.6 % (21/79) in Yili. The majority of isolates (97.3 %, 145/149) harbored the β-lactamase bla CTX-M gene; while bla CTX-M-1 was the dominant phylogenetic group. The analysis of 21 resistance genes and the susceptibility to 13 different antibiotics showed that 91.3 % (136/149) of strains were resistant to three or more antibiotics. Thirty-six strains (24.2 %) belonged to extraintestinal pathogenic E. coli (ExPEC), and phylogenetic typing results were mainly grouped A (50.3 %) and B1 (37.6 %). Also, the biofilm assay revealed that 112 strains (75.2 %) could form biofilms. PFGE results showed that the 49 isolates revealed 21 major pulsotypes (P1–P21) and 28 subtypes with 80 % similarity, indicating the overall genetic diversity in the distribution area and sources of the samples. • 91.3 % of the E. coli strains were classified as multi-resistant strains, and carried multiple drug resistance genes. • Of the 149 E. coli isolates, 36 were defined as ExPEC, indicating their pathogenic potential. • The coincidence rate in 149 E. coli strains for BF ability and antibiotic resistance (13 antibiotics) was >77.2 %. • PFGE showed 21 major pulsotypes indicating the genetic diversity of isolates in terms of distribution region and source. [ABSTRACT FROM AUTHOR]