EEG-based emotion recognition using a temporal-difference minimizing neural network.

Electroencephalogram (EEG) emotion recognition plays an important role in human-computer interaction. An increasing number of algorithms for emotion recognition have been proposed recently. However, it is still challenging to make efficient use of emotional activity knowledge. In this paper, based on prior knowledge that emotion varies slowly across time, we propose a temporal-difference minimizing neural network (TDMNN) for EEG emotion recognition. We use maximum mean discrepancy (MMD) technology to evaluate the difference in EEG features across time and minimize the difference by a multibranch convolutional recurrent network. State-of-the-art performances are achieved using the proposed method on the SEED, SEED-IV, DEAP and DREAMER datasets, demonstrating the effectiveness of including prior knowledge in EEG emotion recognition.

Fusing the spatial structure of electroencephalogram channels can increase the individualization of the functional connectivity network.

An electroencephalogram (EEG) functional connectivity (FC) network is individualized and plays a significant role in EEG-based person identification. Traditional FC networks are constructed by statistical dependence and correlation between EEG channels, without considering the spatial relationships between the channels. The individual identification algorithm based on traditional FC networks is sensitive to the integrity of channels and crucially relies on signal preprocessing; therefore, finding a new presentation for FC networks may help increase the performance of the identification algorithms. EEG signals are smooth across space owing to the volume conduction effect. Considering such spatial relationships among channels can provide a more accurate representation of FC networks. In this study, we propose an EEG FC network with virtual nodes that combines the spatial relationships and functional connectivity of channels. The comparison results for individual identification show that the novel EEG network is more individualized and achieves an accuracy of 98.64% for data without preprocessing. Furthermore, our algorithm is more robust in reducing the number of channels and can perform well even when a large area of channels is removed.

Applying Multiple Functional Connectivity Features in GCN for EEG-Based Human Identification.

EEG-based human identification has gained a wide range of attention due to the further increase in demand for security. How to improve the accuracy of the human identification system is an issue worthy of attention. Using more features in the human identification system is a potential solution. However, too many features may cause overfitting, resulting in the decline of system accuracy. In this work, the graph convolutional neural network (GCN) was adopted for classification. Multiple features were combined and utilized as the structure matrix of the GCN. Because of the constant signal matrix, the training parameters would not increase as the structure matrix grows. We evaluated the classification accuracy on a classic public dataset. The results showed that utilizing multiple features of functional connectivity (FC) can improve the accuracy of the identity authentication system, the best results of which are at 98.56%. In addition, our methods showed less sensitivity to channel reduction. The method proposed in this paper combines different FCs and reaches high classification accuracy for unpreprocessed data, which inspires reducing the system cost in the actual human identification system.

Combined Effects and Cross-Interactions of Different Antibiotics and Polypeptides in Salmonella bredeney.

Salmonella spp. are health-threatening foodborne pathogens. The increasingly common spread of antibiotic-resistant Salmonella spp. is a major public healthcare issue worldwide. In this study, we wished to explore (1) antibiotic or polypeptide combinations to inhibit multidrug-resistant Salmonella bredeney and (2) the regulation of cross-resistance and collateral sensitivity of antibiotics and polypeptides. We undertook a study to select antibiotic combinations. Then, we promoted drug-resistant strains of S. bredeney after 15 types of antibiotic treatment. From each evolving population, the S. bredeney strain was exposed to a particular single drug. Then, we analyzed how the evolved S. bredeney strains acquired resistance or susceptibility to other drugs. A total of 105 combinations were tested against S. bredeney following the protocols of CLSI-2016 and EUCAST-2017. The synergistic interactions between drug pairings were diverse. Notably, polypeptides were more likely to be linked to synergistic combinations: 56% (19/34) of the synergistic pairings were relevant to polypeptides. Simultaneously, macrolides demonstrated antagonism toward polypeptides. The latter were more frequently related to collateral sensitivity than the other drugs because the other 13 drugs sensitized S. bredeney to polypeptides. In an experimental evolution involving 15 drugs, single drug-evolved strains were examined against the other 14 drugs, and the results were compared with the minimal inhibitory concentration of the ancestral strain. Single drug-evolved S. bredeney strains could alter the sensitivity to other drugs, and S. bredeney evolution against antibiotics could sensitize it to polypeptides.

Effect of the luxS gene on biofilm formation and antibiotic resistance by Salmonella serovar Dublin.

Biofilms are communities of bacterial cells that serve to protect them from external adverse influences and enhance bacterial resistance to antibiotics and sanitizers. Here, we studied the regulatory effects of glucose and sodium chloride on biofilm formation in Salmonella serovar Dublin (S. Dublin). To analyze expression levels of the quorum sensing gene luxS, we created a luxS knockout mutant. Also, antimicrobial resistance, hydrophobicity and autoinducer-2 (AI-2) activity of both the wild-type (WT) and the mutant strain were investigated. Our results revealed that glucose was not essential for S. Dublin biofilm formation but had an inhibitory effect on biofilm formation when the concentration was over 0.1%. NaCl was found to be indispensable in forming biofilm, and it also exerted an inhibitory effect at high concentrations (>1.0%). Both the WT and the mutant strains displayed significant MIC growth after biofilm formation. An increase of up to 32,768 times in the resistance of S. Dublin in biofilm phonotype against antibiotic (ampicillin) compared to its planktonic phonotype was observed. However, S. Dublin luxS knockout mutant only showed slight differences compared to the WT strain in the antimicrobial tests although it displayed better biofilm-forming capacity than the WT strain. The mutant strain also exhibited higher hydrophobicity than the WT strain, which was a feature related to biofilm formation. The production of the quorum sensing autoinducer-2 (AI-2) was significantly lower in the mutant strain than in the WT strain since the LuxS enzyme, encoded by the luxS gene, plays an essential role in AI-2 synthesis. However, the limited biofilm-forming ability in the WT strain indicated AI-2 was not directly related to S. Dublin biofilm formation. Furthermore, gene expression analysis of the WT and mutant strains revealed upregulation of genes related to biofilm stress response and enhanced resistance in the luxS mutant strain, which may provide evidence for the regulatory role of the luxS gene in biofilm formation.

The antibacterial activity of LI-F type peptide against methicillin-resistant Staphylococcus aureus (MRSA) in vitro and inhibition of infections in murine scalded epidermis.

LI-F type peptides are a family of cyclic lipodepsipeptide antibiotics isolated from Paenibacillus polymyxa and display potent activities against positive bacteria including methicillin-resistant S. aureus (MRSA). In this study, we investigated the mechanism of action of LI-F type peptide AMP-jsa9 against a MRSA (S. aureus CICC10790), which is resistant to ciprofloxacin, gentamicin, kanamycin, chloramphenicol, methicillin, and tetracycline. It was found that AMP-jsa9 mainly targets the cell membrane of MRSA and is able to inhibit biofilm formation through killing planktonic bacteria cells. Moreover, AMP-jsa9 can bind to DNA in vitro, which represents another pathway for the action on MRSA. Furthermore, in vivo treatment of scalded mice with AMP-jsa9 resulted in inhibiting MRSA infections and healing of the scalded wound. In addition, it was demonstrated that AMP-jsa9 can effectively inhibit MRSA infections in scalded murine epidermis and that inflammatory cytokines including IL-8, IL-6, tumor necrosis factor alpha (TNF-α), and monocyte chemotactic factor-1 (MCP-1) were reduced; moreover, both protein and gene expression levels of vascular endothelial growth factor (VEGF) and endothelial nitric oxide synthase (e-NOS) were enhanced, which promote neovascularization and proliferation of new granulation tissue.