Polyphonic sound event localization and detection based on Multiple Attention Fusion ResNet.

Sound event localization and detection have been applied in various fields. Due to the polyphony and noise interference, it becomes challenging to accurately predict the sound event and their occurrence locations. Aiming at this problem, we propose a Multiple Attention Fusion ResNet, which uses ResNet34 as the base network. Given the situation that the sound duration is not fixed, and there are multiple polyphonic and noise, we introduce the Gated Channel Transform to enhance the residual basic block. This enables the model to capture contextual information, evaluate channel weights, and reduce the interference caused by polyphony and noise. Furthermore, Split Attention is introduced to the model for capturing cross-channel information, which enhances the ability to distinguish the polyphony. Finally, Coordinate Attention is introduced to the model so that the model can focus on both the channel information and spatial location information of sound events. Experiments were conducted on two different datasets, TAU-NIGENS Spatial Sound Events 2020, and TAU-NIGENS Spatial Sound Events 2021. The results demonstrate that the proposed model significantly outperforms state-of-the-art methods under multiple polyphonic and noise-directional interference environments and it achieves competitive performance under a single polyphonic environment.

A hybrid butterfly algorithm in the optimal economic operation of microgrids.

With the increasing capacity of renewable energy generators, microgrid (MG) systems have experienced rapid development, and the optimal economic operation is one of the most important and challenging issues in the MG field. To reduce the overall generation cost of microgrids, a hybrid butterfly algorithm (HBOA) is proposed to address the optimal economic operation problem in MG systems. This algorithm uses adaptive switching thresholds to balance the global exploration capability and local exploitation capability of the algorithm. It introduces a diversity learning mechanism to enhance information exchange among populations to improve the algorithm's accuracy and proposes an elite-guided guidance strategy to accelerate the convergence speed of the algorithm. Numerical simulation experiments on 10 standard test functions validate that the HBOA algorithm has higher optimization accuracy and faster convergence speed. Simulation experiments are conducted on two operation modes of microgrids: Islanded and grid-connected, and compared with other algorithms. In islanded and grid-connected modes, HBOA can reduce operating costs by up to 11.7% and 17.7%, respectively. The experimental results confirm the applicability and superiority of the proposed algorithm for solving the optimal economic operation problem in microgrids.

Pedestrian re-identification based on attention mechanism and Multi-scale feature fusion.

Existing pedestrian re-identification models generally have low pedestrian retrieval accuracy when encountering factors such as changes in pedestrian posture and occlusion because the network cannot fully express pedestrian feature information. Therefore, this paper proposes a method to address this problem by combining the attention mechanism with multi-scale feature fusion, and combining the proposed cross-attention module with the ResNet50 backbone network. In this way, the ability of the network to extract strong salient features is significantly improved; at the same time, using the multi-scale feature fusion module to extract multi-scale features from different depths of the network, achieving the complementary advantages between features through feature addition, feature concatenation and feature weight selection. In addition, a feature enhancement method and an efficient pedestrian retrieval strategy are proposed to jointly promote the accuracy of pedestrian retrieval from both the training and testing levels. When tested on the occluded pedestrian recognition datasets Partial-REID and Partial-iLIDS, the accuracy of this method reached 70.1% and 65.6% on the Rank-1 indicator respectively, and 82.2% and 80.5% on the Rank-3 indicator respectively. At the same time, it also achieved high recognition accuracy when tested on the Market1501 dataset and DukeMTMC-reid dataset, reaching 95.9% and 89.9% on the Rank-1 indicator respectively, 89.1% and 80.3% on the mAP indicator respectively, and 67% and 46.2% on the mINP indicator respectively. It can be seen that this method has achieved good results in solving the above problems.

A novel whisker sensor with variable detection range for object positioning.

The design of a whisker sensor, inspired by mammalian whisker characteristics, is presented in this paper. It uses a novel spring structure to transfer the deformation generated by the whisker tip when it touches an object at the base, which drives the permanent magnet installed at the base to change its position. It achieves precise positioning of the object by using the magnetic induction intensity data output from the Hall sensor MLX90393. Based on the results of the finite element model analysis, the detection range of the whisker sensor can be expanded by replacing the artificial whisker material and selecting a permanent magnet of a suitable size. Calibration experiments and positioning tests were conducted on the sensor. The experimental results showed that the detection radius of the sensor was 24, 30, 33, and 39 mm for the carbon fiber, acrylic, acrylonitrile butadiene styrene plastic (ABS), and nylon whiskers, respectively, when they were matched with a NdFeB annular permanent magnet with an aperture of 3 mm and a thickness of 3 mm. The sensor is small and simple to manufacture with good sensitivity, linearity, hysteresis, and repeatability. The maximum positioning errors of the X and Y positions in the detection plane of the sensor were within ±1.3 mm, and the positioning was accurate. The sensor can be used to identify the shape of an object.

APB-13 improves the adverse outcomes caused by TGEV infection by correcting the intestinal microbial disorders in piglets.

Porcine transmissible gastroenteritis virus (TGEV) is an enteric coronavirus that has caused high morbidity and mortality of piglets worldwide. Previous studies have shown that the TGEV can lead to severe diarrhoea, vomiting and dehydration in 2-week-old piglets and weaned piglets, resulting in a large number of piglet deaths. Antimicrobial peptides have broad-spectrum antimicrobial activity and a strong killing effect on bacteria, especially on the drug-resistant pathogenic bacteria, and it has attracted broad concern. However, there are very few reports on the effect of APB-13 (an antimicrobial peptide) on the intestinal microbes of piglets infected with TGEV. In this study, 16S rRNA gene sequencing was used to compare the microbial phylum and the genus of piglet's enteric microorganism in different experimental groups, and to predict the metabolic function of the microbial flora. At the same time, the apparent digestibility of nutrients, digestive enzyme activity, daily weight gain and survival rate were also measured. TGEV infection could cause the imbalance of intestinal microbes in piglets, and increase of the relative abundance of Proteobacteria, and decrease of the relative abundance of Firmicutes, Bacteroidetes and Actinobacteri. With the addition of APB-13, this problem can be alleviated, which can reduce the relative abundance of Proteobacteria and improve the balance of intestinal microorganisms. At the microbial genus level, after adding APB-13, the relative abundance of Catenibacterium, Enterobacter and Streptococcus in the intestinal tract of piglets infected with TGEV showed significant decrease, while the relative abundance of Lactobacillus and Ruminococcus increased. Finally, we found that APB-13 can significantly increase the activity of digestive enzyme in the intestinal tract of piglet, thereby improving the apparent digestibility of nutrients and the growth performance of piglets. This study demonstrates that APB-13 can alleviate the adverse outcomes caused by TGEV infection by correcting the intestinal microbial disorders.

The Association between MUC5B Rs35705950 and Risks of Idiopathic Interstitial Pneumonia, Systemic Sclerosis Interstitial Lung Disease, and Familial Interstitial Pneumonia: A Meta-Analysis.

BACKGROUND: Interstitial lung disease (ILD) is a category of chronic lung diseases with more than 200 subtypes. Idiopathic interstitial pneumonia (IIP), systemic sclerosis (SSc) ILD, and familial interstitial pneumonia (FIP) are three major groups of lung diseases with different causes or with unknown causes. Mucin5B (MUC5B) belongs to the mucin family, which contribute to the lubricating and viscoelastic properties of the whole saliva, normal lung mucus, and cervical mucus. The association between MUC5B rs35705950 and ILDs risks has been widely studied. However, the results were inconclusive and inconsistent. METHODS: In the present meta-analysis, the database PubMed, Embase, Cochrane Central Register of Controlled Trials, CNKI and Chinese Biomedical Literature Database were searched till Aug 20th, 2018. Overall 16 publications with 28 studies, 76345 cases and 18402 controls were included. RESULTS: The results indicated a significant increase of overall IIP risk for TT genotype and T allele of the rs35705950 in all genetic models (TT vs GG, OR=9.11; TT vs GT+TT, OR=5.80; GT+TT vs GG, OR=4.34; T vs G, OR=4.03. P<0.0001). Subgroup analysis by subtypes of IIP revealed higher risks of TT genotype and T allele for IPF and iNSIP (P<0.05). A significant increase of FIP risk was also found for the TT genotype and T allele of the rs35705950 (TT vs GG, OR=17.08; GT+TT vs GG, OR=6.02; T vs G, OR=1.64.P<0.05). CONCLUSION: No significant relations existed between the rs35705950 and SSc-ILD risks. MUC5B rs35705950 might be a predictor for the susceptibility of IIP and FIP.

Intracranial Subarachnoidal Route of Infection for Investigating Roles of Streptococcus suis Biofilms in Meningitis in a Mouse Infection Model.

Streptococcus suis is not only a major bacterial pathogen of pigs worldwide but also an emerging zoonotic agent. In humans and pigs, meningitis is a major manifestation of S. suis infections. A suitable infection model is an essential tool to understand the mechanisms of diseases caused by pathogens. Several routes of infection in mice have been developed to study the pathogenesis of S. suis infection. However, the intraperitoneal, intranasal, and intravenous routes of infection are not suitable for studying the roles of S. suis surface components in meningitis directly in the brain, such as the extracellular matrix from biofilms. Although intracisternal inoculation has been used for S. suis infection, the precise injection site has not been described. Here, the intracranial subarachnoidal route of infection was described in a mouse model to investigate the roles of biofilms in S. suis meningitis. S. suis planktonic cells or biofilm state cells were directly injected into the subarachnoid space of mice through the injection site located 3.5 mm rostral from the bregma. Histopathological analysis and increased mRNA expression of TLR2 and cytokines of the brain tissue from mice injected with biofilm state cells clearly indicated that S. suis biofilm plays definitive roles in S. suis meningitis. This route of infection has obvious advantages over other routes of infection, allowing the study of the host-bacterium interaction. Furthermore, it permits the effect of bacterial components on host immune responses directly in the brain to be assessed, and mimics bacterial entrance into the central nervous system. This route of infection can be extended for investigating the mechanisms of meningitis caused by other bacteria. In addition, it can also be used to test the efficacy of drugs against bacterial meningitis.

Streptococcus suis serotype 9 strain GZ0565 contains a type VII secretion system putative substrate EsxA that contributes to bacterial virulence and a vanZ-like gene that confers resistance to teicoplanin and dalbavancin in Streptococcus agalactiae.

Streptococcus suis (SS), an important pathogen for pigs, is not only considered as a zoonotic agent for humans, but is also recognized as a major reservoir of antimicrobial resistance contributing to the spread of resistance genes to other pathogenic Streptococcus species. In addition to serotype 2 (SS2), serotype 9 (SS9) is another prevalent serotype isolated from diseased pigs. Although many SS strains have been sequenced, the complete genome of a non-SS2 virulent strain has been unavailable to date. Here, we report the complete genome of GZ0565, a virulent strain of SS9, isolated from a pig with meningitis. Comparative genomic analysis revealed five new putative virulence or antimicrobial resistance-associated genes in strain GZ0565 but not in SS2 virulent strains. These five genes encode a putative triacylglycerol lipase, a TipAS antibiotic-recognition domain protein, a putative TetR family transcriptional repressor, a protein containing a LPXTG domain and a G5 domain, and a type VII secretion system (T7SS) putative substrate (EsxA), respectively. Western blot analysis showed that strain GZ0565 can secrete EsxA. We generated an esxA deletion mutant and showed that EsxA contributes to SS virulence in a mouse infection model. Additionally, the antibiotic resistance gene vanZSS was identified and expression of vanZSS conferred resistance to teicoplanin and dalbavancin in Streptococcus agalactiae. We believe this is the first experimental demonstration of the existence of the T7SS putative substrate EsxA and its contribution to bacterial virulence in SS. Together, our results contribute to further understanding of the virulence and antimicrobial resistance characteristics of SS.

Streptococcus suis small RNA rss04 contributes to the induction of meningitis by regulating capsule synthesis and by inducing biofilm formation in a mouse infection model.

Streptococcus suis (SS) is an important pathogen for pigs, and it is also considered as a zoonotic agent for humans. Meningitis is one of the most common features of the infection caused by SS, but little is known about the mechanisms of SS meningitis. Recent studies have revealed that small RNAs (sRNAs) have emerged as key regulators of the virulence in several bacteria. In the previous study, we reported that SS sRNA rss04 was up-regulated in pig cerebrospinal fluid and contributes to SS virulence in a zebrafish infection model. Here, we show that rss04 facilitates SS invasion of mouse brain and lung in vivo. Label-free quantitation mass spectrometry analysis revealed that rss04 regulates transcriptional regulator CcpA and several virulence factors including LuxS. Transmission electron microscope and Dot-blot analyses indicated that rss04 represses capsular polysaccharide (CPS) production, which in turn facilitates SS adherence and invasion of mouse brain microvascular endothelial cells bEnd.3 in vitro and activates the mRNA expression of TLR2, CCL2, IL-6 and TNF-α in mouse brain in vivo at 12h post-infection. In addition, rss04 positively regulates SS biofilm formation. Survival analysis of infected mice showed that biofilm state in brain contributes to SS virulence by intracranial subarachnoidal route of infection. Together, our data reveal that SS sRNA rss04 contributes to the induction of meningitis by regulating the CPS synthesis and by inducing biofilm formation, thereby increasing the virulence in a mouse infection model. To our knowledge, rss04 represents the first bacterial sRNA that plays definitive roles in bacterial meningitis.

Mac Protein is not an Essential Virulence Factor for the Virulent Reference Strain Streptococcus suis P1/7.

Streptococcus suis is a major pathogen of pigs and also an important zoonotic agent for humans. A S. suis protein containing Mac-1 domain (designated Mac) is a protective antigen, exclusively cleaves porcine IgM, and contributes to complement evasion with the presence of high titers of specific porcine anti-S. suis IgM, but its role in S. suis virulence has not been investigated in natural healthy host without specific IgM. In this study, a mac deletion mutant was constructed by homologous recombination in S. suis serotype 2 virulent reference strain P1/7. Deletion of mac did not significantly influence phagocytosis or intracellular survival within murine macrophages RAW264.7, or the oxidative-burst induction of RAW264.7 and murine neutrophils. Furthermore, the mutant is as virulent as the wild-type strain in pig, mouse, and zebrafish infection models. Our data suggest that Mac is not essential for S. suis virulence in strain P1/7 in natural healthy host without specific IgM, and the immunogenicity of Mac does not appear to correlate with its significance for virulence.