Porcine circovirus-like virus P1 can infect many kinds of animals and mainly causes postweaning multisystemic wasting syndrome. In China, the genetic diversity, variation, and evolutionary processes of this virus have not been described yet. To improve our knowledge of its genetic diversity, evolution, and gene flow, we performed a bioinformatics analysis using the available nucleotide sequences of the P1 virus; among them, 12 nucleotide sequences were from ten pig farms in Jiangsu Province in this epidemiological survey, and 84 sequences were downloaded from GenBank. The P1 sequences showed a rich composition of AT nucleotides. Analyses of the complete genomic sequences were polymorphic and revealed high haplotype (gene) diversity and nucleotide diversity. A phylogenetic analysis based on the NJ method showed that all P1 virus sequences formed two distinct groups: A and B. High genetic differentiation was observed between strains from groups A and B. The codon usage pattern of P1 was affected by dinucleotide compositions. Dinucleotide UU/CC was overrepresented, and dinucleotide CG was underrepresented. The mean evolutionary rate of the P1 virus was estimated to be 3.64 × 10−4 nucleotide substitutions per site per year (subs/site/year). The neutrality tests showed negative values. The purifying selection and recombination events may play a major driving role in generating the genetic diversity of the P1 population. The information from this research may be helpful to obtain new insights into the evolution of P1.

Accurate monitoring of fire and smoke plays an irreplaceable role in preventing fires and safeguarding the safety of citizens' lives and property. The network structure of YOLOv5 is simple, but using convolution to extract features will lead to some problems such as limited receptive field, poor feature extraction ability, and insufficient feature integration. In view of the current defects of YOLOv5 target detection algorithm, a new algorithm model named Swin-YOLOv5 was proposed in this work. Swin transformation mechanism was introduced into YOLOv5 network, which enhanced the receptive field and feature extraction ability of the model without changing the depth of the model. In order to enrich the feature map splicing method of weighted Concat and enhance the feature fusion ability of model pairs, the feature splicing method of three output heads of feature fusion layer network was improved. The feature fusion module was further modified, and the weighted feature splicing method was introduced to improve the network feature fusion ability. Experimental results show that the map (average rage accuracy) of this method rises faster than the benchmark algorithm. Under the same experimental dataset, the map of this algorithm is improved by 0.7%, and the high-precision target detection speed is improved by 1.8 FPS (fast packet switch). Under the same experimental dataset, the improved algorithm could more accurately detect the targets that were not detected or detected inaccurately by the original algorithm, which embodied the adaptability of real scene detection and had practical significance. This work provided an opportunity for the application of fire-smoke detection in forest and indoor scenes and also developed a feasible idea for feature extraction and fusion of YOLOv5.

With the continuous expansion of Neural Network technology in the artificial intelligence field, for example, image recognition and retrieval, object detection, pixel processing, automatic speech generation, etc., Convolutional Neural Networks (CNN) and Deep Learning of Neural Networks (DNN) have made apparent breakthroughs. To improve the inference speed of images, the combination of FPGA-based acceleration and multiple model quantization methods has become one of the most contemporary alternative methods. This paper designed an FPGA-Based acceleration scheme combining software and hardware and effectively applied it to the Yolov4-Tiny object detection model, realizing the accelerated detection inference process from the original 6-7mins to 383ms. First, it chose the static quantization method of fixed-point numbers, fixed the position of the decimal point, and then added Batch Norm between the convolutional layer and the activation function to form a connection structure. Second, it further improved inference speed on an FPGA with a version of ZYNQ-7020 by increasing the bandwidth cap and reducing bandwidth requirements, employing a massive pipeline design. Finally, in the test of the Coco dataset, the plan has completed a substantial acceleration of the average inference speed of the Yolov4-Tiny object detection model from 7.13mins/Picture to 498.89ms/Picture, which has a high application value in the field of object detection. It dramatically improves the inference speed as well as keeps the average accuracy above 0.95.

Porcine circovirus-like virus P1, like porcine circovirus type 2 (PCV2), is a potential pathogen of post-weaning multisystemic wasting syndrome in swine. Yaks are a valuable species and an iconic symbol of the Tibet Plateau which is the highest and largest plateau in the world. In this study, a total of 105 yak diarrheal samples, collected from 13 farms in Linzhi in the Tibet Plateau from January 2019 to December 2021, that were screened for P1 and PCV2 by polymerase chain reaction, 10.48% (n = 11) were positive for P1, 4.76% (n = 5) for PCV2, and 5.71% (n = 6) were positive for coinfection of P1 and PCV2. In addition, the whole genomes of eight P1 strains and eight PCV2 strains were sequenced. Alignment of deduced amino acid sequences of P1 ORF1 and PCV2 ORF2 gene revealed that ON012566 had one unique amino acid mutation at residues 137 (T to P). This mutation has important implication for the study of virus virulence, tissue tropism, and immune response. Phylogenetic analysis shows that the yak-origin P1 strains in this study with cattle-origin P1 reference strains were grouped into one cluster. The yak-origin PCV2 (ON012566) and a buffalo-origin PCV2 (KM116514) reference strain clustered in the same branch in the PCV2b regions. Meanwhile, the remaining PCV2 strains and buffalo-origin PCV2 reference strain (ON012565) clustered in the PCV2d regions. To summarize, to our knowledge, this is the first report on the molecular prevalence and genome characteristics of P1 and PCV2 in yaks in the world and will contribute to further study of the molecular epidemiology, source, and evolution of P1 and PCV2 strains.

No abstract