LHPE-nets: A lightweight 2D and 3D human pose estimation model with well-structural deep networks and multi-view pose sample simplification method.

The cross-view 3D human pose estimation model has made significant progress, it better completed the task of human joint positioning and skeleton modeling in 3D through multi-view fusion method. The multi-view 2D pose estimation part of this model is very important, but its training cost is also very high. It uses some deep learning networks to generate heatmaps for each view. Therefore, in this article, we tested some new deep learning networks for pose estimation tasks. These deep networks include Mobilenetv2, Mobilenetv3, Efficientnetv2 and Resnet. Then, based on the performance and drawbacks of these networks, we built multiple deep learning networks with better performance. We call our network in this article LHPE-nets, which mainly includes Low-Span network and RDNS network. LHPE-nets uses a network structure with evenly distributed channels, inverted residuals, external residual blocks and a framework for processing small-resolution samples to achieve training saturation faster. And we also designed a static pose sample simplification method for 3D pose data. It implemented low-cost sample storage, and it was also convenient for models to read these samples. In the experiment, we used several recent models and two public estimation indicators. The experimental results show the superiority of this work in fast start-up and network lightweight, it is about 1-5 epochs faster than the Resnet-34 during training. And they also show the accuracy improvement of this work in estimating different joints, the estimated performance of approximately 60% of the joints is improved. Its performance in the overall human pose estimation exceeds other networks by more than 7mm. The experiment analyzes the network size, fast start-up and the performance in 2D and 3D pose estimation of the model in this paper in detail. Compared with other pose estimation models, its performance has also reached a higher level of application.

Genotype and mutation patterns of macrolide resistance genes of Mycoplasma pneumoniae from children with pneumonia in Qingdao, China, in 2019.

OBJECTIVES: This study assessed the incidence and resistance of Mycoplasma pneumoniae (MP) in children in Qingdao, China, in 2019. METHODS: We detected MP infection in 78 pharyngeal swabs from children with pneumonia by qPCR. The RepMP4 element in the P1 adhesin gene, domain V of the 23S rRNA gene, and the L4/L22 ribosomal proteins were amplified by nested PCR. Evolutionary analysis was conducted based on the P1 gene sequence. Resistance mutations in domain V of the 23S rRNA gene and L4/L22 ribosomal proteins were analysed. RESULTS: The incidence of MP infection in children with pneumonia was 59.0% (46/78). The mean duration of MP infection was longer than that of non-MP infection. According to P1 gene sequencing of 21 samples, 12 (57.1%) were type 1 and 9 (42.9%) were type 2. Drug resistance mutations A2063G in domain V of 23S rRNA gene and T508C in L22 were identified from all sequenced MP. However, mutations at positions 2064 and 2617 were not found in this study. C162A mutation appeared in most type 2 samples. A430G mutation appeared in one type 1 sample and in several type 2 samples. T279C mutation in L22 was mostly found in type 2 samples. CONCLUSION: The incidence of MP infection was 59.0% in children with pneumonia in Qingdao in 2019. Type 1 MP infection was slightly more common than type 2, indicating that the genotype of MP is gradually shifting from type 1 to type 2. Macrolide resistance mutation A2063G could be detected in all sequenced MP.

The Differential Characteristics Between Severe Fever With Thrombocytopenia Syndrome and Hemorrhagic Fever With Renal Syndrome in the Endemic Regions.

An effective differentiation between severe fever with thrombocytopenia syndrome and hemorrhagic fever with renal syndrome was attained by a model considering patients' age, mouse/tick contact, presence of blush, low back pain, diarrhea, enlarged lymph nodes, and white blood cell count.

Genetic and environmental effects on the bone development of the hand and wrist in Chinese young twins.

We assessed genetic and environmental effects on bone development of the hand and wrist, and on key anthropometric measures in Chinese young twins. In total, 139 monozygotic and 95 dizygotic twin pairs aged from 5 to 18 years were recruited. The twin correlations of total hand and wrist scores for monozygotic (MZ) and dizygotic (DZ) twins were 0.71 and 0.36, respectively. Bivariate model analysis showed moderate genetic correlations only for total skeletal maturity vs. weight and total skeletal maturity vs. waist circumference (r, 0.51 and 0.46, respectively). Our findings demonstrated that genetic factors played important roles in bone development of the hand and wrist in Chinese young twins, and that these genetic effects might be distinct from those influencing anthropometric measures.

[Expression levels of Cdc2 and Cdc25A mRNA in cattle, yak, and cattle-yak testis].

The infertility of cattle-yak, which is the hybrid offspring of cattle and yak, is a difficult problem in crossbreeding and improvement of yak. Cdc2 and Cdc25A are the key genes of meiosis. The decline of their expression levels will cause the spermatogenesis failure and lead to infertility. Therefore, this study was conducted to study the relationship between the infertility of cattle-yak and the expression levels of Cdc2/Cdc25A genes. The expression profiles were obtained by RT-PCR. Cdc2 and Cdc25A genes were widely expressed in many tissues, which confirmed their important role in cell division and the progression of cell cycle. Real-time quantitative PCR analysis indicated that the expression levels of Cdc2 and Cdc25A in cattle and yak testis were higher than those in cattle-yak (P<0.05). Therefore, low expression levels of Cdc2 and Cdc25A genes may have a relationship with the infertility of cattle-yak.