Search

Abstract In real scenarios, accurate and real‐time detection of traffic signs is of great significance to the automatic driving system. To meet the requirements of detection accuracy and speed, a new traffic sign detection method based on YOLOv5 and Swin‐Transformer is proposed in this paper. First, based on the traditional Focus structure, a lightweight shallow information enhancement module is designed. Second, to enhance the channel weights of useful information, an adjustable channel attention mechanism is proposed. Additionally, a Cross Stage Partial module based on Swin‐Transformer is designed to capture contextual information around traffic signs, thereby improving the detection accuracy of small‐scale traffic signs. Finally, to better fuse deep semantic features and shallow detail features, an adaptive feature fusion method is proposed. To verify the superiority of the proposed method, experimental verification was carried out on TT100K and DFG traffic sign detection datasets, and their mAP, AP50 and FPS were (75.3, 94.8, 82) and (79.7, 85.9, 118), respectively. The experimental results show that the proposed traffic sign detection method has high accuracy and real‐time performance, and can meet the needs of traffic sign detection in the actual scene.

Owing to uneven environmental monitoring site distribution, there are significant spatial data gaps for concentrations of ambient fine particles with diameters ≤ 2.5 µm (PM2.5) obtained using traditional monitoring methods. Satellite products are an alternative data source for locations where monitoring sites are unavailable. The Moderate Resolution Imaging Spectroradiometer (MODIS) aerosol optical depth (AOD) product has been widely used in PM2.5 assessment for years; however, it has obvious data gaps in winter. Here, the Visible Infrared Imaging Radiometer Suite (VIIRS) AOD was applied to supplement MODIS AOD data to obtain a fused AOD dataset. A three-stage model consisting of a corrected AOD model, mixed effects model, and geographically weighted regression model was developed and used with meteorological and vegetation factors to estimate PM2.5. Results showed overall model fitting by cross-validation (CV) with an R2 of 0.92, mean absolute error of 5.72 µg/m3, and root mean square error of 7.15 µg/m3. The combination of MODIS AOD and VIIRS AOD was a suitable method for enhancing AOD coverage. The CV R2 value of the three-stage model (0.92) was higher than that of the two-stage model (0.9). Hence, the three-stage model could achieve a better fit in estimating PM2.5 on a regional scale.

Liupao tea is one of the well-known Chinese tea brands and a famous local specialty in Wuzhou, Guangxi, China. However, the genetic background and phylogenetic relationship of the native resource plants of Liupao tea need study, especially at the genomic level. In this study, we reported the complete chloroplast (cp) genome sequence of Camellia sinensis var. sinensis cultivar ‘Liupao’ (LP, Liupao tea population) and inferred its phylogenetic relationship to other tea plant variants or cultivars. The cp genome had a total length of 157,097 bp and the overall GC content was 37.3%. The cp genome contained one LSC region (86,641 bp) and one SSC region (18,276 bp), which were separated by two IR regions (26,090 bp, respectively). Moreover, the cp genomes were composed of 130 genes, including 86 protein-coding genes, 36 tRNA genes, and eight rRNA genes. The phylogenetic analysis showed that LP was closely related to C. sinensis var. pabilimba cv. ‘Lingyunbaihao’. This study will provide useful information for further investigating the genetic background, evolution, and breeding of LP as well as other tea cultivars and varieties.

Objective To observe the ameliorative efficacy of dihydromyricetin (DHM) on diabetic cardiomyopathy (DCM), and reveal its effect and underlying mechanism of improving myocardial glucose metabolism. Methods DCM model was established in C57BL/6J male mice by high-fat diet combined with intraperitoneal injection of streptozotocin (STZ). The mice were subsequently divided into control group (CON, normal diet), DCM group (high-fat diet), and DCM+DHM group (high-fat diet and DHM), with 15 animals in each group. After 13 weeks of intervention, echocardiography and glucose tolerance test were performed before sacrifiction. After execution, the myocardial morphology was observed with HE, Masson, and Sirius Red staining, and serum biochemical indexes were detected. The expression levels of genes and proteins related to glucose absorption and glycolysis in myocardial tissue were determined by immunofluorescence assay and qRT-PCR. The differentially expressed genes and their enriched signal pathways were analyzed with RNA-Seq technique. Results Both the cardiac systolic and diastolic functions were significantly impaired in the DCM group, accompanied with obvious inflammatory cell infiltration and increased levels of serum myocardial injury markers, such as CK, CK-MB and LDH (P < 0.01) when compared with the conditions in the CON group. Obvious myocardial fibrosis was observed in the myocardial tissue of DCM group, and elevated mRNA levels of fibrosis related molecules, TGF-β1, α-SMA and Timp (P < 0.05, P < 0.01), as well as abnormal glycolipid metabolism indexes, including glucose tolerance, blood glucose, TC, TG, LDL-C and HDL-C (P < 0.05, P < 0.01) were found. The levels of glucose absorption related genes GLUT1 and GLUT4, as well as glycolysis related genes HK1, HK2, PFK, LDH and PKM were all remarkably decreased in the myocardium (P < 0.05). However, DHM intervention greatly improved the impaired cardiac functions, ameliorated myocardial fibrosis and injury, and corrected abnormal glycolipid metabolism in the DCM mice. DHM also promoted the expression of the genes related to glucose absorption and glycolysis at mRNA and protein levels. The results of RNA-seq showed that the expression of several genes related to metabolic regulation was significantly changed after DHM intervention, among which NR4A1 might be a potential target of DHM. Conclusion DHM ameliorates the cardiac function of DCM mice, which may be closely associated with the improvement of glucose absorption and glycolysis of cardiomyocytes.

Objective To investigate the effect of dihydromyricetin (DHM) on high-fat diet (HFD)-induced intestinal epithelial barrier function in mouse model of type 2 diabetes mellitus (T2DM), and to reveal the mechanism involved with SIRT3 in mediating DHM in the process. Methods Eighteen 7-week-old SPF male wild-type (WT) mice and 30 SIRT3 KO mice were randomly divided into the control group (NC), HFD group and HFD+DHM group, respectively. The intervention time was 12 weeks. The body weight and food intake of the animals were monitored regularly. At week 12 of intervention, intestinal permeability were tested. After the mice were sacrificed, serum biochemical indexes and LPS levels as well as the intestinal histopathology were detected and observed. The expression of tight junction proteins (ZO-1, Occludin) and inflammatory factors (TNF-α, IL-1β and IL-6) in the isolated small intestinal epithelial cells and Caco-2 cells were detected by qRT-PCR and Western blotting. Then the Caco-2 cells were further infected with lentivirus (LV-SIRT3) to knock down the SIRT3 expression, and the expression levels of above molecules were detected after DHM and LPS treatment. Results In the WT and SIRT3 KO mice, HFD induced a significant increased body weight, abnormal glucose level and lipid metabolism, increased intestinal permeability and obvious changes in intestinal epithelial structure (reduced small intestinal epithelium crypt depth and villi length), as well as decreased levels of tight junction proteins and elevated levels of inflammatory factors. Furthermore, the alterations induced by HFD in SIRT3 KO mice were more significant than those in WT mice (P0.05). In the LV-SIRT3-infected Caco-2 cells, DHM failed to inhibit LPS-induced enhanced expression of the inflammatory cytokines and decreased expression of the tight junction proteins (P>0.05). Conclusion SIRT3 plays an important role in DHM-induced increased expression of small intestinal epithelial tight junction proteins, reduced expression of the inflammatory factors, maintenance of the intestinal epithelial barrier integrity and permeability and improvement of glycolipid metabolism, and thus is beneficial to delay the development of T2DM.

Worst pattern of invasion (WPOI) is a parameter used to quantify tumor invasiveness of oral squamous cell carcinoma (OSCC). Here the authors show that a fibroblast subset characterized by the expression of the oxytocin receptor is enriched in highly invasive WPOI 4-5 OSCC tumors and can be targeted to reduce the desmoplastic stroma and tumor metastasis.