Search

A robust vehicle speed measurement system based on feature information fusion for vehicle multi-characteristic detection is proposed in this paper. A vehicle multi-characteristic dataset is constructed. With this dataset, seven CNN-based modern object detection algorithms are trained for vehicle multi-characteristic detection. The FPN-based YOLOv4 is selected as the best vehicle multi-characteristic detection algorithm, which applies feature information fusion of different scales with both rich high-level semantic information and detailed low-level location information. The YOLOv4 algorithm is improved by combing with the attention mechanism, in which the residual module in YOLOv4 is replaced by the ECA channel attention module with cross channel interaction. An improved ECA-YOLOv4 object detection algorithm based on both feature information fusion and cross channel interaction is proposed, which improves the performance of YOLOv4 for vehicle multi-characteristic detection and reduces the model parameter size and FLOPs as well. A multi-characteristic fused speed measurement system based on license plate, logo, and light is designed accordingly. The system performance is verified by experiments. The experimental results show that the speed measurement error rate of the proposed system meets the requirement of the China national standard GB/T 21555-2007 in which the speed measurement error rate should be less than 6%. The proposed system can efficiently enhance the vehicle speed measurement accuracy and effectively improve the vehicle speed measurement robustness. [ABSTRACT FROM AUTHOR]

Background and Aims: Accumulating circular RNAs (circRNAs) play important roles in tissue repair and organ regeneration. However, the biological effects of circRNAs on liver regeneration remain largely unknown. This study aims to systematically elucidate the functions and mechanisms of circRNAs derived from lipopolysaccharide‐responsive beige‐like anchor protein (LRBA) in regulating liver regeneration. Methods: CircRNAs derived from mouse LRBA gene were identified using CircBase. In vivo and in vitro experiments were conducted to confirm the effects of circLRBA on liver regeneration. RNA pull‐down and RNA immunoprecipitation assays were used to investigate the underlying mechanisms. Clinical samples and cirrhotic mouse models were used to evaluate the clinical significance and transitional value of circLRBA. Results: Eight circRNAs derived from LRBA were registered in CircBase. The circRNA mmu_circ_0018031 (circLRBA) was significantly upregulated in the liver tissues after 2/3 partial hepatectomy (PHx). Adeno‐associated virus serotype 8 (AAV8)‐mediated knockdown of circLRBA markedly inhibited mouse liver regeneration after 2/3 PHx. In vitro experiments confirmed that circLRBA exerted its growth‐promoting function mainly through liver parenchymal cells. Mechanistically, circLRBA acted as a scaffold for the interaction between E3 ubiquitin‐protein ligase ring finger protein 123 and p27, facilitating the ubiquitination degradation of p27. Clinically, circLRBA was lowly expressed in cirrhotic liver tissues and negatively correlated with perioperative levels of total bilirubin. Furthermore, overexpression of circLRBA enhanced cirrhotic mouse liver regeneration after 2/3 PHx. Conclusions: We conclude that circLRBA is a novel growth promoter in liver regeneration and a potential therapeutic target related to deficiency of cirrhotic liver regeneration. [ABSTRACT FROM AUTHOR]

The liver has an excellent capacity for regeneration when faced with external injury and the damage differs from that of other organs in the body. Our aim was to identify the role of circular RNA (circRNA) during the DNA synthesis phase (36 h) of mice liver regeneration. High-throughput RNA sequencing was conducted to explore circRNA and messenger RNA (mRNA) expression in three pairs of mice liver tissue at 0 and 36 h after 2/3 partial hepatectomy. One hundred differentially expressed circRNAs were detected, including 66 upregulated and 34 downregulated circRNAs. We also explored 2483 differentially expressed mRNAs, including 1422 upregulated and 1061 downregulated mRNAs. Gene ontology and Kyoto Encyclopedia of Genes and Genomes indicated that cell cycle regulation, material metabolism, and multiple classical pathways were involved in the DNA synthesis process. A competing endogenous RNA (ceRNA) network containing 5 circRNAs, 28 target genes, and 533 microRNAs (miRNAs) was constructed, and we selected the top 5 miRNAs to map it. Potential key circRNAs were validated with the quantitative real-time PCR technique and their regeneration curves, including consecutive time points, were produced. Finally, a cell counting kit-8 assay on key circRNAs of ceRNA network was performed to further confirm their roles in the DNA synthesis phase of liver regeneration. This study provides a circRNA expression profile for liver regeneration and contributes valuable information for future research. [ABSTRACT FROM AUTHOR]