An improved algorithm based on YOLOv5 for detecting Ambrosia trifida in UAV images.

A YOLOv5-based YOLOv5-KE unmanned aerial vehicle (UAV) image detection algorithm is proposed to address the low detection accuracy caused by the small size, high density, and overlapping leaves of Ambrosia trifida targets in UAV images. The YOLOv5-KE algorithm builds upon the YOLOv5 algorithm by adding a micro-scale detection layer, adjusting the hierarchical detection settings based on k-Means for Anchor Box, improving the loss function of CIoU, reselecting and improving the detection box fusion algorithm. Comparative validation experiments of the YOLOv5-KE algorithm for Ambrosia trifida recognition were conducted using a self-built dataset.

Ginsenoside Rb1 alleviates chronic intermittent hypoxia-induced diabetic cardiomyopathy in db/db mice by regulating the adenosine monophosphate-activated protein kinase/Nrf2/heme oxygenase-1 signaling pathway.

Objective: To examine the protective effect of ginsenoside Rb1 (Rb1), the main component of Renshen (), on cardiomyopathy in db/db mice exposed to chronic intermittent hypoxia (CIH) and explore the potential underlying mechanism of Rb1 in treating diabetic cardiomyopathy (DCM).

Methods: The db/db mice were randomly separated into five groups: normal control group, model group, Rb1 20 mg/kg group, Rb1 40 mg/kg group, and glucagon-like peptide-1 (GLP-1) group. Mice were exposed to air-condition or CIH for 8 weeks, and Rb1 and GLP-1 were administrated before CIH exposure every day.