RESUMO
Advanced object detection methods always face high algorithmic complexity or low accuracy when used in pedestrian target detection for the autonomous driving system. This paper proposes a lightweight pedestrian detection approach called the YOLOv5s-G2 network to address these issues. We apply Ghost and GhostC3 modules in the YOLOv5s-G2 network to minimize computational cost during feature extraction while keeping the network's capability of extracting features intact. The YOLOv5s-G2 network improves feature extraction accuracy by incorporating the Global Attention Mechanism (GAM) module. This application can extract relevant information for pedestrian target identification tasks and suppress irrelevant information, improving the unidentified problem of occluded and small targets by replacing the GIoU loss function used in the bounding box regression with the α-CIoU loss function. The YOLOv5s-G2 network is evaluated on the WiderPerson dataset to ensure its efficacy. Our proposed YOLOv5s-G2 network offers a 1.0% increase in detection accuracy and a 13.2% decrease in Floating Point Operations (FLOPs) compared to the existing YOLOv5s network. As a result, the YOLOv5s-G2 network is preferable for pedestrian identification as it is both more lightweight and more accurate.
RESUMO
Hereditary protein S (PS) deficiency is an independent risk factor for venous thromboembolism. However, the correlation between PS and arterial thrombotic disease, such as cerebral thrombosis, is not clear. The present study focused on the molecular mechanisms underlying ischemic stroke caused by a PS gene mutation in one family. The activity of antithrombin, protein C and PS in the plasma of the proband was measured, and the genes encoding PS were amplified and sequenced. The cellular localization and expression of PS were analyzed in HEK293 cells. The proband was a 50yearold male. Plasma PS activity of the proband was 38.9%, which was significantly decreased compared with normal levels. Sequencing analysis revealed a PROS1 c.1486_1490delGATTA mutation on exon 12. This frameshift mutation converts Asp496 in the precursor PS into the termination codon. In addition, the PROS1 mutation was correlated with low PS activity in the family. Functional tests revealed that the mutant protein aggregated in the cytoplasm and its secretion and expression decreased. In conclusion, protein S mutation appeared to be the primary cause of thrombosis in the family of the present study. However, the correlation between PS deficiency and ischemic stroke requires further investigation.