Research on Low-Voltage Arc Fault Based on CNN-Transformer Parallel Neural Network with Threshold-Moving Optimization.

Low-voltage arc fault detection can effectively prevent fires, electric shocks, and other accidents, reducing potential risks to human life and property. The research on arc fault circuit interrupters (AFCIs) is of great significance for both safety in production scenarios and daily living disaster prevention. Considering the diverse characteristics of loads between the normal operational state and the arc fault condition, a parallel neural network structure is proposed for arc fault recognition, which is based on a convolutional neural network (CNN) and a Transformer. The network uses convolutional layers and Transformer encoders to process the low-frequency current and high-frequency components, respectively. Then, it uses Softmax classification to perform supervised learning on the concatenated features. The method combines the advantages of both networks and effectively reduces the required depth and computational complexity. The experimental results show that the accuracy of this method can reach 99.74%, and with the threshold-moving method, the erroneous judgment rate can be lower. These results indicate that the parallel neural network can definitely detect arc faults and also improve recognition efficiency due to its lean structure.

Defining the transcriptome of PIK3CA-altered cells in a human capillary malformation using single cell long-read sequencing.

PIK3CA-related overgrowth spectrum (PROS) disorders are caused by somatic mosaic variants that result in constitutive activation of the phosphatidylinositol-3-kinase/AKT/mTOR pathway. Promising responses to molecularly targeted therapy have been reported, although identification of an appropriate agent can be hampered by the mosaic nature and corresponding low variant allele frequency of the causal variant. Moreover, our understanding of the molecular consequences of these variants-for example how they affect gene expression profiles-remains limited. Here we describe in vitro expansion of a human capillary malformation followed by molecular characterization using exome sequencing, single cell gene expression, and targeted long-read single cell RNA-sequencing in a patient with clinical features consistent with Megalencephaly-Capillary Malformation Syndrome (MCAP, a PROS condition). These approaches identified a targetable PIK3CA variant with expression restricted to PAX3+ fibroblast and undifferentiated keratinocyte populations. This study highlights the innovative combination of next-generation single cell sequencing methods to better understand unique transcriptomic profiles and cell types associated with MCAP, revealing molecular intricacies of this genetic syndrome.

Neural stem and progenitor cells support and protect adult hippocampal function via vascular endothelial growth factor secretion.

Adult neural stem and progenitor cells (NSPCs) reside in the dentate gyrus (DG) of the hippocampus throughout the lifespan of most mammalian species. In addition to generating new neurons, NSPCs may alter their niche via secretion of growth factors and cytokines. We recently showed that adult DG NSPCs secrete vascular endothelial growth factor (VEGF), which is critical for maintaining adult neurogenesis. Here, we asked whether NSPC-derived VEGF alters hippocampal function independent of adult neurogenesis. We found that loss of NSPC-derived VEGF acutely impaired hippocampal memory, caused neuronal hyperexcitability and exacerbated excitotoxic injury. We also found that NSPCs generate substantial proportions of total DG VEGF and VEGF disperses broadly throughout the DG, both of which help explain how this anatomically-restricted cell population could modulate function broadly. These findings suggest that NSPCs actively support and protect DG function via secreted VEGF, thereby providing a non-neurogenic functional dimension to endogenous NSPCs.