Search

Since the propagation of deep neural networks results in the loss of detailed feature information, the performance of most object detection methods is limited due to their tendency to learn regional features in visual space while neglecting relationships between objects. Therefore, this study proposes the Graph Relational Decision Network (GRDN), which mines relationships between objects in a dataset. The GRDN consists of a graph decision network, decision coefficient, and step-wise relation deduction module. The graph decision network comprises an edge decision network, and a node decision network, wherein a data-driven technique is employed to obtain implicit relationships between labels in a dataset. These relationships are expressed through an adaptive dynamic graph, which is subsequently recoded by means of the decision coefficient, which can enhance semantic information. In the step-wise relation deduction module, semantic information is employed as a guide to prevent distraction. A series of experiments were conducted on the MS COCO dataset. The proposed method achieves 52.8% box AP on object detection, which is 2.3% box AP higher than Cascade Mask R-CNN. The experimental results show that the addition of dynamic semantic information in this study can make up for the loss of detailed information and focus on key information, thereby improving the detection ability of small objects and occluded objects. In summary, this study extracts inter-object relationships to obtain more complete semantic information, which enriches the research of object detection. • The proposed method mines relationships between objects in a dataset. • A graph decision network is proposed to dynamically obtain semantic information. • A decision coefficient is introduced to enhance the semantic information. • The step-wise relation deduction module can obtain vital semantic information. [ABSTRACT FROM AUTHOR]

Evidence proved that gestational ozone (O 3) exposure can increase the risk of neonatal adverse respiratory outcomes, but offspring asthma is unclear. This study aimed to investigate whether gestational O 3 exposure could exacerbate offspring asthma, and to research the differences in effects of O 3 exposure at different gestational periods on offspring asthma. The pregnant ICR mice were randomly grouped and were administered O 3 (air as control) at gestational day (GD) 1–6, 7–12, and 13–18, respectively. The pups aged 2–4 weeks were treated with ovalbumin (OVA) to establish a model of early life asthma. Asthma characteristics such as pulmonary inflammation, goblet cell proliferation, airway remodeling, OVA-specific immunoglobulin (Ig) E secretion and cytokines were examined. OVA sensitization and challenge successfully induced asthma in offspring. Compared with the air control, pulmonary inflammation infiltration, mucous secretion, the concentration of OVA-specific IgE, the level of tumor necrosis factor (TNF)-α, and T helper (Th) 2-skewed response were significantly exacerbated when O 3 exposure at GD13-18 following inhaling OVA, while pulmonary inflammatory infiltration, mucus secretion, and Th2-skewed response were not significantly changed when O 3 exposure at both GD1-6 and GD7-12. What's more, the above indicators in asthmatic offspring due to O 3 exposure at GD13-18 were more severe than at GD1-6 and GD7-12. Interestingly, the signs of asthma only appeared in the offspring after OVA inhalation. When offspring were not treated with OVA, the prenatal O 3 exposure alone did not lead to asthmatic reactions in offspring. In addition, O 3 exposure at GD13-18 markedly increased the number of neutrophils and macrophages in Bronchoalveolar Lavage Fluid (BALF) of asthmatic offspring, and significantly exacerbated Th2 immune imbalance in asthmatic offspring, but had no effect on Th17 immune imbalance. Exposure to O 3 during pregnancy aggravated asthma in offspring, in which the third trimester is the most sensitive window. Image 1 • Exposure to O 3 during pregnancy exacerbated OVA-induced asthma in offspring. • The third trimester was the sensitive window for O 3 transgenerational toxicity. • Neutrophil and macrophage infiltration was the main feature in offspring asthma. • Th1/Th2 immune imbalance in asthmatic offspring was exacerbated. • The model of offspring asthma in early life was established and applied. Capsule: Exposure to O 3 during pregnancy aggravated OVA-induced asthma in offspring, in which the third trimester is the most sensitive window. [ABSTRACT FROM AUTHOR]

Artificial intelligence based on deep learning is better at improving the representation ability of models from data. However, due to the limitation of fixed receptive field, these agents are not able to provide a correct response outside the fixed receptive field. To address this problem, this paper provides a new perspective with improving the Image Recognition tasks. This study firstly constructs two extended receptive fields using structural causal model. Then, an approximate intervention method that changes the traditional likelihood prediction to predict the result of causal intervention is proposed. Finally, this study formulates the objective function to adapt the proxy training, which makes the whole model work well. Above all of these, a new Vision Transformer variant named Causal-ViT is proposed. Furthermore, rich experimental results of different tasks are reported. These results show that the proposed perspective makes a significant improvement in Image Recognition tasks. By simply plugging Causal-ViT to different sub-tasks, all of them bring the new benchmarks of themselves field, which proves our method is flexible. • The structural causal model is introduced for removing observation bias. • The external knowledge is incorporated into causal intervention processing. • A fusion module is designed for adapting original features and causality context. • This study conducts rich experiments and achieves new SOTA in most benchmarks. [ABSTRACT FROM AUTHOR]

Objectives To investigate the occurrence of antibiotic residues in different types of environmental samples including water samples in rural Shandong province, China. Further, to characterize the potential ecological risk for development of antibiotic resistance in the environment, and the potential direct human health risk of exposure to antibiotics via drinking water and vegetables. Methods Environmental samples ( n  = 214) (river water, waste water, drinking water, sediments, manure, soil and edible parts of vegetables) were collected in twelve villages in Shandong province in eastern China. High performance liquid chromatography–tandem mass spectrometry (HPLC–MS/MS) was used to determine the concentration of antibiotic residues. The ratio of the measured environmental concentrations (MEC) to the predicted no-effect concentrations (PNEC) was used to evaluate the ecological risk (risk quotient, RQ) for development of antibiotic resistance. The potential risks to human health through exposure to antibiotics in drinking water were assessed by comparing measured environmental concentrations (MEC) and predicted no-effect concentration in drinking water (PNEC DW ), and in vegetables by comparing estimated daily intake (EDI) to ADI. Results Sulfapyridine, sulfamethoxazole, ciprofloxacin, enrofloxacin, levofloxacin, norfloxacin, chloramphenicol, florfenicol, doxycycline, and metronidazole were detected at concentrations ranging between 0.3 and 3.9 ng/L in river water, 1.3 and 12.5 ng/L in waste water, 0.5 and 21.4 ng/L in drinking water, 0.31 and 1.21 μg/kg in river sediment, 0.82 and 1.91 μg/kg in pig manure, 0.1 and 11.68 μg/kg in outlet sediment, 0.5 and 2.5 μg/kg in soil, and 6.3 and 27.2 μg/kg in vegetables. The RQs for resistance development were >1 for enrofloxacin, levofloxacin, and ranged between 0.1 and 1 for ciprofloxacin. MECs/PNEC DW ratios were <1 from exposure to antibiotics through drinking water for both adults and children. EDI/ADI ratios were <0.1 from exposure to antibiotics by vegetable consumption. Conclusions Antibiotic pollutants were ubiquitous in various environmental compartments of Shandong province of China. Risk estimates indicated a potential for the measured levels of enrofloxacin, levofloxacin and ciprofloxacin in waste water to pose an ecological risk for resistance selection, and further studies are needed to validate this finding. The investigated antibiotics did not appear to pose an appreciable direct human health risk from environmental exposure through drinking water or vegetables consumption. However, they might still pose a risk for resistance development. [ABSTRACT FROM AUTHOR]