Single image dehazing has always been a challenging problem in the field of computer vision. Traditional image defogging methods use manual features. With the development of artificial intelligence, the defogging method based on deep learning has developed rapidly. In this paper, we propose a novel image defogging approach called NIN-DehazeNet for single image. This method estimates the transmission map by NIN-DehazeNet combining Network-in-Network with MSCNN(Single Image Dehazing via Multi-Scale Convolutional Neural Networks). In the test stage, we estimate the transmission map of the input hazy image based on the trained model, and then generate the dehazed image using the estimated atmospheric light and computed transmission map. Extensive experiments have shown that the proposed algorithm overperformance traditional methods. INDEX TERMS Single image dehazing, manual features, deep learning, NIN-DehazeNet, Network-in-Network, multi-scale convolutional neural networks,atmospheric scattering model.
Objective. Constructing an efficient human emotion recognition model based on electroencephalogram (EEG) signals is of great significance for realizing emotional brain computer interaction and improving machine intelligence. Approach. In this paper, we present a spatial-temporal feature fused convolutional graph attention network (STFCGAT) model based on multi-channel EEG signals for human emotion recognition. First, we combined the single-channel differential entropy (DE) feature with the cross-channel functional connectivity (FC) feature to extract both the temporal variation and spatial topological information of EEG. After that, a novel convolutional graph attention network was used to fuse the DE and FC features and further extract higher-level graph structural information with sufficient expressive power for emotion recognition. Furthermore, we introduced a multi-headed attention mechanism in graph neural networks to improve the generalization ability of the model. Main results. We evaluated the emotion recognition performance of our proposed model on the public SEED and DEAP datasets, which achieved a classification accuracy of 99.11±0.83% and 94.83±3.41% in subject-dependent and subject-independent experiments on SEED dataset, and achieved an accuracy of 91.19±1.24% and 92.03±4.57% for discrimination of arousal and valence in subject-independent experiments on DEAP dataset. Notably, our model achieved state-of-the-art (SOTA) performance on cross-subject emotion recognition task for both datasets. In addition, we gained an insight into the proposed frame by both the ablation experiments and the analysis of spatial patterns of FC and DE features. Significance. All these results prove the effectiveness of the STFCGAT architecture for emotion recognition and also indicate that there are significant differences in the spatial-temporal characteristics of the brain under different emotional states.
IMPORTANCEThe monoclonal antibody combination of casirivimab and imdevimab reduced viral load, hospitalization, or death when administered as a 1200-mg or greater intravenous (IV) dose in a phase 3 COVID-19 outpatient study. Subcutaneous (SC) and/or lower IV doses should increase accessibility and/or drug supplies for patients. OBJECTIVE To assess the virologic efficacy of casirivimab and imdevimab across different IV and SC doses compared with placebo. DESIGN, SETTING, AND PARTICIPANTS This phase 2, randomized, double-blind, placebocontrolled, parallel-group, dose-ranging study included outpatients with SARS-CoV-2 infection at 47 sites across the United States. Participants could be symptomatic or asymptomatic; symptomatic patients with risk factors for severe COVID-19 were excluded. Data were collected from December 15, 2020, to March 4, 2021. INTERVENTIONS Patients were randomized to a single IV dose (523 patients) of casirivimab and imdevimab at 300, 600, 1200, or 2400 mg or placebo; or a single SC dose (292 patients) of casirivimab and imdevimab at 600 or 1200 mg or placebo. MAIN OUTCOMES AND MEASURES The primary end point was the time-weighted average daily change from baseline (TWACB) in viral load from day 1 (baseline) through day 7 in patients seronegative for SARS-CoV-2 at baseline. RESULTS Among 815 randomized participants, 507 (282 randomized to IV treatment, 148 randomized to SC treatment, and 77 randomized to placebo) were seronegative at baseline and included in the primary efficacy analysis. Participants randomized to IV had a mean (SD) age of 34.6 (9.6) years (160 [44.6%] men; 14 [3.9%] Black; 121 [33.7%] Hispanic or Latino; 309 [86.1%] White); those randomized to SC had a mean age of 34.1 (10.0) years (102 [45.3%] men; 75 [34.7%] Hispanicor Latino; 6 [2.7%] Black; 190 [84.4%] White). All casirivimab and imdevimab treatments showed significant virologic reduction through day 7. Least-squares mean differences in TWACB viral load for casirivimab and imdevimab vs placebo ranged from -0.56 (95% CI; -0.89 to -0.24) log 10 copies/mL for the 1200-mg IV dose to -0.71 (95% CI, -1.05 to -0.38) log 10 copies/mL for the 2400-mg IV dose. There were no adverse safety signals or dose-related safety findings, grade 2 or greater infusionrelated or hypersensitivity reactions, grade 3 or greater injection-site reactions, or fatalities. Two serious adverse events not related to COVID-19 or the study drug were reported.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.