Sleep stage classification is essential for sleep assessment and disease diagnosis. However, how to effectively utilize brain spatial features and transition information among sleep stages continues to be challenging. In particular, owing to the limited knowledge of the human brain, predefining a suitable spatial brain connection structure for sleep stage classification remains an open question. In this paper, we propose a novel deep graph neural network, named GraphSleepNet, for automatic sleep stage classification. The main advantage of the GraphSleepNet is to adaptively learn the intrinsic connection among different electroencephalogram (EEG) channels, represented by an adjacency matrix, thereby best serving the spatial-temporal graph convolution network (ST-GCN) for sleep stage classification. Meanwhile, the ST-GCN consists of graph convolutions for extracting spatial features and temporal convolutions for capturing the transition rules among sleep stages. Experiments on the Montreal Archive of Sleep Studies (MASS) dataset demonstrate that the GraphSleepNet outperforms the state-of-the-art baselines.
In this work, a sensitive electrochemical immunosensor has been reported for the determination of norfloxacin in animal-derived foods. The poly (amidoamine) dendrimer encapsulated gold nanoparticles (PAMAM-Au) played dual roles in the proposed sensing platform which not only accelerated the electron transfer process of sensing, but also increased the efficiency of the immobilized antibody. The HRP-labeled antigen, as the signal labels in the immunosensor, was introduced to catalyze the following reaction of the substrate hydroquinone with the aid of H2O2 in the competitive reaction. On the basis of the signal amplification of PAMAM-Au, the signal intensity was linearly related to the concentration of norfloxacin in the range of 1 μg·L−1–10 mg·L−1. All the results showed that the proposed strategy with low LOD (0.3837 μg·L−1) and favorable recovery (91.6–106.1%) in the practical sample, and it could provide a suitable protocol for norfloxacin detection in animal-derived foods with high sensitivity, good accuracy, and stability.
To understand the mechanism of delay propagation from the perspective of multiple airports, constructing delay propagation relation (DPR) networks among airports is a novel analysis method. The latest method is to use transfer entropy to mine the delay propagation relation among airports. However, the transfer entropy will produce bias due to estimating high-dimensional conditional mutual information (CMI) in the delay propagation scenario. In this paper, we propose the low-dimensional approximation of CMI for transfer entropy (LTE) to address the above issue. By applying this improved algorithm, the delay propagation relation among airports can be more accurately explored and a more accurate DPR network can be obtained. For this network, we apply the complex network theory and its related indicators to provide systematic analysis about delay propagation. The results of case analysis show that in the delay propagation interactions among airports, large airports always receive delays and small airports propagate delays outward. Meanwhile, delays propagate more efficiently in the aviation system of smaller airlines. These results can provide some theoretical supports for making measures to reduce delay propagation.INDEX TERMS Delay propagation relation, transfer entropy, flight delay, causality analysis, complex network.
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.