Background Market-applicable concurrent electrocardiogram (ECG) diagnosis for multiple heart abnormalities that covers a wide range of arrhythmias, with better-than-human accuracy, has not yet been developed. We therefore aimed to engineer a deep learning approach for the automated multilabel diagnosis of heart rhythm or conduction abnormalities by real-time ECG analysis. MethodsWe used a dataset of ECGs (standard 10 s, 12-channel format) from adult patients (aged ≥18 years), with 21 distinct rhythm classes, including most types of heart rhythm or conduction abnormalities, for the diagnosis of arrhythmias at multilabel level. The ECGs were collected from three campuses of Tongji Hospital (Huazhong University of Science and Technology, Wuhan, China) and annotated by cardiologists. We used these datasets to develop a convolutional neural network approach to generate diagnoses of arrythmias. We collected a test dataset of ECGs from a new group of patients not included in the training dataset. The test dataset was annotated by consensus of a committee of board-certified, actively practicing cardiologists. To evaluate the performance of the model we assessed the F1 score and the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, as well as quantifying sensitivity and specificity. To validate our results, findings for the test dataset were compared with diagnoses made by 53 ECG physicians working in cardiology departments who had a wide range of experience in ECG interpretation (range 0 to >12 years). An external public validation dataset of 962 ECGs from other hospitals was used to study generalisability of the diagnostic model.

We have theoretically investigated the reflectivity spectrums of single- and double-layer photonic crystal slabs and the dielectric multilayer stack. It is shown that light can be perfectly confined in a single-layer photonic crystal slab at a given incident angle by changing the thickness, permittivity or hole radius of the structure. With a tunable double-layer photonic crystal slab, we demonstrate that the occurrence of tunable bound states in the continuum is dependent on the spacing between two slabs. Moreover, by analytically investigating the Drude lossless multilayer stack model, the spacing dependence of bound states in the continuum is characterized as the phase matching condition that illuminates these states can occur at any nonzero incident angles by adjusting the spacing.

No abstract

No abstract

In this paper, a novel uneven-layered coding metamaterial tile is proposed for ultra-wideband radar cross section (RCS) reduction and diffuse scattering. The metamaterial tile is composed of two kinds of square ring unit cells with different layer thickness. The reflection phase difference of 180° (±37°) between two unit cells covers an ultra-wide frequency range. Due to the phase cancellation between two unit cells, the metamaterial tile has the scattering pattern of four strong lobes deviating from normal direction. The metamaterial tile and its 90-degree rotation can be encoded as the ‘0’ and ‘1’ elements to cover an object, and diffuse scattering pattern can be realized by optimizing phase distribution, leading to reductions of the monostatic and bi-static RCSs simultaneously. The metamaterial tile can achieve −10 dB RCS reduction from 6.2 GHz to 25.7 GHz with the ratio bandwidth of 4.15:1 at normal incidence. The measured and simulated results are in good agreement and validate the proposed uneven-layered coding metamaterial tile can greatly expanding the bandwidth for RCS reduction and diffuse scattering.