[1] The total zenith tropospheric delay (ZTD) is an important parameter of the atmosphere and directly or indirectly reflects the weather and climate processes and variations. In this paper the ZTD time series with a 2-hour resolution are derived from globally distributed 150 International GPS Service (IGS) stations (1994)(1995)(1996)(1997)(1998)(1999)(2000)(2001)(2002)(2003)(2004)(2005)(2006), which are used to investigate the secular trend and seasonal variation of ZTD as well as its implications in climate. The mean secular ZTD variation trend is about 1.5 ± 0.001 mm/yr at all IGS stations. The secular variations are systematically increasing in most parts of the Northern Hemisphere and decreasing in most parts of the Southern Hemisphere. Furthermore, the ZTD trends are almost symmetrically decreasing with increasing altitude, while the summation of upward and downward trends at globally distributed GPS sites is almost zero, possibly reflecting that the secular ZTD variation is in balance at a global scale. Significant annual variations of ZTD are found over all GPS stations with the amplitude from 25 to 75 mm. The annual variation amplitudes of ZTD near oceanic coasts are generally larger than in the continental inland. Larger amplitudes of annual ZTD variation are mostly found at middle latitudes (near 20°S and 40°N) and smaller amplitudes of annual ZTD variation are located at higher latitudes (e.g., Antarctic) and the equator areas. The phase of annual ZTD variation is about 60°in the Southern Hemisphere (about February, summer) and about 240°in the Northern Hemisphere (about August, summer). The mean amplitude of semiannual ZTD variations is about 10 mm, much smaller than annual variations. The semiannual amplitudes are larger in the Northern Hemisphere than in the Southern Hemisphere, indicating that the semiannual variation amplitudes of ZTD in the Southern Hemisphere are not significant. In addition, the higher-frequency variability (RMS of ZTD residuals) ranges from 15 to 65 mm of delay, depending on altitude of the station. Inland stations tend to have lower variability and sites at ocean and coasts have higher variability. These seasonal ZTD cycles are due mainly to the wet component variations (ZWD).

In this study, we propose a method for the automated detection of obstructive sleep apnea (OSA) from a single-lead electrocardiogram (ECG) using a convolutional neural network (CNN). A CNN model was designed with six optimized convolution layers including activation, pooling, and dropout layers. One-dimensional (1D) convolution, rectified linear units (ReLU), and max pooling were applied to the convolution, activation, and pooling layers, respectively. For training and evaluation of the CNN model, a single-lead ECG dataset was collected from 82 subjects with OSA and was divided into training (including data from 63 patients with 34,281 events) and testing (including data from 19 patients with 8571 events) datasets. Using this CNN model, a precision of 0.99%, a recall of 0.99%, and an F-score of 0.99% were attained with the training dataset; these values were all 0.96% when the CNN was applied to the testing dataset. These results show that the proposed CNN model can be used to detect OSA accurately on the basis of a single-lead ECG. Ultimately, this CNN model may be used as a screening tool for those suspected to suffer from OSA.

No abstract

Background In this study, we propose a method for automatically predicting atrial fibrillation (AF) based on convolutional neural network (CNN) using a short-term normal electrocardiogram (ECG) signal. Methods We designed a CNN model and optimized it by dropout and normalization. One-dimensional convolution, max-pooling, and fully-connected multiple perceptron were used to analyze the short-term normal ECG. The ECG signal was preprocessed and segmented to train and evaluate the proposed CNN model. The training and test sets consisted of the two AF and one normal dataset from the MIT-BIH database. Results The proposed CNN model for the automatic prediction of AF achieved a high performance with a sensitivity of 98.6%, a specificity of 98.7%, and an accuracy of 98.7%. Conclusion The results show the possibility of automatically predicting AF based on the CNN model using a short-term normal ECG signal. The proposed CNN model for the automatic prediction of AF can be a helpful tool for the early diagnosis of AF in healthcare fields.

Thus, proposed deep learning architecture achieved a high performance for multiclass classification of OSAH using single-lead ECG recordings. The proposed method can be employed in screening of patients suspected of having OSAH.