Water quality forecasting based on data decomposition, fuzzy clustering and deep learning neural network.

Water quality forecasting can provide useful information for public health protection and support water resources management. In order to forecast water quality more accurately, this paper proposes a novel hybrid model by combining data decomposition, fuzzy C-means clustering and bidirectional gated recurrent unit. Firstly, the original water quality data is decomposed into several subseries by empirical wavelet transform, and then, the decomposed subseries are recombined by fuzzy C-means clustering. Next, for each clustered series, bidirectional gated recurrent unit is applied to develop prediction model. Finally, the forecast result is obtained by the summation of the predictions for the subseries. The proposed forecast model is evaluated by the water quality data of Poyang Lake, China. Results show that the proposed forecast model provides highly accurate forecast result for all of the six water quality data: the average of MAPE of the forecast results for the six water quality datasets is 4.59% for 7 day ahead prediction. Furthermore, our model shows better forecast performance than the other models. Particularly, compared with the single BiGRU model, MAPE decreased by 32.86% in average. Results demonstrate that the proposed forecast model can be used effectively for water quality forecasting.

Crystallographic Orientation Analysis of Nanocrystalline Tungsten Thin Film Using TEM Precession Electron Diffraction and SEM Transmission Kikuchi Diffraction.

Two advanced, automated crystal orientation mapping techniques suited for nanocrystalline materials­precession electron diffraction (PED) in transmission electron microscopy (TEM) and on-axis transmission Kikuchi diffraction (TKD) in scanning electron microscopy (SEM)­are evaluated by comparing the orientation maps obtained from the identical location on a 30 nm-thick nanocrystalline tungsten (W) thin film. A side-by-side comparison of the orientation maps directly showed that the large-scale orientation features are almost identical. However, there are differences in the fine details, which arise from the fundamentally different nature of the spot pattern and Kikuchi line pattern in terms of the excitation volume and the angular resolution. While TEM-PED is more reliable to characterize grains oriented along low-index zone axes, the high angular resolution of SEM-TKD allows the detection of small misorientation between grains and thus yields better quantification and statistical analysis of grain orientation. Given that both TEM-PED and SEM-TKD orientation mapping techniques are complementary tools for nanocrystalline materials, one can be favorably selected depending on the requirements of the analysis, as they have competitive performance in terms of angular resolution and texture quantification.

The evolution of electrocardiographic changes in patients with Duchenne muscular dystrophies.

PURPOSE: Myocardial dysfunction and dysrhythmias are inevitable consequences of Duchenne muscular dystrophy. We aimed to evaluate specific trends of electrocardiographic changes that reflect the progress of cardiomyopathy in patients with Duchenne muscular dystrophy. METHODS: Fifty electrocardiograms (ECGs) of 30 patients (ages 1 to 27 years) who had not been prescribed medications for heart failure treatment at the time of examination were retrospectively analyzed and compared with 116 ECGs of age-matched healthy 116 controls. Heart rate, leads with fragmented QRS (fQRS), corrected QT, Tpeak-to-Tend, and Tpeak-to-Tend/QT were analyzed. RESULTS: The patients with Duchenne muscular dystrophy failed to show a normal age-related decline in heart rate but showed an increasing trend in the prevalence of fQRS, corrected QT, corrected Tpeak-to-Tend, and Tpeak-to-Tend/QT over time. In the ≤10-year-old patient group, a significant difference was found only in the prevalence of fQRS between the patients and the controls. The prevalence of fQRS, heart rate, Tpeak-to-Tend/QT, and corrected Tpeak-to-Tend demonstrated significant differences between the patients and the controls in the middle age group (11 to 15 years old). All the indexes were statistically significantly different in the ≥16-year-old patient group. CONCLUSION: The prevalence of lead with fQRS representing regional wall motion abnormalities was higher in the young patients than in the young healthy controls, and this might be one of the first signs of myocardial change in the patients. Markers of depolarization and repolarization abnormalities were gradually prominent in the patients aged >10 years. Further studies are needed to confirm these findings.