An Recognition-Verification Mechanism for Real-Time Chinese Sign Language Recognition Based on Multi-Information Fusion.

For online sign language recognition (SLR) based on inertial measurement unit (IMU) and a surface electromyography (sEMG) sensor, achieving high-accuracy is a major challenge. The traditional method for that is the segmentation-recognition mechanism, which has two key challenges: (1) it is difficult to design a highly robust segmentation method for online data with inconspicuous segmentation information; and (2) the diversity of input data will increase the burden of the classification. The recognition-verification mechanism was proposed to improve the performance of online SLR. In the recognition stage, we used sliding windows to pull the data, and applied a convolutional neural network (CNN) to classify the sign language signal. In the verification stage, the confidence was evaluated by the Siamese network to judge the correctness of the classification results. The accuracy and rapidity of the classification model were discussed for 86 categories of Chinese sign language. In the experiments for online SLR, the superiority of the recognition-verification mechanism compared to the segmentation-recognition mechanism was verified.

A Locally Weighted Linear Regression Look-Up Table-Based Iterative Reconstruction Method for Dual Spectral CT.

OBJECTIVE: Compared with traditional computed tomography (CT), dual spectral CT (DSCT) exhibits superior material distinguishability and thus has broad prospects in industrial and medical fields. In iterative DSCT algorithms, accurately modeling forward-projection functions is crucial, but it is very difficult to analytically provide accurate functions. METHODS: In this article, we propose a locally weighted linear regression look-up table-based (LWLR-LUT) iterative reconstruction method for DSCT. First, the proposed method uses LWLR to establish LUTs for the forward-projection functions through calibration phantoms, achieving good local information calibration. Second, the reconstructed images can be iteratively obtained through the established LUTs. The proposed method not only does not require knowledge of the X-ray spectra and the attenuation coefficients, but also implicitly accounts for some scattered radiation while fitting locally the forward-projection functions in the calibration space. RESULTS: Both numerical simulations and real data experiments demonstrate that the proposed method can achieve highly accurate polychromatic forward-projection functions and greatly improve the quality of the images reconstructed from scattering-free and scattering projections. CONCLUSION: The proposed method is simple and practical, and achieves good material decomposition effects for objects with different complex structures through simple calibration phantoms.

Models to assess imported cases on the rebound of COVID-19 and design a long-term border control strategy in Heilongjiang Province, China.

Since the outbreak of COVID-19 in Wuhan, China in December 2019, it has spread quickly and become a global pandemic. While the epidemic has been contained well in China due to unprecedented public health interventions, it is still raging or not yet been restrained in some neighboring countries. Chinese government adopted a strict policy of immigration diversion in major entry ports, and it makes Suifenhe port in Heilongjiang Province undertook more importing population. It is essential to understand how imported cases and other key factors of screening affect the epidemic rebound and its mitigation in Heilongjiang Province. Thus we proposed a time switching dynamical system to explore and mimic the disease transmission in three time stages considering importation and control. Cross validation of parameter estimations was carried out to improve the credibility of estimations by fitting the model with eight time series of cumulative numbers simultaneous. Simulation of the dynamics shows that illegal imported cases and imperfect protection in hospitals are the main reasons for the second epidemic wave, the actual border control intensities in the province are relatively effective in early stage. However, a long-term border closure may cause a paradox phenomenon such that it is much harder to restrain the epidemic. Hence it is essential to design an effective border reopening strategy for long-term border control by balancing the limited resources on hotel rooms for quarantine and hospital beds. Our results can be helpful for public health to design border control strategies to suppress COVID-19 transmission.

Treatment Effect of Qingfei Paidu Decoction Combined With Conventional Treatment on COVID-19 Patients and Other Respiratory Diseases: A Multi-Center Retrospective Case Series.

Background: Qingfei Paidu decoction (QFPDD) has been widely used in treating coronavirus disease 2019 (COVID-19) in China. However, studies on the treatment effect of COVID-19 patients and other respiratory diseases have not been well demonstrated. Our study aims to determine the treatment effect of QFPDD in combination with conventional treatment on COVID-19 patients and other respiratory diseases. Methods: This retrospective study recruited COVID-19 patients who were treated with QFPDD for at least two courses (6 days) from seven hospitals in five provinces from January 21 to March 18 2020. Demographic, epidemiological, clinical, laboratory, computed tomography characteristics, treatment, and outcome data were collected and analyzed. The improvements in clinical symptoms before and after QFPDD treatment were compared. Results: Eight COVID-19 patients were included in this study. Of them, six were males (75.0%). The median age of the patients was 66 (60-82) years. Four patients were classified as mild and moderate cases (50.0%); there were two severe cases (25.0%) and critical cases (25.0%). The most common symptom was cough (7 [87.5%]), followed by fever (6 [75.0%]), fatigue (4 [50.0%]), asthma (4 [50.0%]), and anorexia (3 [37.5%]). Abnormal findings included decrease in neutrophils (3 [37.5%]), lymphocytes (2 [25.0%]), alkaline phosphatase (3 [37.5%]), lactic dehydrogenase (4 [50.0%]), erythrocyte sedimentation rate (2 [25.0%]), and C-reactive protein (5 [83.3%]) at admission. After one course (3 days) of QFPDD, nasal obstruction and sore throat completely disappeared, and fever (5 [83.3%]), fatigue (2 [50.0%]), and cough (2 [28.6%]) were improved. After two courses (6 days), the fever disappeared completely in all patients, and the other symptoms showed a tendency to improve. In non-severe patients, 87.5% baseline symptoms completely disappeared. In severe patients, 61.1% of the baseline symptoms completely disappeared after patients were administered QFPDD for two courses. Of the abnormal indicators, 55.6% returned to normal levels. The median duration to complete fever recovery was 1.0 day. The median durations of viral shedding and hospitalization were 10.5 and 21.5 days, respectively. None of the patients worsened and died, and no serious adverse events occurred related to QFPDD during hospitalization. Conclusion: QFPDD combined with conventional treatment improved clinical symptoms in COVID-19 patients with other respiratory diseases, and no serious adverse reactions associated with QFPDD were observed. Larger sample studies confirm our findings in the future.

An iterative reconstruction method based on monochromatic images for dual energy CT.

PURPOSE: Dual-energy computed tomography (DECT) scans objects using two different X-ray spectra to acquire more information, which is also called dual spectral CT (DSCT) in some articles. Compared to traditional CT, DECT exhibits superior material distinguishability. Therefore, DECT can be widely used in the medical and industrial domains. However, owing to the nonlinearity and ill condition of DECT, studies are underway on DECT reconstruction to obtain high quality images and achieve fast convergence speed. Therefore, in this study, we propose an iterative reconstruction method based on monochromatic images (IRM-MI) to rapidly obtain high-quality images in DECT reconstruction. METHODS: An IRM-MI is proposed for DECT. The proposed method converts DECT reconstruction problem from the basis material images decomposition to monochromatic images decomposition to significantly improve the convergence speed of DECT reconstruction by changing the coefficient matrix of the original equations to increase the angle of the high- and low-energy projection curves or reduce the condition number of the coefficient matrix. The monochromatic images were then decomposed into basis material images. Furthermore, we conducted numerical experiments to evaluate the performance of the proposed method. RESULTS: The decomposition results of the simulated data and real data experiments confirmed the effectiveness of the proposed method. Compared to the extended algebraic reconstruction technique (E-ART) method, the proposed method exhibited a significant increase in the convergence speed by increasing the angle of polychromatic projection curves or decreasing the condition number of the coefficient matrix, when choosing the appropriate monochromatic images. Therefore, the proposed method is also advantageous in acquiring high quality and rapidly converged images. CONCLUSIONS: We developed an iterative reconstruction method based on monochromatic images for the material decomposition for DECT. The numerical experiments using the proposed method validated its capability of decomposing the basis material images. Furthermore, the proposed method achieved faster convergence speed compared to the E-ART method.

An oblique projection modification technique (OPMT) for fast multispectral CT reconstruction.

In x-ray multispectral (or photon-counting) computed tomography (MCT), the object of interest is scanned under multiple x-ray spectra, and it can acquire more information about the scanned object than conventional CT, in which only one x-ray spectrum is used. The obtained polychromatic projections are utilized to perform material-selective and energy-selective image reconstruction. Compared with the conventional single spectral CT, MCT has a superior material distinguishability. Therefore, it has wide potential applications in both medical and industrial areas. However, the nonlinearity and ill condition of the MCT problem make it difficult to get high-quality and fast convergence of images for existing MCT reconstruction algorithms. In this paper, we proposed an iterative reconstruction algorithm based on an oblique projection modification technique (OPMT) for fast basis material decomposition of MCT. In the case of geometric inconsistency, along the current x-ray path, the oblique projection modification direction not only relates to the polychromatic projection equation of the known spectrum, but it also comprehensively refers to the polychromatic projection equation information of the unknown spectra. Moreover, the ray-by-ray correction makes it applicable to geometrically consistent projection data. One feature of the proposed algorithm is its fast convergence speed. The OPMT considers the information from multiple polychromatic projection equations, which greatly speeds up the convergence of MCT reconstructed images. Another feature of the proposed algorithm is its high flexibility. The ray-by-ray correction will be suitable for any common MCT scanning mode. The proposed algorithm is validated with numerical experiments from both simulated and real data. Compared with the ASD-NC-POCS and E-ART algorithms, the proposed algorithm achieved high-quality reconstructed images while accelerating the convergence speed of them.

Theoretical investigation on the structure and thermodynamic properties of the 2,4-dinitroimidazole complex with methanol.

The structure and thermodynamic properties of the 2, 4-dinitroimidazole complex with methanol were investigated using the B3LYP and MP2(full) methods with the 6-31++G(2d,p) and 6-311++G(3df,2p) basis sets. Four types of hydrogen bonds [N-H⋯O, C-H⋯O, O-H⋯O (nitro oxygen) and O-H⋯π] were found. The hydrogen-bonded complex having the highest binding energy had a N-H⋯O hydrogen bond. Analyses of natural bond orbital (NBO) and atoms-in-molecules (AIM) revealed the nature of the intermolecular hydrogen-binding interaction. The changes in thermodynamic properties from monomers to complexes with temperatures ranging from 200.0 to 800.0 K were investigated using the statistical thermodynamic method. Hydrogen-bonded complexes of 2,4-dinitroimidazole with methanol are fostered by low temperatures.