In modern society, air pollution is an important topic as this pollution exerts a critically bad influence on human health and the environment. Among air pollutants, Particulate Matter (PM2.5) consists of suspended particles with a diameter equal to or less than 2.5 μm. Sources of PM2.5 can be coal-fired power generation, smoke, or dusts. These suspended particles in the air can damage the respiratory and cardiovascular systems of the human body, which may further lead to other diseases such as asthma, lung cancer, or cardiovascular diseases. To monitor and estimate the PM2.5 concentration, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are combined and applied to the PM2.5 forecasting system. To compare the overall performance of each algorithm, four measurement indexes, Mean Absolute Error (MAE), Root Mean Square Error (RMSE) Pearson correlation coefficient and Index of Agreement (IA) are applied to the experiments in this paper. Compared with other machine learning methods, the experimental results showed that the forecasting accuracy of the proposed CNN-LSTM model (APNet) is verified to be the highest in this paper. For the CNN-LSTM model, its feasibility and practicability to forecast the PM2.5 concentration are also verified in this paper. The main contribution of this paper is to develop a deep neural network model that integrates the CNN and LSTM architectures, and through historical data such as cumulated hours of rain, cumulated wind speed and PM2.5 concentration. In the future, this study can also be applied to the prevention and control of PM2.5.

Abstract:One of the most important research topics in smart grid technology is load forecasting, because accuracy of load forecasting highly influences reliability of the smart grid systems. In the past, load forecasting was obtained by traditional analysis techniques such as time series analysis and linear regression. Since the load forecast focuses on aggregated electricity consumption patterns, researchers have recently integrated deep learning approaches with machine learning techniques. In this study, an accurate deep neural network algorithm for short-term load forecasting (STLF) is introduced. The forecasting performance of proposed algorithm is compared with performances of five artificial intelligence algorithms that are commonly used in load forecasting. The Mean Absolute Percentage Error (MAPE) and Cumulative Variation of Root Mean Square Error (CV-RMSE) are used as accuracy evaluation indexes. The experiment results show that MAPE and CV-RMSE of proposed algorithm are 9.77% and 11.66%, respectively, displaying very high forecasting accuracy.

The present study examined the association of specific virus infections with acute respiratory tract conditions among hospitalized and outpatient children in a subtropical country. A total of 2,295 virus infections were detected in 6,986 patients between 1997 and 1999, including infections caused by respiratory syncytial virus (RSV) (1.7%), parainfluenza virus (2.0%), influenza B virus (2.6%), adenovirus (4.0%), herpes simplex virus type 1 (4.4%), influenza A virus (5.5%), and enterovirus (12.7%). There were 61 mixed infections, and no consistent seasonal variation was found. One or more viruses were detected among 24.8% of hospitalized patients and 35.0% of outpatients. The frequencies and profiles of detection of various viruses among in-and outpatients were different. The occurrence of enterovirus infections exceeded that of other viral infections detected in 1998 and 1999 due to outbreaks of enterovirus 71 and coxsackievirus A10. RSV was the most prevalent virus detected among hospitalized children, whereas influenza virus was the most frequently isolated virus in the outpatient group. Most respiratory viral infections (39.3%) occurred in children between 1 and 3 years old. RSV (P < 0.025) and influenza A virus (P < 0.05) infections were dominant in the male inpatient group. In addition, most pneumonia and bronchiolitis (48.4%) was caused by RSV among hospitalized children less than 6 months old. Adenovirus was the most common agent associated with pharyngitis and tonsilitis (45.5%). These data expand our understanding of the etiology of acute respiratory tract viral infections among in-and outpatients in a subtropical country and may contribute to the prevention and control of viral respiratory tract infections.Viruses, including respiratory syncytial virus (RSV), parainfluenza viruses, influenza viruses, adenoviruses, rhinoviruses, and enteroviruses, are a frequent cause of respiratory tract infections in children (2, 6, 11). In hospitalized children, RSV infections occur at greater frequency than other viral infections of the lower respiratory tract (1,7,15,23,28). Symptoms of RSV infections include coughing, wheezing, hypoxia, bronchiolitis, and pneumonia (18,21). Recently, several strategies for prophylaxis and treatment of RSV infection have been developed (8,20,21). Passive immunization using RSV immunoglobulin and monoclonal antibodies for prevention of RSV disease in premature infants have provided effective forms of prophylactic intervention for high-risk groups (8,20,21). A combination of RSV immunoglobulin and the antiviral agent ribavirin given to bone marrow transplant recipients infected with RSV has also been shown to result in higher survival compared to untreated patients (31). Influenza virus is the most frequent cause of acute respiratory illness, which results in local, regional or worldwide epidemics with various degrees of severity each year (16). Although the new antiviral drug zanamivir for influenza A and B and live attenuated intranasal influenza vaccine were shown to be highly eff...

Three new [n-pentyl beta-carboline-1-propionate (1), 5-hydroxymethyl-9-methoxycanthin-6-one (2), and 1-hydroxy-9-methoxycanthin-6-one (3)] and 19 known beta-carboline alkaloids were isolated from the roots of Eurycoma longifolia. The new structures were determined by comprehensive analyses of their 1D and 2D NMR and mass spectral data and by chemical transformation. These compounds were screened for in vitro cytotoxic and antimalarial activities, and 9-methoxycanthin-6-one (4) and canthin-6-one (5) demonstrated significant cytotoxicity against human lung cancer (A-549) and human breast cancer (MCF-7) cell lines.

Phytochemical investigation of Physalis angulata was initiated following primary biological screening. Fractionation of CHCl3 and n-BuOH solubles of the MeOH extract from the whole plant was guided by in vitro cytotoxic activity assay using cultured HONE-1 and NUGC cells and led to the isolation of seven new withanolides, withangulatins B-H (1-7), and a new minor physalin, physalin W (8), along with 14 known compounds, including physaprun A, withaphysanolide, dihydrowithanolide E, physanolide A, withaphysalin A, and physalins B, D, F, G, I, J, T, U, and V. New compounds (1-8) were fully characterized by a combination of spectroscopic methods (1D and 2D NMR and MS) and the relative stereochemical assignments based on NOESY correlations and analysis of coupling constants. Biological evaluation of these compounds against a panel of human cancer cell lines showed broad cytotoxic activity. Withangulatin B (1) and physalins D (10) and F (11) displayed potent cytotoxic activity against a panel of human cancer cell lines with EC50 values ranging from 0.2 to 1.6 microg/mL. Structure-activity relationship analysis indicated that withanolides and physalins with 4beta-hydroxy-2-en-1-one and 5beta,6beta-epoxy moieties are potential cytotoxic agents.

COVID-19 is spreading all across the globe. Up until March 23, 2020, the confirmed cases in 173 12 countries and regions of the globe had surpassed 346,000, and more than 14,700 deaths had resulted. The 13 confirmed cases outside of China had also reached over 81,000, with over 3,200 deaths. In this study, a 14 Convolutional Neural Network (CNN) was proposed to analyze and predict the number of confirmed cases. 15 Several cities with the most confirmed cases in China were the focus of this study, and a COVID-19 16 forecasting model, based on the CNN deep neural network method, was proposed. To compare the overall 17 efficacies of different algorithms, the indicators of mean absolute error and root mean square error were 18 applied in the experiment of this study. The experiment results indicated that compared with other deep 19 learning methods, the CNN model proposed in this study has the greatest prediction efficacy. The feasibility 20 and practicality of the model in predicting the cumulative number of COVID-19 confirmed cases were also 21 verified in this study.22

With the fast expansion of renewable energy system installed capacity in recent years, the availability, stability, and quality of smart grids have become increasingly important. The renewable energy output forecasting applications have also been developing rapidly in recent years, and such techniques have particularly been applied in the fields of wind and solar photovoltaic (PV). In the case of solar PV output forecasting, many applications have been performed with machine learning and hybrid techniques. In this paper, we propose a high-precision deep neural network model named PVPNet to forecast PV system output power. The methodology behind the proposed model is based on deep neural networks, and the model is able to generate a 24-h probabilistic and deterministic forecasting of PV power output based on meteorological information, such as temperature, solar radiation, and historical PV system output data. The forecasting accuracy of PVPNet is determined by the mean absolute error (MAE) and root mean square error (RMSE) values. The results from the experiments show that the MAE and RMSE of the proposed algorithm are 109.4845 and 163.1513, respectively. The results prove that the prediction accuracy of the PVPNet outperforms other benchmark models, and the algorithm also effectively predicts complex time series with a high degree of volatility and irregularity. INDEX TERMS Deep neural network, photovoltaic output power forecasting, photovoltaic system, renewable energy sources.

No abstract