1 June 2011 in Journal of Biomedical Informatics
1 June 2011 in Journal of Biomedical Informatics
7 March 2018 in DEStech Transactions on Social Science, Education and Human Science
In this paper, we proposed a new hybrid ARIMA–RNN model to forecast stock price, the model based on moving average filter. This model can not only overcome the volatility problem of a single model, but also avoid the overfitting problem of neural network. We forecast stock price using ARIMA, RNN and ARIMA-RNN respectively, and we compare the value of MAE, MSE and MAPE of each model. We conclude that the hybrid ARIMA–RNN model has the best forecasting result.
22 May 2020 in Disaster Medicine and Public Health Preparedness
We investigated the adoption of World Health Organization (WHO) naming of COVID-19 into the respective languages among the Group of Twenty (G20) countries, and the variation of COVID-19 naming in the Chinese language across different health authorities. On May 7, 2020, we identified the websites of the national health authorities of the G20 countries to identify naming of COVID-19 in their respective languages, and the websites of the health authorities in mainland China, Hong Kong, Macau, Taiwan and Singapore and identify their Chinese name for COVID-19. Among the G20 nations, Argentina, China, Italy, Japan, Mexico, Saudi Arabia and Turkey do not use the literal translation of COVID-19 in their official language(s) to refer to COVID-19, as they retain “novel” in the naming of this disease. China is the only G20 nation that names COVID-19 a pneumonia. Among Chinese-speaking jurisdictions, Hong Kong and Singapore governments follow the WHO’s recommendation and adopt the literal translation of COVID-19 in Chinese. In contrast, mainland China, Macau, and Taiwan refer to COVID-19 as a type of pneumonia in Chinese. We urge health authorities worldwide to adopt naming in their native languages that are consistent with WHO’s naming of COVID-19.