Infectious disease occurs when a person is infected by a pathogen from another person or an animal. It is a problem that causes harm at both individual and macro scales. The Korea Center for Disease Control (KCDC) operates a surveillance system to minimize infectious disease contagions. However, in this system, it is difficult to immediately act against infectious disease because of missing and delayed reports. Moreover, infectious disease trends are not known, which means prediction is not easy. This study predicts infectious diseases by optimizing the parameters of deep learning algorithms while considering big data including social media data. The performance of the deep neural network (DNN) and long-short term memory (LSTM) learning models were compared with the autoregressive integrated moving average (ARIMA) when predicting three infectious diseases one week into the future. The results show that the DNN and LSTM models perform better than ARIMA. When predicting chickenpox, the top-10 DNN and LSTM models improved average performance by 24% and 19%, respectively. The DNN model performed stably and the LSTM model was more accurate when infectious disease was spreading. We believe that this study’s models can help eliminate reporting delays in existing surveillance systems and, therefore, minimize costs to society.

In this paper, we propose a real-time prediction model that can respond to particulate matters (PM) in the air, which are an indication of poor air quality. The model applies interpolation to air quality and weather data and then uses a Convolutional Neural Network (CNN) to predict PM concentrations. The interpolation transforms the irregular spatial data into an equally spaced grid, which the model requires. This combination creates the interpolated CNN (ICNN) model that we use to predict PM10 and PM2.5 concentrations. The PM10 and PM2.5 evaluation results show an effective prediction performance with an R-squared higher than 0.97 and a root mean square error (RMSE) of approximately 16% of the standard deviation. Furthermore, both PM10 and PM2.5 prediction models forecast high concentrations with high reliability, with a probability of detection higher than 0.90 and a critical success index exceeding 0.85. The proposed ICNN prediction model achieves a high prediction performance using spatio-temporal information and presents a new direction in the prediction field.

No abstract

earthquakes are natural disasters that cause damage in a wide range of regions and represent a complex system that does not have a clear causal relationship with specific observable factors. This research analyzes the earthquake activities on the Korean peninsula with respect to spatial and temporal factors. Using logarithmic regression analysis, we showed that the relationship between the location of the earthquake and its frequency in these locations follows a power law distribution. In addition, we showed that since 1998 the average earthquake magnitude has decreased from 3.0143 to 2.5433 and the frequency has risen by 3.98 times. Finally, the spatial analysis revealed significantly concentrated earthquake activities in a few particular areas and showed that earthquake occurrence points have shifted southeast. This research showed the change in earthquake dynamics and concentration of earthquake activities in particular regions over time. This finding implies the necessity of further research on spatially-derived earthquake policies on the change of earthquake dynamics. Damage caused by earthquakes is difficult to predict 1 because they are a complex system that cause new phenomena and disorder through interaction between its components 2-4. This complex system can be found in both social 5-7 and natural 8-11 phenomena, and there are studies analyzing such complex systems using the power law 12-15 and complex networks 16-21. Therefore, to investigate the earthquake phenomena of the Korean Peninsula, this study examines the change of earthquake patterns with time and the distribution of the power law according to space and magnitude. The selected region for this research, the Korean Peninsula, is located in the stable intraplate region of East Asia 22. With an average of 41.65 earthquakes stronger than M L 2 by year, it is considered a relatively safe area in terms of earthquakes 23. However, in 2016 and 2017, the number of earthquakes stronger than M L 2 in the Korean Peninsula, was 254 and 223, respectively. Moreover, on September 12th, 2016, an M L 5.8 earthquake occurred in Gyeongju, Gyeongsang-do Province, being recorded as the strongest earthquake so far. On November 15th, 2017, an M L 5.4 earthquake occurred in Pohang, Gyeongsang-do Province, the second strongest earthquake in Korea. They caused the greatest social and economic damage compared to all past earthquakes in the Korean Peninsula 24. These consecutive strong earthquakes have increased public interest in earthquakes 25. Various earthquake studies have been conducted to analyze their complexity. Omori validated the power law distribution between earthquakes 26 and their aftershocks, and Gutenberg proved that if the earthquake magnitude is small, the frequency increases in a constant ratio 27. Using identified earthquake power laws from previous studies, Serra and Corral compared the truncated gamma and tapered Gutenberg-Richter distributions to the simple Gutenberg-Richter power law distribution. They proved that truncated gamma distribution sho...

No abstract