Many studies have attempted to predict chlorophyll-a concentrations using multiple regression models and validating them with a hold-out technique. In this study commonly used machine learning models, such as Support Vector Regression, Bagging, Random Forest, Extreme Gradient Boosting (XGBoost), Recurrent Neural Network (RNN), and Long–Short-Term Memory (LSTM), are used to build a new model to predict chlorophyll-a concentrations in the Nakdong River, Korea. We employed 1–step ahead recursive prediction to reflect the characteristics of the time series data. In order to increase the prediction accuracy, the model construction was based on forward variable selection. The fitted models were validated by means of cumulative learning and rolling window learning, as opposed to the hold–out technique. The best results were obtained when the chlorophyll-a concentration was predicted by combining the RNN model with the rolling window learning method. The results suggest that the selection of explanatory variables and 1–step ahead recursive prediction in the machine learning model are important processes for improving its prediction performance.

The relationship between temperature and myocardial infarction has not been fully explained. In this study, we identified the threshold temperature and examined the relationship between temperature and emergency admissions due to MI in Korea. Poisson generalized additive model analyses were used to assess the short-term effects of temperature (mean, maximum, minimum, diurnal) on MI emergency visits, after controlling for meteorological variable and air pollution (PM10, NO₂). We defined the threshold temperature when the inflection point showed a statistically significant difference in the regression coefficients of the generalized additive models (GAMs) analysis. The analysis was performed on the following subgroups: geographical region, gender, age (<75 years or ≥75 years), and MI status (STEMI or non-STEMI). The threshold temperatures during heat exposure were for the maximum temperature as 25.5–31.5°C and for the mean temperature as 27.5–28.5°C. The threshold temperatures during cold exposure were for the minimum temperature as −2.5–1.5°C. Relative risks (RRs) of emergency visits above hot temperature thresholds ranged from 1.02 to 1.30 and those below cold temperature thresholds ranged from 1.01 to 1.05. We also observed increased RRs ranged from 1.02 to 1.65 of emergency visits when temperatures changes on a single day or on successive days. We found a relationship between temperature and MI occurrence during both heat and cold exposure at the threshold temperature. Diurnal temperature or temperature change on successive days also increased MI risk.

This study aims to compare the classification performance of statistical models on highly imbalanced kidney data. The health examination cohort database provided by the National Health Insurance Service in Korea is utilized to build models with various machine learning methods. The glomerular filtration rate (GFR) is used to diagnose chronic kidney disease (CKD). It is calculated using the Modification of Diet in Renal Disease method and classified into five stages (1, 2, 3A and 3B, 4, and 5). Different CKD stages based on the estimated GFR are considered as six classes of the response variable. This study utilizes two representative generalized linear models for classification, namely, multinomial logistic regression (multinomial LR) and ordinal logistic regression (ordinal LR), as well as two machine learning models, namely, random forest (RF) and autoencoder (AE). The classification performance of the four models is compared in terms of accuracy, sensitivity, specificity, precision, and F1-Measure. To find the best model that classifies CKD stages correctly, the data are divided into a 10-fold dataset with the same rate for each CKD stage. Results indicate that RF and AE show better performance in accuracy than the multinomial and ordinal LR models when classifying the response variable. However, when a highly imbalanced dataset is modeled, the accuracy of the model performance can distort the actual performance. This occurs because accuracy is high even if a statistical model classifies a minority class into a majority class. To solve this problem in performance interpretation, we not only consider accuracy from the confusion matrix but also sensitivity, specificity, precision, and F-1 measure for each class. To present classification performance with a single value for each model, we calculate the macro-average and micro-weighted values for each model. We conclude that AE is the best model classifying CKD stages correctly for all performance indices.

Most previous studies have focused on the association between acute myocardial function (AMI) and temperature by gender and age. Recently, however, concern has also arisen about those most susceptible to the effects of temperature according to socioeconomic status (SES). The objective of this study was to determine the effect of heat and cold on hospital admissions for AMI by subpopulations (gender, age, living area, and individual SES) in South Korea. The Korea National Health Insurance (KNHI) database was used to examine the effect of heat and cold on hospital admissions for AMI during 2004–2012. We analyzed the increase in AMI hospital admissions both above and below a threshold temperature using Poisson generalized additive models (GAMs) for hot, cold, and warm weather. The Medicaid group, the lowest SES group, had a significantly higher RR of 1.37 (95% CI: 1.07–1.76) for heat and 1.11 (95% CI: 1.04–1.20) for cold among subgroups, while also showing distinctly higher risk curves than NHI for both hot and cold weather. In additions, females, older age group, and those living in urban areas had higher risks from hot and cold temperatures than males, younger age group, and those living in rural areas.

In this study, using public transport smart card data observed in Seoul, Korea, we provide empirical evidence related to the impact of the opening of a new railway line on passenger demand changes at transfer stations. An intervention time series modeling framework was applied to evaluate the travel demand patterns based upon massive card data collected before and after a new line opened. The results show that the new line opening has had meaningful intervention effects on passenger demand, but significant changes were not observed at all stations. This implies that the trends have been changed structurally and the changes may last for a long time. Consequently, it is found that the new line opening changed the trends of passenger ridership and these changes can be successfully explained by various intervention patterns derived from extensive Automatic Fare Collection (AFC) data. The intervention analysis will provide valuable information to transit agencies to enable them to make better decisions related to transit planning, pricing, and the deployment of new transit services.

Railway accidents are critical issues characterized by a large number of injuries and fatalities per accident due to massive public transport systems. This study proposes a new approach for evaluating the damages resulting from railway accidents using the two-part models (TPMs) such as the zero-inflated Poisson regression model (ZIP model) and the zero-inflated negative-binomial regression model (ZINB model) for the non-negative count measurements and the zero-inflated gamma regression model (ZIG model) and the zero-inflated log-normal regression model (ZILN model) for the semi-continuous measurements. The models are employed for the evaluation of the railway accidents on Korea Railroad, considering the accident damages, such as the train delay time, the number of trains delayed and the cost of considering the accident count responses, for the period 2008 to 2016. From the results obtained, we found that the human-related factors, the high-speed railway system or the Korea Train Express (KTX) and the number of casualties, are the main cost-escalating factors. The number of trains delayed and the amount of delay time tend to increase both the probability of incurring costs and the amount of cost. For better evaluation, the railway accident data should contain accurate information with less recurrence of zeros.