Search

In South Korea, the rapid proliferation of smartphones has led to an uptick in messenger phishing attacks associated with electronic communication financial scams. In response to this, various phishing detection algorithms have been proposed. However, collecting messenger phishing data poses challenges due to concerns about its potential use in criminal activities. Consequently, a Korean phishing dataset can be composed of imbalanced data, where the number of general messages might outnumber the phishing ones. This class imbalance problem and data scarcity can lead to overfitting issues, making it difficult to achieve high performance. To solve this problem, this paper proposes a phishing messages classification method using Biased Discriminant Analysis without resorting to data augmentation techniques. In this paper, by optimizing the parameters for BDA, we achieved exceptionally high performances in the phishing messages classification experiment, with 95.45% for Recall and 96.85% for the BA metric. Moreover, when compared with other algorithms, the proposed method demonstrated robustness against overfitting due to the class imbalance problem and exhibited minimal performance disparity between training and testing datasets. [ABSTRACT FROM AUTHOR]

Recently, South Korea has been transitioning into a super-aged society. The purpose of this paper is to identify the patterns and underlying causes of gerontophobia expressions in South Korea. This paper refines the patterns of gerontophobia expressions into five types: "Fear of Aging," "Resource Burden," "Social Isolation," "Criticism of Social Behavior," and "Stereotypes of Political Orientation." Based on these types, this study develops a deep learning algorithm to detect the type of gerontophobia expressions. To do this, kc-BERT was used and 760,140 news comments (for six years from May 1, 2017, to June 31, 2021) in Naver news was used. The result shows that "Fear of Aging" type exhibited a significant decreasing trend, while the other types showed no meaningful changes. The results of topic modeling on news articles indicated that various aspects of elderly life, unresolved historical events, COVID-19, digital and financial exclusion, economic and social welfare, and other critical societal issues co-occur and contribute to gerontophobia. This study provides a framework to understand the characteristics of online gerontophobia, offering insights into its underlying causes, and providing practical implications for policy makers. [ABSTRACT FROM AUTHOR]

As the penetration of renewable energy sources into a power system increases, the significance of precise short-term forecasts for wind power generation becomes paramount. However, the erratic and non-periodic nature of wind poses challenges in accurately predicting the output. This paper presents a comprehensive investigation into forecasting wind power generation for the following day, using three machine learning models: long short-term memory (LSTM), convolutional neural network-bidirectional LSTM (CNN-biLSTM), and light gradient boosting machine (LGBM). In addition, this paper proposes a method to improve the prediction performance of LGBM by separating data according to the distribution of features, and training and testing each separated dataset with a distinct model. This study includes a comparative analysis of the performance of the proposed models in predicting wind turbine output, offering valuable insights into their respective efficiencies. The results of this investigation were analyzed for two geographically distinct wind farms (Korea and the UK). The findings of this study are expected to facilitate the selection of efficient prediction models within the forecast accuracy auxiliary service market and assist grid operators in ensuring reliable power supply for the grid. [ABSTRACT FROM AUTHOR]

Real-world route navigation data indicate that nontrivial portion of drivers do not prefer the system-recommended best routes. Current navigation systems have simplified assumptions about drivers' route choice preferences and do not adequately accommodate drivers' heterogeneous route choice preferences, mainly because of: (i) difficulty in acquiring exogenous criteria (e.g., sociodemographic information) that are typically used to differentiate drivers' preferences in behavioral modeling; and (ii) difficulty in capturing preference of individuals due to limited preference data at the individual level. To address these, this paper introduced a human-centric machine learning technique named Multi-Task Linear Classification Model Adaption (MT-LinAdapt). It can capture drivers' common aspects of route choice preferences and yet adapts to each driver's own preference. In addition, any evolvement of individual drivers' preferences can be simultaneously integrated to update the common preference for further individual drivers' preference adaptation. This paper evaluated MT-LinAdapt against two state-of-the-art route recommendation strategies including an aggregate-level and an individual-level data-based strategies, which are categorized based on the data used for modeling. With a real-world dataset containing 30,837 drivers' navigation usage data in Daegu City, South Korea, MT-LinAdapt was compared to existing strategies for its performance at different levels of data availability, and showed at least the same performance with existing strategies when minimum preference data is available and achieves up to 7% higher prediction accuracy as more data becomes available. Higher prediction accuracies are expected to bring better user satisfaction and compliance rates which can further help with transportation system control and management strategies. [ABSTRACT FROM AUTHOR]

The residual value (RV) of a vehicle refers to its estimated worth at some point in the future. It is a core component in every auto finance product, used to determine the credit lines and the leasing rates. As such, an accurate prediction of RV is critical for the auto finance industry, since it can pose a risk of revenue loss by over‐prediction or make the financial product incompetent through under‐prediction. Although there are a number of prior studies on training machine learning models on a large amount of used car sales data, we had to cope with real‐world operational requirements such as compliance with regulations (i.e., monotonicity of output with respect to a subset of features) and generalization to unseen input (i.e., new and rare car models). In this paper, we describe how we addressed these practical challenges and created value for our business at Hyundai Capital Services, the top auto financial service provider in Korea. [ABSTRACT FROM AUTHOR]

The American Society of Anesthesiologist's Physical Status (ASA-PS) classification system assesses comorbidities before sedation and analgesia, but inconsistencies among raters have hindered its objective use. This study aimed to develop natural language processing (NLP) models to classify ASA-PS using pre-anesthesia evaluation summaries, comparing their performance to human physicians. Data from 717,389 surgical cases in a tertiary hospital (October 2004–May 2023) was split into training, tuning, and test datasets. Board-certified anesthesiologists created reference labels for tuning and test datasets. The NLP models, including ClinicalBigBird, BioClinicalBERT, and Generative Pretrained Transformer 4, were validated against anesthesiologists. The ClinicalBigBird model achieved an area under the receiver operating characteristic curve of 0.915. It outperformed board-certified anesthesiologists with a specificity of 0.901 vs. 0.897, precision of 0.732 vs. 0.715, and F1-score of 0.716 vs. 0.713 (all p <0.01). This approach will facilitate automatic and objective ASA-PS classification, thereby streamlining the clinical workflow. [ABSTRACT FROM AUTHOR]

Objective: Cognitive decline is often considered an inevitable aspect of aging; however, recent research has identified a subset of older adults known as "superagers" who maintain cognitive abilities comparable to those of younger individuals. Investigating the neurobiological characteristics associated with superior cognitive function in superagers is essential for understanding "successful aging." Evidence suggests that the gut microbiome plays a key role in brain function, forming a bidirectional communication network known as the microbiome-gut-brain axis. Alterations in the gut microbiome have been linked to cognitive aging markers such as oxidative stress and inflammation. This study aims to investigate the unique patterns of the gut microbiome in superagers and to develop machine learning-based predictive models to differentiate superagers from typical agers. Methods: We recruited 161 cognitively unimpaired, community-dwelling volunteers aged 60 years or from dementia prevention centers in Seoul, South Korea. After applying inclusion and exclusion criteria, 115 participants were included in the study. Following the removal of microbiome data outliers, 102 participants, comprising 57 superagers and 45 typical agers, were finally analyzed. Superagers were defined based on memory performance at or above average normative values of middle-aged adults. Gut microbiome data were collected from stool samples, and microbial DNA was extracted and sequenced. Relative abundances of bacterial genera were used as features for model development. We employed the LightGBM algorithm to build predictive models and utilized SHAP analysis for feature importance and interpretability. Results: The predictive model achieved an AUC of 0.832 and accuracy of 0.764 in the training dataset, and an AUC of 0.861 and accuracy of 0.762 in the test dataset. Significant microbiome features for distinguishing superagers included Alistipes, PAC001137_g, PAC001138_g, Leuconostoc, and PAC001115_g. SHAP analysis revealed that higher abundances of certain genera, such as PAC001138_g and PAC001115_g, positively influenced the likelihood of being classified as superagers. Conclusion: Our findings demonstrate the machine learning-based predictive models using gut-microbiome features can differentiate superagers from typical agers with a reasonable performance. [ABSTRACT FROM AUTHOR]

This paper proposes an automatic air-to-ground (A2G) channel model selection method based on machine learning (ML) using digital surface model (DSM) terrain data. In order to verify whether a communication network for a new non-terrestrial user service such as Urban Air Mobility (UAM) satisfies the required performance, it is necessary to perform a simulation reflecting the characteristics of the corresponding terrain environments as accurately as possible. For this simulation, A2G channel models corresponding to various terrain environments and a method of automatically classifying the terrain type of the simulation area must be provided. Many A2G channel models based on actual measurement results exist, but the practical automatic topography classification method still needs to be developed. This paper proposes the first practical automatic topography classification method using a two-step neural network-based classifier utilizing various geographic feature data as input. Since there is no open topography dataset to evaluate the accuracy of the proposed method, we built a new dataset for five topography classes that reflect the characteristics of Korea's topography, which is also a contribution of our study. The simulation results using the new data set show that the proposed ML-based method could increase the selection accuracy compared to the technique for direct classification by humans or the existing cross-correlation-based classification method. Since the proposed method utilizes the DSM data, open to the public, it can easily reflect the different terrain characteristics of each country. Therefore, the proposed method can be effectively used in the realistic performance evaluation of new non-terrestrial communication networks utilizing vast airspace such as UAM or 6G mobile communications. [ABSTRACT FROM AUTHOR]

Using traditional methods based on detection rules written by human security experts presents significant challenges for the accurate detection of network threats, which are becoming increasingly sophisticated. In order to deal with the limitations of traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads that contain binary and text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte-pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets such as IP addresses and ports. Given these features, we combine a text 1D CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique on the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC), currently operating in South Korea. The proposed model showed remarkable performance compared to previous studies, achieving highly accurate classification with an F1-score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute, helping security agents in the field maximize their time and analyze more complex attack patterns. [ABSTRACT FROM AUTHOR]

The wheels of railway vehicles are of paramount importance in relation to railroad operations and safety. Currently, the management of railway vehicle wheels is restricted to post-event inspections of the wheels whenever physical phenomena, such as abnormal vibrations and noise, occur during the operation of railway vehicles. To address this issue, this paper proposes a method for predicting abnormalities in railway wheels in advance and enhancing the learning and prediction performance of machine learning algorithms. Data were collected during the operation of Line 4 of the Busan Metro in South Korea by directly attaching sensors to the railway vehicles. Through the analysis of key factors in the collected data, factors that can be used for tire condition classification were derived. Additionally, through data distribution analysis and correlation analysis, factors for classifying tire conditions were identified. As a result, it was determined that the z-axis of acceleration has a significant impact, and machine learning techniques such as SVM (Linear Kernel, RBF Kernel) and Random Forest were utilized based on acceleration data to classify tire conditions into in-service and defective states. The SVM (Linear Kernel) yielded the highest recognition rate at 98.70%. [ABSTRACT FROM AUTHOR]

Background: Language learners are taking advantage of the increased accuracy afforded by machine translation (MT) tools like Google Translate. There is a growing debate as to whether these tools support or hinder English as a foreign language (EFL) education. Some EFL students are drawn to MT tools to save time and energy when communicating, but how this use relates to second language acquisition needs to be clarified. Objective: This study investigated the perceptions and practices of MT tools among university EFL students in Saudi Arabia and South Korea. Methods: The study surveyed Saudi (n = 310) and South Korean (n = 160) university students to explore the use of MT tools in EFL learning. It used mean scores, correlation analysis, and structural equation modelling to understand the perceived benefits and limitations of MT tools and their influence on the use of translation websites. The findings were triangulated using content analysis of open‐ended items. Results and Conclusion: Findings indicate students showed a high level of acceptance and utilization of MT tools. English avoidance behaviour (B = 0.43), benefits (B = 0.32), and foreign language proficiency (B = −0.19) predicted 61% of actual use of MT tools like Google Translate. Further, students frequently used MT tools despite the reported concerns about accuracy mistakes. Saudi students listed a more comprehensive array of why they use MT tools than Korean students, while Saudis and Koreans frequently used MT tools for individual word and sentence translations. Implications: Students should edit MT output when writing and are encouraged to use the voice recording and other functions of MT tools to learn language skills. Instructors must prevent overuse and dependency on MT tools, especially among low‐proficiency students who want to avoid using English. Lay Description: What is currently known about the subject matter: Students use translation tools to complete foreign language assignmentsStudents have a positive view towards translation toolsInstructors have mixed feelings on their students' use of translation tools What their paper adds to this: A mixed method study to learn strengths and limitations with translation toolsCross‐cultural study to compare perceptions from two regionsIdentified benefits to pronunciation skills through voice recording functionsLimitations with translation accuracy did not negatively influence actual use Implications of study findings for practitioners: Identified benefits with translation tools can be applied to writing instructionLimitations identified including over‐dependency and cheating should be avoidedStudents are recommended to use the speech function to practice pronunciationPost‐editing (revising) is an important part of using translation tools [ABSTRACT FROM AUTHOR]

Suicide among the older population is a significant public health concern in South Korea. As the older individuals have long considered suicide before committing suicide trials, it is important to analyze the suicidal ideation that precedes the suicide attempt for intervention. In this study, six machine learning algorithms were employed to construct a predictive model for suicidal thinking and identify key variables. A traditional logistic regression analysis was supplementarily conducted to test the robustness of the results of machine learning. All analyses were conducted using a hierarchical approach to compare the model fit of each model in both machine learning and logistic regression. Three models were established for analysis. In Model 1, socioeconomic, residential, and health behavioral factors were incorporated. Model 2 expanded upon Model 1 by integrating physical health status, and Model 3 further incorporated mental health conditions. The results indicated that the gradient boosting algorithm outperformed the other machine learning techniques. Furthermore, the household income quintile was the most important feature in Model 1, followed by subjective health status, oral health, and exercise ability in Model 2, and anxiety and depression in Model 3. These results correspond to those of the hierarchical logistic regression. Notably, economic and residential vulnerabilities are significant factors in the mental health of the older population with higher instances of suicidal thoughts. This hierarchical approach could reveal the potential target population for suicide interventions. [ABSTRACT FROM AUTHOR]

An interpolation method, which estimates unknown values with constrained information, is based on mathematical calculations. In this study, we addressed interpolation from an image-based perspective and expanded the use of image inpainting to estimate values at unknown points. When chemical gas is dispersed through a chemical attack or terrorism, it is possible to determine the concentration of the gas at each location by utilizing the deployed sensors. By interpolating the concentrations, we can obtain the contours of gas concentration. Accurately distinguishing the contours of a contaminated region from a map enables the optimal response to minimize damage. However, areas with an insufficient number of sensors have less accurate contours than other areas. In order to achieve more accurate contour data, an image inpainting-based method is proposed to enhance reliability by erasing and reconstructing low-accuracy areas in the contour. Partial convolution is used as the machine learning approach for image-inpainting, with the modified loss function for optimization. In order to train the model, we developed a gas diffusion simulation model and generated a gas concentration contour dataset comprising 100,000 contour images. The results of the model were compared to those of Kriging interpolation, one of the conventional spatial interpolation methods, finally demonstrating 13.21% higher accuracy. This suggests that interpolation from an image-based perspective can achieve higher accuracy than numerical interpolation on well-trained data. The proposed method was validated using gas concentration contour data from the verified gas dispersion modeling software Nuclear Biological Chemical Reporting And Modeling System (NBC_RAMS), which was developed by the Agency for Defense Development, South Korea. [ABSTRACT FROM AUTHOR]

Here, we describe the development and validation of an automatic assessment system that examines students' hand-drawn visual representations in free-response items. The data were collected from 1,028 students in the second through 11th grades in South Korea using two items from the Test About Particles in a Gas questionnaire (Novick & Nussbaum, 1981). Students' free responses, which include hand drawings and writing, were coded for two dimensions — structural (particulate/continuous/other) and distributional (expanded/concentrated/other). Machine learning (ML) models were trained to assess the responses on the particulate nature of matter. For classifying hand drawings, a pre-trained Inception-v3 model followed by a support vector machine was trained and its performance was evaluated. The assessment model yielded high machine-human agreement (MHA) (kappa = 0.732–0.926, accuracy = 0.820–0.942, precision = 0.817–0.941, recall = 0.820–0.942, F1 = 0.818–0.941, and area under the curve [AUC] = 0.906–0.990). Students' written responses were tokenized, and a dictionary of scientific semantic scores was prepared. The final model for the overall assessment of both drawing and writing yielded high MHA (kappa = 0.800–0.881, accuracy = 0.859–0.956, precision = 0.865–0.957, recall = 0.859–0.956, F1 = 0.859–0.956, and AUC = 0.944–0.995), which varied by the final classifiers of the models. There were some variances in the performance of the assessment model according to the school level. This study suggests that artificial intelligence can be used to automate assessments of students' representations of scientific concepts in free-response items, particularly those drawn in a pencil-and-paper format. [ABSTRACT FROM AUTHOR]

The efficient scheduling of resources within emergency departments (EDs) is crucial to minimizing patient length of stay (LoS) times and maximizing the utilization of limited resources. Reducing patient wait times can enhance the operation of emergency departments and improve patient satisfaction and the quality of medical care. This study develops a simulation model using Discrete Event Simulation (DES) methodology, examining six resource scheduling policies that consider different combinations of general and senior physicians. By leveraging six scheduling policies and machine learning techniques, this model dynamically identifies the most effective scheduling policy, based on a comprehensive dataset of ED visits in South Korea. The ED simulation achieves an accuracy rate of 90% and demonstrates that our proposed integrated machine learning approach reduces average length of stay (LoS) to approximately 322.91 min, compared to 327.10 min under traditional methods. This study underscores the potential of integrating DES and machine learning to enhance resource management in EDs. [ABSTRACT FROM AUTHOR]

Nasal endoscopy is routinely performed to distinguish the pathological types of masses. There is a lack of studies on deep learning algorithms for discriminating a wide range of endoscopic nasal cavity mass lesions. Therefore, we aimed to develop an endoscopic-examination-based deep learning model to detect and classify nasal cavity mass lesions, including nasal polyps (NPs), benign tumors, and malignant tumors. The clinical feasibility of the model was evaluated by comparing the results to those of manual assessment. Biopsy-confirmed nasal endoscopic images were obtained from 17 hospitals in South Korea. Here, 400 images were used for the test set. The training and validation datasets consisted of 149,043 normal nasal cavity, 311,043 NP, 9,271 benign tumor, and 5,323 malignant tumor lesion images. The proposed Xception architecture achieved an overall accuracy of 0.792 with the following class accuracies on the test set: normal = 0.978 ± 0.016, NP = 0.790 ± 0.016, benign = 0.708 ± 0.100, and malignant = 0.698 ± 0.116. With an average area under the receiver operating characteristic curve (AUC) of 0.947, the AUC values and F1 score were highest in the order of normal, NP, malignant tumor, and benign tumor classes. The classification performances of the proposed model were comparable with those of manual assessment in the normal and NP classes. The proposed model outperformed manual assessment in the benign and malignant tumor classes (sensitivities of 0.708 ± 0.100 vs. 0.549 ± 0.172, 0.698 ± 0.116 vs. 0.518 ± 0.153, respectively). In urgent (malignant) versus nonurgent binary predictions, the deep learning model achieved superior diagnostic accuracy. The developed model based on endoscopic images achieved satisfactory performance in classifying four classes of nasal cavity mass lesions, namely normal, NP, benign tumor, and malignant tumor. The developed model can therefore be used to screen nasal cavity lesions accurately and rapidly. [ABSTRACT FROM AUTHOR]

This study accounted for the importance of daily expansion flow data in compensating for insufficient flow data in a watershed. In particular, the 8-day interval flow measurement data (intermittent monitoring data) could cause uncertainty in the high- or low-flow conditions that have been used to estimate the flow duration curve (FDC) and the load duration curve (LDC) used in Total Maximum Daily Load (TMDL) evaluation in Korea. Thus, this study developed a method to expand the 8-day interval flow data (missing data) to daily flow data in order to evaluate the Total Maximum Daily Load (TMDL) appropriately in a watershed. We employed the machine learning technique (the gradient descent method provided by the Google TensorFlow package) to develop a regression for expanding the 8-day interval flow data. The method was applied in the Nakdong River basin located in Korea to collect the 8-day interval and daily flow data from a number of gauging stations. The results of the expanded daily flow were evaluated through the RMSE, MAE, IOA, and NSE, and the valid expanded daily flow data were obtained for the 29 TMDL gauging stations (IOA 0.84~0.99, NSE −0.18~0.99). A good performance in the creation of daily flow data (continuous data) from the 8-day interval flow data (intermittent data) was shown using the proposed method. In addition, the Web GIS-based pollutant load assessment system was developed to evaluate the TMDL; it included the daily data expansion method and provided the pollution load characteristics objectively and intuitively. This system will help decision makers, such as environmental regulators, researchers, and the general public, and support their decision making for pollution source management with accessible and efficient tools for understanding and addressing water quality issues. [ABSTRACT FROM AUTHOR]

In determining wind loads when designing buildings—especially high-rise buildings—wind speed is a critical factor. With increased progression of city high-rise construction, accurate prediction has become ever more important. Many factors, such as local climates, roughness of surrounding conditions, and terrain, may affect wind speed. But among all factors considered, terrain has a very large influence. Difficulties in reflecting the influence of terrain on wind speed include (1) collecting topographic data information; (2) quantitatively evaluating terrain features; and (3) expressing specific area relationships with surrounding observation stations. This paper poses means to solve these limitations by (1) using satellite imagery to gather topographic information; (2) evaluating terrain quantitatively with convolutional neural network (CNN)–based encoders; and (3) employing a graph neural network (GNN) to estimate the wind speed relationship of an arbitrary place to that of observation stations. Herein, a machine learning model utilizing the aforementioned means was proposed. To support this model, an experiment was conducted using observed wind speed data in Korea. Throughout the experiment, previous studies were used to compare results with ratification of the posed model. Given the submitted findings, further research and investigation to establish correlation with other experimental case results are proposed. [ABSTRACT FROM AUTHOR]

Rainfall-induced landslides frequently occur in the mountainous region of the Korean peninsula. The resulting landslide-induced debris causes extreme property damage, huge financial losses, and human deaths. To mitigate their effect different landslide susceptibility mapping is frequently used. However, these methods do identify regions with potential landslides but they do not quantify their severity. In this paper, multi-category ordered machine models, namely, proportional odd logistic regression (POLR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (EGB) methods, are proposed to fill the specified gap. Moreover, the exploratory data analysis on the landslide-induced debris dataset has been conducted to examine patterns and relationships between landslide-induced debris severity(size), causal factors(rainfall), and influencing factors. Findings revealed that cumulative three days' rainfall and slope length were most responsible for the severity of landslide-originated debris severity and slopes between 20° to 40° were identified as the most vulnerable region. Furthermore, the predictive accuracy statistics were compared to assess the suitable model for debris severity for the Korean case. The RF and EGB ranked higher with an overall accuracy of 90.07 % and 86.09 % and kappa of 0.72 and 0.61 on the validation set, respectively. The findings of this research may be useful in the identification of high-risk zones for extreme rainfall-induced debris to elaborate mitigation and resilience policies, post-disaster rehabilitation planning, and land use management. [ABSTRACT FROM AUTHOR]

This study uses the API of Upbit, one of Korea's cryptocurrency exchanges, to predict continuous time series for a limited period and cryptocurrencies using LSTM, a machine learning technique. The trading (buying and selling) point algorithm presented in this study was used to conduct experimental research on efficient profit creation for cryptocurrency investment. Several related studies have shown the results of time series prediction for long-term forecasts, such as a week or several months. Still, they have not attempted to make an ultra-short-term prediction in units of one minute. This paper attempts such a 1 min prediction. This is an experiment to create efficient profits by setting efficient trading (buying and selling) points using machine learning techniques and repeating these operations by an algorithm. Applying it to cryptocurrency shows the possibility of time series prediction. [ABSTRACT FROM AUTHOR]

In predicting energy consumption, classic econometric and statistical models are used to forecast energy consumption. These models may have limitations in an increasingly fast-changing energy market, which requires big data analysis of energy consumption patterns and relevant variables using complex mathematical tools. In current literature, there are minimal comparison studies reviewing machine learning algorithms to predict energy consumption in Korea. To bridge this gap, this paper compared three different machine learning algorithms, namely the Random Forest (RF) model, XGBoost (XGB) model, and Long Short-Term Memory (LSTM) model. These algorithms were applied in Period 1 (prior to the onset of the COVID-19 pandemic) and Period 2 (after the onset of the COVID-19 pandemic). Period 1 was characterized by an upward trend in energy consumption, while Period 2 showed a reduction in energy consumption. LSTM performed best in its prediction power specifically in Period 1, and RF outperformed the other models in Period 2. Findings, therefore, suggested the applicability of machine learning to forecast energy consumption and also demonstrated that traditional econometric approaches may outperform machine learning when there is less unknown irregularity in the time series, but machine learning can work better with unexpected irregular time series data. [ABSTRACT FROM AUTHOR]

We investigated a screening method for mild cognitive impairment (MCI) that combined bioimpedance features and the Korean Mini-Mental State Examination (K-MMSE) score. Data were collected from 539 subjects aged 60 years or older at the Gwangju Alzheimer's & Related Dementias (GARD) Cohort Research Center, A total of 470 participants were used for the analysis, including 318 normal controls and 152 MCI participants. We measured bioimpedance, K-MMSE, and the Seoul Neuropsychological Screening Battery (SNSB-II). We developed a multiple linear regression model to predict MCI by combining bioimpedance variables and K-MMSE total score and compared the model's accuracy with SNSB-II domain scores by the area under the receiver operating characteristic curve (AUROC). We additionally compared the model performance with several machine learning models such as extreme gradient boosting, random forest, support vector machine, and elastic net. To test the model performances, the dataset was divided into a training set (70%) and a test set (30%). The AUROC values of SNSB-II scores were 0.803 in both sexes, 0.840 for males, and 0.770 for females. In the combined model, the AUROC values were 0.790 (0.773) for males (and females), which were significantly higher than those from the model including MMSE scores alone (0.723 for males and 0.622 for females) or bioimpedance variables alone (0.640 for males and 0.615 for females). Furthermore, the accuracies of the combined model were comparable to those of machine learning models. The bioimpedance-MMSE combined model effectively distinguished the MCI participants and suggests a technique for rapid and improved screening of the elderly population at risk of cognitive impairment. [ABSTRACT FROM AUTHOR]

Specific humidity (SH) which means the amount of water vapor in 1 kg of air, is used as an indicator of energy exchange between the atmosphere and the Earth's surface. SH is typically computed using microwave satellites. However, the spatial resolution of data for microwave satellite is too low. To overcome this disadvantage, we introduced new methods that applied data collected by the Landsat-8 satellite with high spatial resolution (30 m), a meteorological model, and observation data for South Korea in 2016–2017 to 4 machine learning techniques to develop an optimized technique for computing SH. Among the 4 machine learning techniques, the random forest-based method had the highest accuracy, with a coefficient of determination (R) of 0.98, Root Mean Square Error (RMSE) of 0.001, bias of 0, and Relative Root Mean Square Error (RRMSE) of 11.16%. We applied this model to compute land surface SH using data from 2018 to 2019 and found that it had high accuracy (R = 0.927, RMSE = 0.002, bias = 0, RRMSE = 28.35%). Although the data used in this study were limited, the model was able to accurately represent a small region based on an ensemble of satellite and model data, demonstrating its potential to address important issues related to SH measurements from satellites. [ABSTRACT FROM AUTHOR]

Die-casting is a popular manufacturing process that produces precise metal parts with excellent dimensional accuracy and smooth cast surfaces. Recently die-casting process condition data can be acquired to be used as input for machine learning techniques for fault detection. The rapid development of complex and accurate machine learning algorithms, such as tree ensembles and deep learning, allows the accurate detection of faulty products. However, interpreting and explaining black-box models is crucial in the die-casting industry because the predictions provided by the machine learning solution can be adopted in practice only after understanding the internal decision mechanism of the model. To solve this problem, rule extraction methods generate simple rule-based predictive models from complex tree ensembles. Nevertheless, rulesets may contain numerous complex rules with redundant conditions, and the standard structure of rulesets does not clearly show the hierarchical relationships and frequent interactions among their elements. For this reason, in this study, a visualization tool based on formal concept analysis, called RuleLat (Rule Lattice), is proposed, which generates simple visual representations of rule-based classifiers. The generated models depict the hierarchical relationships of interactions among conditions, rules, and predicted classes in a modified concept lattice that is easy to analyze and understand. To demonstrate the applicability of the proposed method, a case study using real-world manufacturing data collected from a die-casting company in Korea is presented. RuleLat is adopted as a tool for interpretable machine learning, and the process conditions of three types of defects (porosity, material, and imprint) are analyzed and discussed. [ABSTRACT FROM AUTHOR]

Age is an essential piece of demographic information for social profiling, as different social and behavioral characteristics are age-related. To acquire age information, most of the previously conducted social profiling studies have predicted age information. However, age predictions in social profiling have been very limited, because it is difficult or impossible to obtain age information from social media. Moreover, age-prediction results have rarely been used to study human dynamics. In these circumstances, this study focused on naver.com, a nationwide social media website in Korea. Although the social profiles of news commenters on naver.com can be analyzed and used, the age information is incomplete (i.e., partially open to the public) owing to anonymity and privacy protection policies. Therefore, no prior research has used naver.com for age predictions or subsequent analyses based on the predicted age information. To address this research gap, this study proposes a method that uses a machine learning approach to predict the age information of anonymous commenters on unlabeled (i.e., with age information hidden) news articles on naver.com. Furthermore, the predicted age information was fused with the section information of the collected news articles, and fuzzy differences between age groups were analyzed for topics of interest, using the proposed correlation–similarity matrix and fuzzy sets of age differences. Thus, differentiated from the previous social profiling studies, this study expands the literature on social profiling and human dynamics studies. Consequently, it revealed differences between age groups from anonymous and incomplete Korean social media that can help in understanding age differences and ease related intergenerational conflicts to help reach a sustainable South Korea. [ABSTRACT FROM AUTHOR]

In this study, we utilize data-driven approaches to predict flight departure delays. The growing demand for air travel is outpacing the capacity and infrastructure available to support it. In addition, abnormal weather patterns caused by climate change contribute to the frequent occurrence of flight delays. In light of the extensive network of international flights covering vast distances across continents and oceans, the importance of forecasting flight delays over extended time periods becomes increasingly evident. Existing research has predominantly concentrated on short-term predictions, prompting our study to specifically address this aspect. We collected datasets spanning over 10 years from three different airports such as ICN airport in South Korea, JFK and MDW airport in the United States, capturing flight information at six different time intervals (2, 4, 8, 16, 24, and 48 h) prior to flight departure. The datasets comprise 1,569,879 instances for ICN, 773,347 for JFK, and 404,507 for MDW, respectively. We employed a range of machine learning and deep learning approaches, including Decision Tree, Random Forest, Support Vector Machine, K-nearest neighbors, Logistic Regression, Extreme Gradient Boosting, and Long Short-Term Memory, to predict flight delays. Our models achieved accuracy rates of 0.749 for ICN airport, 0.852 for JFK airport, and 0.785 for MDW airport in 2-h predictions. Furthermore, for 48-h predictions, our models achieved accuracy rates of 0.748 for ICN airport, 0.846 for JFK airport, and 0.772 for MDW airport based on our experimental results. Consequently, we have successfully validated the accuracy of flight delay predictions for longer time frames. The implications and future research directions derived from these findings are also discussed. [ABSTRACT FROM AUTHOR]

High-growth firms (HGFs), also known as gazelle firms, have attracted considerable attention due to their outstanding contributions to job creation and additional spillover benefits. Despite years of work, it is still challenging to predict high-growth firms, and many essential HGF characteristics are yet unknown. This study analyzes high-quality Korean firm data and predicts high-growth firms using big data and machine learning methods, such as LASSO, adaptive LASSO, and random forest analysis. Besides, we include variables related to business strategies and activities such as innovation, information systems like ERP, outsourcing, strategic alliances, and expansion to international markets to determine whether the addition of this information enhances HGF prediction. We discovered the significance of revenue growth, efficiency management, asset investment, and human resource management skills in increasing one's chances of becoming an HGF. The findings suggest that rather than being an erratic process or being purely driven by structural characteristics, firm growth is determined by the firm's endogenous strategic characteristics. Plain English Summary: With cutting-edge machine learning techniques including LASSO, adaptive LASSO, and random forest, we discovered the significance of revenue growth, efficiency management, asset investment, and human resource management skills in increasing one's chances of becoming an HGF. [ABSTRACT FROM AUTHOR]

The optical flow technique has advantages in motion tracking and has long been employed in precipitation nowcasting to track the motion of precipitation fields using ground radar datasets. However, the performance and forecast time scale of models based on optical flow are limited. Here, we present the results of the application of the deep learning method to optical flow estimation to extend its forecast time scale and enhance the performance of nowcasting. It is shown that a deep learning model can better capture both multispatial and multitemporal motions of precipitation events compared with traditional optical flow estimation methods. The model comprises two components: 1) a regression process based on multiple optical flow algorithms, which more accurately captures multispatial features compared with a single optical flow algorithm; and 2) a U-Net-based network that trains multitemporal features of precipitation movement. We evaluated the model performance with cases of precipitation in South Korea. In particular, the regression process minimizes errors by combining multiple optical flow algorithms with a gradient descent method and outperforms other models using only a single optical flow algorithm up to a 3-h lead time. Additionally, the U-Net plays a crucial role in capturing nonlinear motion that cannot be captured by a simple advection model through traditional optical flow estimation. Consequently, we suggest that the proposed optical flow estimation method with deep learning could play a significant role in improving the performance of current operational nowcasting models, which are based on traditional optical flow methods. Significance Statement: The purpose of this study is to improve the accuracy of short-term rainfall prediction based on optical flow methods that have been employed for operational precipitation nowcasting. By utilizing open-source libraries, such as OpenCV, and commonly applied machine learning techniques, such as multiple linear regression and U-Net networks, we propose an accessible model for enhancing prediction accuracy. We expect that the improvement in prediction accuracy will significantly improve the practical application of operational precipitation nowcasting. [ABSTRACT FROM AUTHOR]

It is very difficult for us to accurately predict occurrence of a fire. But, this is very important to protect human life and property. So, we study fire hazard prediction and evaluation methods to cope with fire risks. In this paper, we propose three models based on statistical machine learning and optimized risk indexing for fire risk assessment. We build logistic regression, deep neural networks (DNN) and fire risk indexing models, and verify performances between proposed and traditional models using real investigated data related to fire occurrence in Korea. In general, fire prediction models currently in use do not provide satisfactory levels of accuracy. The reason for this result is that the factors affecting fire occurrence are very diverse and frequency of fire occurrence is very sparse. To improve accuracy of fire occurrence, we first build logistic regression and DNN models. In addition, we construct a fire risk indexing model for a more improved model of fire prediction. To illustrate comparison results between our research models and current fire prediction model, we use real fire data investigated in Korea between 2011 to 2017. From the experimental results of this paper, we can confirm that accuracy of prediction by the proposed method is superior to the existing fire occurrence prediction model. Therefore, we expect the proposed model to contribute to evaluating the possibility of fire risk in buildings and factories in the field of fire insurance and to calculate the fire insurance premium. [ABSTRACT FROM AUTHOR]

From a global perspective, gastric cancer (GC) persists as a significant healthcare issue. In the Western world, the majority of cases are discovered at late stages, when the treatment is generally unsuccessful. There are no organized screening programs outside of Asia (Japan and Republic of Korea). Traditional diagnosis techniques (such as upper endoscopy), conventional tumor markers (CEA, CA19-9, and CA72-4), radiographic imaging, and CT scanning all have drawbacks. The gold standard for the earliest detection of cancer and related premalignant lesions is still endoscopy with a proper biopsy follow-up. Since there are currently no clinically approved biomarkers for the early diagnosis of GC, the identification of non-invasive biomarkers is expected to help improve the prognosis and survival rate of these patients. The search for new screening biomarkers is currently underway. These include genetic biomarkers, such as circulating tumor cells, microRNAs, and exosomes, as well as metabolic biomarkers obtained from biofluids. Meanwhile, cutting-edge high-resolution endoscopic technologies are demonstrating promising outcomes in the visual diagnosis of mucosal lesions with the aid of linked color imaging and machine learning models. Following the PRISMA guidelines, this study examined the articles in databases such as PubMed, resulting in 167 included articles. This review discusses the currently available and emerging methods for diagnosing GC early on, as well as new developments in the endoscopic detection of early lesions of the stomach. [ABSTRACT FROM AUTHOR]

Identifying and predicting the nitrate inflow and distribution characteristics of groundwater is critical for groundwater contamination control and management in rural mixed-land-use areas. Several groundwater nitrate prediction models have been developed; in particular, a nitrate concentration model that uses dissolved ions in groundwater as an input variable can produce accurate results. However, obtaining sufficient chemical data from a target area remains challenging. We tested whether machine learning models can effectively determine nitrate contamination using field-measured data (pH, electrical conductivity, water temperature, dissolved oxygen, and redox potential) and existing geographic information system (GIS) data (lithology, land cover, and hydrogeological properties) from the Nonsan Stream Watershed in South Korea, an area where nitrate contamination occurs owing to intensive agricultural activities. In total, 183 groundwater samples from different wells, mixed municipal sites, and agricultural activities were used. The results indicated that among the four machine learning models (artificial neural network (ANN), classification and regression tree (CART), random forest (RF), and support vector machine (SVM)), the RF (R2: 0.74; RMSE: 3.5) and SVM (R2: 0.80; RMSE: 2.8) achieved the highest prediction accuracy and smallest error in all groundwater parameter estimates. Land cover, aquifer type, and soil drainage were the primary RF and SVM model input variables, representing agricultural activity-related and hydrogeological infiltration effects. Our research found that in rural areas with limited hydro-chemical data, RF and SVM models could be used to identify areas at high risk of nitrate contamination using spatial variability, GIS-aided visualization, and easily accessible field-measured groundwater quality data. [ABSTRACT FROM AUTHOR]

The number of senior citizens with large bowel obstruction is steadily growing in Korea. Plain radiography was used to examine the severity and treatment of this phenomenon. To avoid examiner subjectivity in radiography readings, we propose an automatic segmentation method to identify fluid-filled areas indicative of large bowel obstruction. Our proposed method applies the Hough transform to locate suspicious areas successfully and applies the possibilistic fuzzy c-means unsupervised learning algorithm to form the target area in a noisy environment. In an experiment with 104 real-world large-bowel obstruction radiographs, the proposed method successfully identified all suspicious areas in 73 of 104 input images and partially identified the target area in another 21 images. Additionally, the proposed method shows a true-positive rate of over 91% and false-positive rate of less than 3% for pixel-level area formation. These performance evaluation statistics are significantly better than those of the possibilistic c-means and fuzzy c-means-based strategies; thus, this hybrid strategy of automatic segmentation of large bowel suspicious areas is successful and might be feasible for real-world use. [ABSTRACT FROM AUTHOR]

Fly ash (FA) is the most commonly used supplementary cementitious material in the world. However, the reactivity of FA varies substantially. In this study, new machine learning (ML) model has been developed to efficiently predict the amorphous content in FA type F. Compared to the existing ML model using types F and C of FA from different countries, this study more focused on the improved prediction of FA type F only produced from South Korea. It was found that the contents of CaO and SiO2 impact high in predicting the amount of aluminosilicate glass. However, the contribution of Al2O3 and Fe2O3 are ranked differently. The improved model algorithm was proposed as a combination of three ensemble techniques of bagging, boosting, and stacking. As a result of the test, the final model shows R 2 of 0.80 in predicting the amount of aluminosilicate glass in FA type F. [ABSTRACT FROM AUTHOR]

Satellite-based surface albedo data are widely used to monitor and analyse the global climate and environmental changes. Korea continuously retrieves surface albedo from the Communication, Ocean and Meteorological Satellite (COMS)/Meteorological Imager sensor (MI) and GEO-KOMPSAT-2A (GK-2A)/Advanced Meteorological Imager sensor (AMI). However, the quality of these surface albedo outputs differs due to differences in the algorithms, input data and resolution, which limits their long-term use as climate data. By analyzing errors in the surface albedo data from COMS/MI and GK-2A/AMI and applying corrections, continuous climate monitoring can be enhanced. This study developed a correction model based on machine learning using multiple linear regression (MLR), random forest (RF) and deep neural network (DNN) models to consider the albedo data error characteristics of each satellite. The best performing RF model was used for correction. The errors of the corrected RF COMS/MI data were reduced; when validated with insitu data, the Root Mean Square Error (RMSE) of the COMS/MI improved from 0.056 to 0.023, similar to the RMSE of 0.019 of GK2A/AMI. It also showed stability in the time series validation with GLASS satellite data, with a consistent mean RMSE of 0.036. [ABSTRACT FROM AUTHOR]

Since the WHO's 2021 aging redefinition emphasizes "healthy aging" by focusing on the elderly's ability to perform daily activities, sarcopenia, which is defined as the loss of skeletal muscle mass, is now becoming a critical health concern, especially in South Korea with a rapidly aging population. Therefore, we develop a prediction model for sarcopenia by using machine learning (ML) techniques based on the Korea National Health and Nutrition Examination Survey (KNHANES) data 2008–2011, in which we focus on the role of socioeconomic status (SES), social infrastructure, and quality of life (QoL) in the prevalence of sarcopenia. We successfully identify sarcopenia with approximately 80% accuracy by using random forest (RF) and LightGBM (LGB), CatBoost (CAT), and a deep neural network (DNN). For prediction reliability, we achieve area under curve (AUC) values of 0.831, 0.868, and 0.773 for both genders, males, and females, respectively. Especially when using only male data, all the models consistently exhibit better performance overall. Furthermore, using the SHapley Additive exPlanations (SHAP) analysis, we find several common key features, which mainly contribute to model building. These include SES features, such as monthly household income, housing type, marriage status, and social infrastructure accessibility. Furthermore, the causal relationships of household income, per capita neighborhood sports facility area, and life satisfaction are analyzed to establish an effective prediction model for sarcopenia management in an aging population. [ABSTRACT FROM AUTHOR]

South Korea has developed road-based transportation and uses a lot of gasoline. South Korea imports gasoline since it is not produced domestically. So, fluctuations in gasoline prices have a significant impact on the national economy. Currently, gasoline orders, which are based on gasoline consumption, are analyzed in relation to fluctuations in gasoline prices. However, gasoline orders can also change due to various non-price factors. Therefore, to understand the trend of gasoline orders, it is important to identify additional factors that gas stations consider when determining orders. We collected 180 monthly samples of data on 167 variables. Sudden international issues lead to rapid fluctuations in gasoline orders, which can lead to outliers. A class imbalance occurs because outliers are generally fewer in number than the normal data points. Therefore, to address the class imbalance, we proposed a method that grouped the data samples into 11 clusters using the K-means clustering algorithm and then augmented the data into 85 datasets in each cluster through the Variational Auto-Encoder. We evaluated the augmented datasets through the R-Squared, Root Mean Squared Errors, and accuracy of various regression models. Based on the experimental results, when predicting gasoline orders at gas stations in South Korea using augmented datasets, linear regression showed the best performance. [ABSTRACT FROM AUTHOR]

Clusters facing a crisis could have devastating effects on the economic conditions of the regions. Therefore, it is important to study how resilience works in the lives of clusters. The purpose of the current study is to more quantitatively understand the life path of the growth and decline of industrial clusters by verifying actual patterns. Also, it is to explain why these patterns were formed by qualitatively analyzing the process of utilizing resilience. The main contribution to the field of the lifecycle of clusters would be proving the theoretical concepts with data of the entire official industrial clusters in South Korea for 2 decades. Although previous works have attempted to define life paths by classifying the groups, most of their cases only dealt with one or two cases, making it difficult to generalize to a theory that can explain all types of clusters. This research used South Korean data as representative data for classification by analyzing the 1375 industrial clusters for 20 years. The trend of their life paths was calculated using a classic time-series decomposition method, and dynamic time series warping was adopted to measure the similarity between the paths. The k-medoids method from an unsupervised machine learning technique was adopted to classify the data. They were classified into three types: Malmo-type, Silicon Valley-type, and Detroit-type. The same classification method can be applied to other countries. Through this classification, the necessary or weak determinants of resilience in their clusters can be found. By making up for these shortcomings, continuous growth can be achieved. [ABSTRACT FROM AUTHOR]

The energy-intensive steel industry, which consumes substantial amounts of electricity, meets its power demands through external electricity purchases and self-generation through the operation of its own generators. This study aimed to optimize boiler combustion efficiency and increase power generation output by deriving optimal operational values for O2 and CO within the boiler flue gas using machine learning (ML) with the aim of achieving maximum boiler efficiency. This study focuses on the power-generation boilers at steel mill P in Korea. First, 361 types of operation data from power generation equipment were collected and preprocessed. Subsequently, a partial least squares regression (PLSR) algorithm was used to develop a prediction model for O2 and CO values, known as the Boiler Flue Gas Prediction Model (BFG-PM). The prediction accuracy for O2 was notably high (83.2%), whereas that for CO was lower (53.4%). Nonetheless, the model's reliability was high because more than 90% of the predicted values were within a 10% error range. Finally, the correlation of the BFG-PM model was applied to the performance test code (PTC) 4.0 for the boiler efficiency calculations formula, deriving the optimal O2 and CO control points. Through a simulation, it was verified that the boiler efficiency was improved by controlling the combustion air. In addition, an average increase in boiler efficiency of 0.29% was confirmed by applying it directly to the generator operating on-site. The results of this study are expected to contribute to annual cost savings, with a reduction of USD 217,000 in electricity purchasing costs and USD 19,700 in greenhouse gas emissions trading expenses. [ABSTRACT FROM AUTHOR]

The damage caused by fire accidents is increasing worldwide. In particular, when a fire occurs, property damage directly affects the lives of citizens. Therefore, in this study, machine learning techniques were applied to analyze the prediction of the future amount of property damage from fire as well as the fire occurrence factors within a geographic area. To achieve this, three years of spatially distributed fire big data for Seoul, the capital of Korea, was used. For the predictive analysis of the amount of fire property damage, the results of analysis by applying machine learning techniques through k-fold cross-validation were calculated. As part of these results, when predicting and analyzing the amount of fire property damage using the random forest (RF) algorithm, an accuracy of 83% was calculated by comparing the predicted data with the actual data. On this basis, the importance of the fire risk factors was analyzed, and it was found that the main factor in the occurrence of fires is the condition of the facilities inside apartment houses. The findings of this study are expected to be used as an important guide for identifying property damage by fire and the factors determining the occurrence of fires in Korea, enabling the evaluation of their spatial distribution and the application of corrective measures to reduce possible damage by urban fires. [ABSTRACT FROM AUTHOR]

Soil moisture (SM) is an indicator of the moisture status of the land surface, which is useful for monitoring extreme weather events. Representative global SM datasets include the National Aeronautics and Space Administration (NASA) Soil Moisture Active Passive (SMAP), the Global Land Data Assimilation System (GLDAS), and the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis 5 (ERA5), but due to their low spatial resolutions, none of these datasets well describe SM changes in local areas, and they tend to have a low accuracy. Machine learning (ML)-based SM predictions have demonstrated high accuracy, but obtaining semi-real-time SM information remains challenging, and the dependence of the validation accuracy on the data sampling method used, such as random or yearly sampling, has led to uncertainties. In this study, we aimed to develop an ML-based model for real-time SM estimation that can capture local-scale variabilities in SM and have reliable accuracy, regardless of the sampling method. This study was conducted in South Korea, and satellite image data, numerical weather prediction (NWP) data, and topographic data provided within one day were used as the input data. For SM modeling, 13 input variables affecting the surface SM status were selected: 10- and 20-day cumulative standardized precipitation indexes (SPI10 and SPI20), a normalized difference vegetation index (NDVI), downward shortwave radiation (DSR), air temperature (Tair), land surface temperature (LST), soil temperature (Tsoil), relative humidity (RH), latent heat flux (LE), slope, elevation, topographic ruggedness index (TRI), and aspect. Then, SM models based on random forest (RF) and automated machine learning (AutoML) were constructed, trained, and validated using random sampling and leave-one-year-out (LOYO) cross-validation. The RF- and AutoML-based SM models had significantly high accuracy rates based on comparisons with in situ SM (mean absolute error (MAE) = 2.212–4.132%; mean bias error (MBE) = −0.110–0.136%; root mean square error (RMSE) = 3.186–5.384%; correlation coefficient (CC) = 0.732–0.913), while the AutoML-based SM model tended to have a higher accuracy than the RF-based SM model, regardless of the data sampling method used. In addition, when compared to in situ SM data, the SM models demonstrated the highest accuracy, outperforming both GLDAS and ERA5 SM data and well representing changes in the dryness/wetness of the land surface according to meteorological events (heatwave, drought, and rainfall). The SM models proposed in this study can, thus, offer semi-real-time SM data, aiding in the monitoring of moisture changes in the land surface, as well as short-term meteorological disasters, like flash droughts or floods. [ABSTRACT FROM AUTHOR]

Artemisia argyi has been widely used as an herbal medicine and food in South Korea. However, the harvesting time of A. argyi is still not known. In addition, quality-based classification of A. argyi used for consumption is necessary because of its pharmacological properties. To this end, the A. argyi harvesting time was determined, and quality grading of A. argyi was performed based on the following factors: the contents of eupatilin, jaceosidin, essential oils and the leaf weight ratio. It is appropriate to harvest A. argyi at the end of June in 2019 and the plants harvested in early July exhibit the highest quality, considering weather condition and statistical analyses. To grade the quality of A. argyi, machine learning algorithms were applied based on the aforementioned four components. Among the various models, the logistic regression model showed the best performance, with an area under the receiver operating characteristic curve of 0.906. In this study, we developed methods for determining the harvest time and classifying its quality so that it can be applied to different weather conditions every year with precision. [ABSTRACT FROM AUTHOR]

This study aimed to assess factors affecting pregnancy intention among women of reproductive age in Korea. We analyzed data from the Korean National Health and Nutrition Examination Survey (KNHANES), a population-based survey that included 22,731 women aged 15–49. As age was associated with birth year and was found to be a confounding factor in the analysis of participants' characteristics, we used propensity score matching to assess the characteristics of pregnant women compared with non-pregnant women of the same age and birth year. We also employed the XGBoost machine learning model to identify the most important factors related to pregnancy intentions. Our feature importance analysis showed that weekly working hours were the most significant factor affecting pregnancy intentions. Additionally, we performed cluster analysis and logistic regression models to determine optimal weekly working hours. Cluster analysis identified participants into three distinct groups based on their characteristics, indicating that the group with an average of 34.4±12.9 hours per week had the highest likelihood of becoming pregnant. Logistic regression was used to analyze the odds of pregnancy for every 5-hour increase in weekly working hours. The results of logistic regression indicated that women who worked between 35–45 hours per week had higher odds of pregnancy, with significant odds ratios of 2.009 (95% confidence interval: 1.581–2.547, p <.001) for 40–45 hours per week and 1.450 (95% confidence interval: 1.001–2.040, p <.05) for 35–40 hours per week, compared to women working other hours. In Korea, the standard workweek is typically 40 hours; however, Koreans often work considerably longer hours, with the second-highest number of working hours among OECD countries in 2022. This study suggests that strict monitoring of working hours and expansion of telecommuting for childbearing-age women are important factors in increasing the fertility rate in Korea. [ABSTRACT FROM AUTHOR]

COVID-19 has further aggravated problems by compelling people to stay indoors and limit social interactions, leading to a worsening of the depression situation. This study aimed to construct a TabNet model combined with SHapley Additive exPlanations (SHAP) to predict depression in South Korean society during the COVID-19 pandemic. We used a tabular dataset extracted from the Seoul Welfare Survey with a total of 3027 samples. The TabNet model was trained on this dataset, and its performance was compared to that of several other machine learning models, including Random Forest, eXtreme Gradient Boosting, Light Gradient Boosting, and CatBoost. According to the results, the TabNet model achieved an Area under the receiver operating characteristic curve value (AUC) of 0.9957 on the training set and an AUC of 0.9937 on the test set. Additionally, the study investigated the TabNet model's local interpretability using SHapley Additive exPlanations (SHAP) to provide post hoc global and local explanations for the proposed model. By combining the TabNet model with SHAP, our proposed model might offer a valuable tool for professionals in social fields, and psychologists without expert knowledge in the field of data analysis can easily comprehend the decision-making process of this AI model. [ABSTRACT FROM AUTHOR]

This study compares the bias correction techniques of empirical quantile mapping (QM) and the Long Short-Term Memory (LSTM) machine learning model for summertime daily rainfall simulation focusing on precipitation-dependent bias and temporal variation. Numerical experiments using Weather Research and Forecasting (WRF) were conducted over South Korea with lateral boundary conditions of ERA5 reanalysis data. For the spatial distribution of mean summertime rainfall, the bias-uncorrected WRF simulation (WRF_RAW) showed dry bias for most of the region of South Korea. The WRF results corrected by QM and LSTM (WRF_QM and WRF_LSTM, respectively) were improved for the mean summer rainfall simulation with the root mean square error values of 0.17 and 0.69, respectively, which were smaller than those of the WRF_RAW (1.10). Although the WRF_QM performed better than the WRF_LSTM in terms of the summertime mean and monthly precipitation, the WRF_LSTM presented a closer interannual rainfall variation to the observation than the WRF_QM. The coefficient of determination for calendar-day mean rainfall was the highest in the following order: the WRF_LSTM (0.451), WRF_QM (0.230), and WRF_RAW (0.201). However, the WRF_LSTM had a limitation in reproducing extreme rainfall exceeding 50 mm/day due to the few cases of extreme precipitation in training data. Nevertheless, the WRF_LSTM better simulated the observed light-to-moderate precipitation (10–50 mm/day) than the others. [ABSTRACT FROM AUTHOR]

According to BBC News, online hate speech increased by 20% during the COVID-19 pandemic. Hate speech from anonymous users can result in psychological harm, including depression and trauma, and can even lead to suicide. Malicious online comments are increasingly becoming a social and cultural problem. It is therefore critical to detect such comments at the national level and detect malicious users at the corporate level. To achieve a healthy and safe Internet environment, studies should focus on institutional and technical topics. The detection of toxic comments can create a safe online environment. In this study, to detect malicious comments, we used approximately 9,400 examples of hate speech from a Korean corpus of entertainment news comments. We developed toxic comment classification models using supervised learning algorithms, including decision trees, random forest, a support vector machine, and K-nearest neighbors. The proposed model uses random forests to classify toxic words, achieving an F1-score of 0.94. We analyzed the trained model using the permutation feature importance, which is an explanatory machine learning method. Our experimental results confirmed that the toxic comment classifier properly classified hate words used in Korea. Using this research methodology, the proposed method can create a healthy Internet environment by detecting malicious comments written in Korean. [ABSTRACT FROM AUTHOR]

Background: A considerable volume of possible applications of artificial intelligence (AI) in the field of rhinology exists, and research in the area is rapidly evolving. Objective: This scoping review aims to provide a brief overview of all current literature on AI in the field of rhinology. Further, it aims to highlight gaps in the literature for future rhinology researchers. Methods: OVID MEDLINE (1946-2022) and EMBASE (1974-2022) were searched from January 1, 2017 until May 14, 2022 to identify all relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews checklist was used to guide the review. Results: A total of 2420 results were identified of which 62 met the eligibility criteria. A further 17 articles were included through bibliography searching, for a total of 79 articles on AI in rhinology. Each year resulted in an increase in the number of publications, from 3 articles published in 2017 to 31 articles published in 2021. Articles were produced by authors from 22 countries with a relative majority coming from the USA (19%), China (19%), and South Korea (13%). Articles were placed into 1 of 5 categories: phenotyping/endotyping (n = 12), radiological diagnostics (n = 42), prognostication (n = 10), non-radiological diagnostics (n = 7), surgical assessment/planning (n = 8). Diagnostic or prognostic utility of the AI algorithms were rated as excellent (n = 29), very good (n = 25), good (n = 7), sufficient (n = 1), bad (n = 2), or was not reported/not applicable (n = 15). Conclusions: AI is experiencing an increasingly significant role in rhinology research. Articles are showing high rates of diagnostic accuracy and are being published at an almost exponential rate around the world. Utilizing AI in radiological diagnosis was the most published topic of research, however, AI in rhinology is still in its infancy and there are several topics yet to be thoroughly explored. [ABSTRACT FROM AUTHOR]

Background: In today's digital economy, enterprises are adopting collaboration software to facilitate digital transformation. However, if employees are not satisfied with the collaboration software, it can hinder enterprises from achieving the expected benefits. Although existing literature has contributed to user satisfaction after the introduction of collaboration software, there are gaps in predicting user satisfaction before its implementation. To address this gap, this study offers a machine learningbased forecasting method. Methods: We utilized national public data provided by the national information society agency of South Korea. To enable the data to be used in a machine learningbased binary classifier, we discretized the predictor variable. We then validated the effectiveness of our prediction model by calculating feature importance scores and prediction accuracy. Results: We identified 10 key factors that can predict user satisfaction. Furthermore, our analysis indicated that the naive Bayes (NB) classifier achieved the highest prediction accuracy rate of 0.780, followed by logistic regression (LR) at 0.767, extreme gradient boosting (XGBoost) at 0.744, support vector machine (SVM) at 0.744, K-nearest neighbor (KNN) at 0.707, and decision tree (DT) at 0.637. Conclusions: This research identifies essential indicators that can predict user satisfaction with collaboration software across four levels: institutional guidance, information and communication technology (ICT) environment, company culture, and demographics. Enterprises can use this information to evaluate their current collaboration status and develop strategies for introducing collaboration software. Furthermore, this study presents a novel approach to predicting user satisfaction and confirm the effectiveness of the machine learning-based prediction method proposed in this study, adding to the existing knowledge on the subject. [ABSTRACT FROM AUTHOR]

The severity and incidence of flash floods are increasing in forested regions, causing significant harm to residents and the environment. Consequently, accurate estimation of flood peaks is crucial. As conventional physically based prediction models reflect the traits of only a small number of areas, applying them in ungauged catchments is challenging. The interrelationship between catchment characteristics and flood features to estimate flood peaks in ungauged areas remains underexplored, and evaluation standards for the appropriate number of flood events to include during data collection to ensure effective flood peak prediction have not been established. Therefore, we developed a machine-learning predictive model for flood peaks in ungauged areas and determined the minimum number of flood events required for effective prediction. We employed rainfall-runoff data and catchment characteristics for estimating flood peaks. The applicability of the machine learning model for ungauged areas was confirmed by the high predictive performance. Even with the addition of rainfall-runoff data from ungauged areas, the predictive performance did not significantly improve when sufficient flood data were used as input data. This criterion could facilitate the determination of the minimum number of flood events for developing adequate flood peak predictive models. [ABSTRACT FROM AUTHOR]

Recently, equipment replacement and maintenance repair and operation (MRO) optimization have substantially increased owing to the aging and deterioration of industrial plants, such as steel-making factories in Korea. Therefore, plant owners are required to quickly review equipment supply contracts, i.e., purchase order (PO) documents, with suppliers and vendors. Currently, there is inconsistency in the time and quality required for the PO document review process by engineers, depending on their manual skills and practice. This study developed a general provisions question-answering model (GPQAM) by combining knowledge graph (KG) and question-answering (QA) techniques to search for semantically connected contract clauses through the definition of relationships between entities during the review of equipment purchase contracts. The PO documents analyzed in this case study were based on one steel-making company's general provisions (GP). GPQAM is a machine learning (ML)-based model with two sub-models (i.e., KG and QA) that automatically generates the most relevant answers to semantic search questions through a cypher query statement in GP for the PO engineers. First, based on the developed GP lexicon and its classifying taxonomy to be stored in the Neo4j graph database (GDB), the KG sub-model finds the corresponding synonyms and consequently shows GP-related information in a graphic form. Second, the QA sub-model is a function to find and answer contract information within the KG and applies pattern-matching technology based on the Aho–Corasick (AC) algorithm. Third, nodes with the meaning most similar to the question are selected using similarity measurement if a response cannot be extracted through the pattern-matching process. Forty-five pilot test questions were created and applied to the GPQAM model evaluation. The F1 score was 82.8%, indicating that the unsupervised training methods developed in this study could be better applied to a semantic QA process in plant engineering documents, where sufficient training data are limited and bargained. An expert survey of PO practitioners confirmed that the semantic QA capability of GPQAM might be efficient and useful for their work. As the first case of applying KG technology to semantic QA for plant equipment PO contracts, this study might be a meaningful contribution to the steel plant industry and, therefore, extended to construction and engineering contract applications. [ABSTRACT FROM AUTHOR]

Data is growing quickly due to a significant increase in social media applications. Today, billions of people use an enormous amount of data to access the Internet. The backbone network experiences a substantial load as a result of an increase in users. Users in the same region or company frequently ask for similar material, especially on social media platforms. The subsequent request for the same content can be satisfied from the edge if stored in proximity to the user. Applications that require relatively low latency can use Content Delivery Network (CDN) technology to meet their requirements. An edge and the data center constitute the CDN architecture. To fulfill requests from the edge and minimize the impact on the network, the requested content can be buffered closer to the user device. Which content should be kept on the edge is the primary concern. The cache policy has been optimized using various conventional and unconventional methods, but they have yet to include the timestamp beside a video request. The 24-h content request pattern was obtained from publicly available datasets. The popularity of a video is influenced by the time of day, as shown by a time-based video profile. We present a cache optimization method based on a time-based pattern of requests. The problem is described as a cache hit ratio maximization problem emphasizing a relevance score and machine learning model accuracy. A model predicts the video to be cached in the next time stamp, and the relevance score identifies the video to be removed from the cache. Afterwards, we gather the logs and generate the content requests using an extracted video request pattern. These logs are pre-processed to create a dataset divided into three-time slots per day. A Long short-term memory (LSTM) model is trained on this dataset to forecast the video at the next time interval. The proposed optimized caching policy is evaluated on our CDN architecture deployed on the Korean Advanced Research Network (KOREN) infrastructure. Our findings demonstrate how adding time-based request patterns impacts the system by increasing the cache hit rate. To show the effectiveness of the proposed model, we compare the results with state-of-the-art techniques. [ABSTRACT FROM AUTHOR]