Search

With the increase in both rainfall and intensity due to climate change, the risk of debris flows is also increasing. In Korea, the increasing damage caused by debris flows has become a social issue, and research on debris-flow response is becoming increasingly important. Understanding the rainfall that induces debris flows is crucial for debris-flow response, and methods such as the I-D method have been used to evaluate and predict the risk of debris flows. However, previous studies on debris flow-induced rainfall analysis have been limited by the subjective decision of the researcher to select the impact meteorological stations, which greatly affects reliability. In this paper, in order to establish an objective standard, various maximum allowable distances between debris-flow disaster areas and meteorological stations were adjusted to 1, 3, 5, 7, 9, 11, 13, and 15 km using the CTRL-T automatic calculation algorithm, and the optimal maximum allowable distance suitable for Korean terrain was derived through parameter sensitivity analysis. Based on this, we developed a nomogram for sediment disaster risk prediction and warning in Gangwon-do, and applied it to past disaster cases, and found that, although the prediction time for each stage varies depending on the maximum allowable distance, on average, it is possible to predict the risk of sediment flows 4 to 5 h in advance. It is believed that the results of this study can be used to reduce sediment flow damage in advance. [ABSTRACT FROM AUTHOR]

In recent years, autonomous mobile platforms have seen an increase in usage in several applications. One of which is street-sweeping. Although street-sweeping is a necessary process due to health and cleanliness, fleet operations are difficult to plan optimally. Since each vehicle has several constraints (battery, debris, and water), path planning becomes increasingly difficult to perform manually. Additionally, in real-world applications vehicles may become inactive due to a breakdown, which requires real-time scheduling technology to update the paths for the remaining vehicles. In this paper, the fleet street-sweeping problem can be solved using the proposed lower-level and higher-level path generation methods. For the lower level, a Smart Selective Navigator algorithm is proposed, and a modified genetic algorithm is used for the higher-level path planning. A case study was presented for Uchi Park, South Korea, where the proposed methodology was validated. Specifically, results generated from the ideal scenario (all vehicles operating) were compared to the breakdown scenario, where little to no difference in the overall statistics was observed. Additionally, the lower-level path generation could yield solutions with over 94% area coverage. [ABSTRACT FROM AUTHOR]

Currently, cryptographic hash functions are widely used in various applications, including message authentication codes, cryptographic random generators, digital signatures, key derivation functions, and post-quantum algorithms. Notably, they play a vital role in establishing secure communication between servers and clients. Specifically, servers often need to compute a large number of hash functions simultaneously to provide smooth services to connected clients. In this paper, we present highly optimized parallel implementations of Lightweight Secure Hash (LSH), a hash algorithm developed in Korea, on server sides. To optimize LSH performance, we leverage two parallel architectures: AVX-512 on high-end CPUs and NVIDIA GPUs. In essence, we introduce a word-level parallel processing design suitable for AVX-512 instruction sets and a data parallel processing design appropriate for the NVIDIA CUDA platform. In the former approach, we parallelize the core functions of LSH using AVX-512 registers and instructions. As a result, our first implementation achieves a performance improvement of up to 50.37% compared to the latest LSH AVX-2 implementation. In the latter approach, we optimize the core operation of LSH with CUDA PTX assembly and apply a coalesced memory access pattern. Furthermore, we determine the optimal number of blocks/threads configuration and CUDA streams for RTX 2080Ti and RTX 3090. Consequently, in the RTX 3090 architecture, our optimized CUDA implementation achieves about a 180.62% performance improvement compared with the initially ported LSH implementation to the CUDA platform. As far as we know, this is the first work on optimizing LSH with AVX-512 and NVIDIA GPU. The proposed implementation methodologies can be used alone or together in a server environment to achieve the maximum throughput of LSH computation. [ABSTRACT FROM AUTHOR]

A number of accidents at sea are primarily caused by low visibility due to sea fog. Therefore, it is important to estimate sea fog intensity and visibility in real-time in the ocean environment. Visibility meters utilize optical sensors rather than visional information, so that the measured visibility data occasionally includes errors. Moreover, visibility meters have significant costs so that it is not viable to install them at various locations. Therefore, this paper proposes an algorithm called RDCP (Reduced Dark Channel Prior), which provides reliable estimation at a low cost by processing images captured from cameras, since they receive identical information as human eyes. For the estimation, the RDCP algorithm firstly acquires dark channels from an ocean image, then applies an optimized threshold value to the dark channels and crops out the sky region in the ocean image. For the estimation performance evaluation, 320 raw images captured from cameras at four different ports in Republic of Korea are used. Considering facilities in oceans, which are usually operated in power-limited environment, the processing time performance of PDCP is also examined. The experiments demonstrate that the RDCP algorithm provides reliable estimation performance in real-time. [ABSTRACT FROM AUTHOR]

Problems with overvoltage and reverse energy flow arise as the percentage of distribution energy resources (DERs) in distribution system rises. This paper implements a MATLAB/Simulink linked model that communicates with the OpenDSS engine. The point of common coupling (PCC) voltage typically mitigates using the inverter outputs control. However, case overvoltage issues occur in distribution networks and the influence of the volt–var control effect is insufficient to reduce PCC voltage to a stable range. To improve the reactive control effect, this paper proposes active power control and voltage error compensation methods that maximize the reactive power control effect. The DER management system (DERMS) platform was constructed to analyze the effect of changing DER output values. The DERMS data are organized based on real distribution line (D/L) system data where overvoltage occurred in Korea and the control effect of the real system is analyzed. This control method analysis can be used to develop an inverter control scheme for the over voltage issues described in this paper. [ABSTRACT FROM AUTHOR]

Summary: In this paper, a new technique is suggested for best electric load forecasting of South Korea. The proposed study is based on an improved metaheuristic methodology. This paper proposes a new improved version of Support Vector Machine for Regression (SVR) base on the proposed algorithm. The algorithm is based on a modified version of Crow Search Algorithm (ACSA), where, by combining by the SVR, generates an efficient classifier. Although, different drawbacks of using original CSA are stated, the proposed ACSA method provides a proper modification for resolving of these shortcomings. The forecasting model has been then performed to a historical data from South Korea to indicate the algorithm efficiency and the results are compared with some other methods, including SVR‐CGA, SVR‐CAS, ANN, and simple Regression to show the suggested method performance. Final results show that MAPD, MSE, and RMSE values of the test data with lower values for South, North, Center, and East, provided better results based on the proposed SVR‐ACSA based on different values of center and kernel of the SVR. Experimental results on the case study shows that the minimum MAPD has been added which is happened in Northern regional is 1.1062, 1.1336, 1.1065, 1.02, 2.23, 1.96, and 1.49 for SVR‐ACSA, SVR‐CGA, SVR‐CAS, ANN, Regression, LSTM‐RNN, and ELM which indicates the method's higher efficiency. [ABSTRACT FROM AUTHOR]

Summary: The fused lasso signal approximator (FLSA) is a smoothing procedure for noisy observations that uses fused lasso penalty on unobserved mean levels to find sparse signal blocks. Several path algorithms have been developed to obtain the whole solution path of the FLSA. However, it is known that the FLSA has model selection inconsistency when the underlying signals have a stair‐case block, where three consecutive signal blocks are either strictly increasing or decreasing. Modified path algorithms for the FLSA have been proposed to guarantee model selection consistency regardless of the stair‐case block. In this paper, we provide a comprehensive review of the path algorithms for the FLSA and prove the properties of the recently modified path algorithms' hitting times. Specifically, we reinterpret the modified path algorithm as the path algorithm for local FLSA problems and reveal the condition that the hitting time for the fusion of the modified path algorithm is not monotone in a tuning parameter. To recover the monotonicity of the solution path, we propose a pathwise adaptive FLSA having monotonicity with similar performance as the modified solution path algorithm. Finally, we apply the proposed method to the number of daily‐confirmed cases of COVID‐19 in Korea to identify the change points of its spread. [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]

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]

Weighting the Hanwoo (Korean cattle) is very important for Korean beef producers when selling the Hanwoo at the right time. Recently, research is being conducted on the automatic prediction of the weight of Hanwoo only through images with the achievement of research using deep learning and image recognition. In this paper, we propose a method for the automatic weight prediction of Hanwoo using the Bayesian ridge algorithm on RGB-D images. The proposed system consists of three parts: segmentation, extraction of features, and estimation of the weight of Korean cattle from a given RGB-D image. The first step is to segment the Hanwoo area from a given RGB-D image using depth information and color information, respectively, and then combine them to perform optimal segmentation. Additionally, we correct the posture using ellipse fitting on segmented body image. The second step is to extract features for weight prediction from the segmented Hanwoo image. We extracted three features: size, shape, and gradients. The third step is to find the optimal machine learning model by comparing eight types of well-known machine learning models. In this step, we compared each model with the aim of finding an efficient model that is lightweight and can be used in an embedded system in the real field. To evaluate the performance of the proposed weight prediction system, we collected 353 RGB-D images from livestock farms in Wonju, Gangwon-do in Korea. In the experimental results, random forest showed the best performance, and the Bayesian ridge model is the second best in MSE or the coefficient of determination. However, we suggest that the Bayesian ridge model is the most optimal model in the aspect of time complexity and space complexity. Finally, it is expected that the proposed system will be casually used to determine the shipping time of Hanwoo in wild farms for a portable commercial device. [ABSTRACT FROM AUTHOR]

Recent changes in medical education and assessment led to a focus on occupational competency, and this study investigated the perceptions of Korean medicine doctors (KMDs) on the national licensing examination for KMDs (NLE-KMD). The survey aimed to understand KMDs' recognition of the current situation, items to improve, and items to emphasize in the future. We conducted the web-based survey from 22 February to 4 March 2022, and 1244 among 23,338 KMDs answered voluntarily. Through this study, we found the importance of competency-related clinical practice and Korean standard classification of disease (KCD), and the presence of a generation gap. KMDs considered clinical practice (clinical tasks and clinical work performance) and the item related to the KCD important. They valued (1) the focus on KCD diseases that are frequently seen in clinical practice and (2) the readjustment and introduction of the clinical skills test. They also emphasized KCD-related knowledge and skills for the assessment and diagnosis of KCD diseases, especially those frequently treated at primary healthcare institutes. We confirmed the generation gap in the subgroup analysis according to the license acquisition period, and the ≤5-year group emphasized clinical practice and the KCD, while the >5-year group stressed traditional KM theory and clinical practice guidelines. These findings could be used to develop the NLE-KMD by setting the direction of Korean medicine education and guiding further research from other perspectives. [ABSTRACT FROM AUTHOR]

Background This study aimed to assess the specific associations between stroke and all-cause and cause-specific mortality among Korean adults. Methods We used data extracted from the Korean National Health Insurance claims database from 2002 to 2013, including information on individuals with or without stroke aged 20 years and older. Patients with intracerebral hemorrhage, ischemic stroke or unspecified stroke were classified as stroke patients, while a reference population matched in terms of sex and age were also selected. The outcomes were all-cause mortality, natural causes of death (i.e. all natural causes, death by stroke and death by other diseases) and suicide. Survival analysis was performed using the Cox proportional hazards model. Results Of the 73 150 eligible participants—including 14 630 stroke patients and 58 520 age- and sex-matched controls—11 121 (15.2%) died during the study period. Of them, 10 513 participants (94.5%) died of natural causes, including 1653 (14.5%) who died due to stroke and 8860 (79.7%) who died due to other diseases. Two hundred and fifty patients (2.2%) died by suicide. Stroke patients showed higher adjusted hazard ratios (HR) for all-cause (HR = 6.48, 95% CI, 3.87–10.86), all-natural-cause (HR = 2.68, 95% CI, 2.53–2.84), stroke (HR = 21.16, 95% CI, 17.49–25.61), other disease (HR = 1.69, 95% CI, 1.58–1.81) and suicide mortality (HR = 3.34, 95% CI, 2.24–4.98) than those without stroke. The effect size of stroke for suicide mortality was greater than that for other causes of mortality (except stroke mortality). Conclusions Stroke was associated with a higher risk of all-cause, natural cause and suicide mortality; stroke was more strongly associated with risk of suicide mortality than with any mortality for any other causes. From a policy standpoint, these results suggest the need for greater supportive care to prevent unnatural deaths among stroke patients. [ABSTRACT FROM AUTHOR]

In radar operations, the detection performance is reduced owing to various external factors. These factors include interference and other targets, as well as losses from the atmosphere and terrain. Because of its geomorphic characteristics, radar operating in Korea is affected by interference, and its performance is degraded. This paper describes the simulation of the environment of near-radar interference and multiple targets. The modeling and simulation (M&S) tool was developed to predict and prevent the degradation in radar performance in advance. We validated existing constant false alarm rate (CFAR) detection algorithms by generating signals through the M&S tool and proposed a new CFAR algorithm to enhance the radar performance. Consequently, radar performance is enhanced by the new CFAR algorithm in radar interference and multiple target environments. [ABSTRACT FROM AUTHOR]

Background: Although the optimal use of prescribed medications for stroke survivors is critical for preventing secondary stroke, longitudinal observations of the natural course of medication persistence and adherence in Korean stroke survivors are rare. Furthermore, studies are needed to identify strong predictors influencing medication adherence and to determine whether these predictors change over time. Aims and objectives: To evaluate the longitudinal medication persistence and adherence at 3 months and 1 year after discharge in all stroke patients and to identify predictors of long‐term medication adherence in patients who can self‐medicate. Design: A multicentre, prospective, longitudinal descriptive study. Methods: A total of 600 consecutive ischaemic stroke patients were recruited from three stroke centres across Korea, from 1 September, 2017 to 28 February, 2019. Various factors related to medication adherence suggested by the World Health Organisation were investigated through face‐to‐face interviews at each centre during hospitalisation. Medication persistence and adherence were assessed at 3 months and 1 year after discharge using the eight‐item Morisky Medication Adherence Scale through telephone interviews. Results: Of 537 survivors at 3 months, 526 (98.0%) were persistent and 472 (89.7%) were adherent. Of 493 survivors at 1 year, 477 (96.8%) were persistent and 392 (82.2%) were adherent. Medication belief, income and health literacy were statistically significant predictors of three‐month medication adherence, which predicted one‐year medication adherence with older age and low income. Conclusions: Among Korean stroke survivors, three‐month and one‐year medication persistence and adherence were relatively good. Medication beliefs and three‐month medication adherence were important and modifiable factors predicting three‐month adherence and one‐year adherence, respectively. Relevance to clinical practice: To increase long‐term adherence to medication, various strategies are needed to improve beliefs about medication, taking into account the patient's age and level of knowledge. These interventions need to be initiated during hospitalisation to form early medication habits after discharge. [ABSTRACT FROM AUTHOR]

Aims and objectives: This study aimed to determine the effect of overtime on alertness at work among rotating‐shift nurses in South Korea and to investigate whether these effects of overtime vary across the different types of shifts. Background: Nurse overtime is prevalent in healthcare settings to manage nursing shortages and staffing needs; however, it negatively affects patient and nurse outcomes. Furthermore, little attention has been paid to the effects of previous overtime shifts and overtime for consecutive shifts on alertness during work. Design: A prospective observational study was employed. The study followed STROBE checklist for observational studies. Methods: Data were collected between June 2019 and February 2020 from 82 nurses who worked in acute care hospitals. An ecological momentary assessment was used to capture real‐time data of overtime and alertness. Alertness scores were estimated using the sleep/wake data measured by an actigraph. Mixed‐effect models were employed to investigate the association between overtime and alertness. Results: A majority of the shift nurses worked overtime. Episodes of a decline in alertness scores to the level of increased accident or serious error risk (alertness score ≤80) were most frequently seen during night shifts (98.9%), followed by day (59.8%) and evening shifts (10.1%). Previous‐day overtime hours and consecutive overtime days were associated with decreased alertness scores during work. A significantly positive correlation was observed between alertness scores ≤80 and previous‐day overtime hours and consecutive overtime days in all shifts. Conclusions: The study findings indicate that a majority of nurses who work overtime experience decreased alertness while on duty. Relevance to clinical practice: Policy development at the government, organisational and unit level is needed to guarantee adequate rest for shift nurses by adjusting work schedules and assignments and limiting overtime. [ABSTRACT FROM AUTHOR]

Reducing antibiotics overuse is essential to minimize antibiotics related side effects and to prevent the emergence of multidrug-resistant bacteria. Procalcitonin (PCT) guided antibiotics therapy has been reported to be safe in patients with acute respiratory infections and sepsis, improving clinical outcomes as well as reducing the duration of antibiotics use. However, there is still no universal agreement on clinical guidelines in Korea for optimal PCT applications. Through this expert consensus meeting, clinical research findings in the PCT-guided antibiotics treatment interventions and real-world clinical applications were discussed. From the perspective of antibiotic stewardship, PCT application target groups, cut-offs, and testing cycles were discussed to reach a consensus on the PCT-guided antibiotics treatment algorithm for application in Korea. Combining clinical assessment for patients with an appropriate PCT-guided antibiotics treatment algorithm could improve the diagnosis and treatment of acute respiratory infections and sepsis. In addition, continuous education and regular feedback would improve the effectiveness of antibiotic stewardship. [ABSTRACT FROM AUTHOR]

This study identifies the roots of inequality of opportunity in South Korea by applying algorithmic approaches to survey data. In contrast to extant studies, we identify the roots of inequality of opportunity by estimating the importance of variables, interpreting the estimated results, and analyzing the importance of individual variables, instead of measuring inequality of opportunity. We apply a decision tree classification algorithm, light gradient boosting machine, and SHapley Additive exPlanations to estimate the importance of the studied variables and interpret the estimated results. According to the estimated results, the region where the individuals grew up, their gender, and their father's job during their childhood were the main factors contributing to inequality of opportunity. This study proves that the considerable regional disparity and social environment perpetuate gender inequality in South Korean society. It argues that an individual's socio-economic achievements are strongly influenced by their father's background, thus, outweighing other family background-related factors. Individuals receive unequal opportunities owing to a combination of region, father's background, and their own gender, thereby, affecting their socioeconomic achievements. If these factors remain influential from birth to adulthood, removing the conditions that structure them would be one way to achieve equality of opportunity. [ABSTRACT FROM AUTHOR]

How does attitude to death influence consumption level and profiles and conversely? The database is a representative follow-up of Korean respondents from 2006 to 2016. Satisfaction with quality of life is combined with endogenous consumption level, consumption patterns, deviation from expected mortality—the propensity for dying—, and wealth. Exogenous variables include sex, age, education, children, place of residence, and employment. Satisfaction decreases with age; women are less satisfied and anticipate higher mortality than men. Older people anticipate an age-specific mortality rate that increases only linearly with age, while mortality actually increases exponentially. This cognitive bias, due to the fact that people perceive linear progressions but find it difficult to project themselves over time, leads them to overestimate their satisfaction in terms of quality of life, thus creating a protective effect on well-being, to the detriment of accurate economic visibility of the life cycle. [ABSTRACT FROM AUTHOR]

The size of phytoplankton (a key primary producer in marine ecosystems) is known to influence the contribution of primary productivity and the upper trophic level of the food web. Therefore, it is essential to identify the dominant sizes of phytoplankton while inferring the responses of marine ecosystems to change in the marine environment. However, there are few studies on the spatio-temporal variations in the dominant sizes of phytoplankton in the littoral sea of Korea. This study utilized a deep learning model as a classification algorithm to identify the dominance of different phytoplankton sizes. To train the deep learning model, we used field measurements of turbidity, water temperature, and phytoplankton size composition (chlorophyll-a) in the littoral sea of Korea, from 2018 to 2020. The new classification algorithm from the deep learning model yielded an accuracy of 70%, indicating an improvement compared with the existing classification algorithms. The developed classification algorithm could be substituted in satellite ocean color data. This enabled us to identify spatio-temporal variation in phytoplankton size composition in the littoral sea of Korea. We consider this to be highly effective as fundamental data for identifying the spatio-temporal variation in marine ecosystems in the littoral sea of Korea. [ABSTRACT FROM AUTHOR]

Remote sensing snowfall retrievals are powerful tools for advancing our understanding of global snow accumulation patterns. However, current satellite-based snowfall retrievals rely on assumptions about snowfall particle shape, size, and distribution that contribute to uncertainty and biases in their estimates. Vertical radar reflectivity profiles provided by the vertically pointing X-band radar (VertiX) instrument in Egbert, Ontario, Canada, are compared with in situ surface snow accumulation measurements from January to March 2012 as a part of the Global Precipitation Measurement (GPM) Cold Season Precipitation Experiment (GCPEx). In this work, we train a random forest (RF) machine learning model on VertiX radar profiles and ERA5 atmospheric temperature estimates to derive a surface snow accumulation regression model. Using event-based training–testing sets, the RF model demonstrates high predictive skill in estimating surface snow accumulation at 5-min intervals with a low mean-square error of approximately 1.8 × 10−3 mm2 when compared with collocated in situ measurements. The machine learning model outperformed other common radar-based snowfall retrievals (Ze–S relationships) that were unable to accurately capture the magnitudes of peaks and troughs in observed snow accumulation. The RF model also displayed consistent skill when applied to unseen data at a separate experimental site in South Korea. An estimate of predictor importance from the RF model reveals that combinations of multiple reflectivity measurement bins in the boundary layer below 2 km were the most significant features in predicting snow accumulation. Nonlinear machine learning–based retrievals like those explored in this work can offer new, important insights into global snow accumulation patterns and overcome traditional challenges resulting from sparse in situ observational networks. [ABSTRACT FROM AUTHOR]

The Building Supervision of South Korea has been developed under the government′s desire to prevent poor construction and improve the quality of buildings to promote a safer life for the people. Although the building environment of today has been achieved through several improvements, the introduction of such technology is insufficient. Especially since building supervision is primarily carried out almost by manpower, in an era where numerous convergence technologies from the 4th industry are being utilized. Therefore, this study aimed to solve this inefficiency in the building supervision system by using the object detection technology of deep learning in the BIM environment. As a basic study to develop a smart supervision checking system that checks whether the information on the construction site matches the design information, the column ties were selected as a supervision item, and research was conducted. For this, we constructed the tie detection network and suggested an algorithm for information checking between the construction site and BIM environment. Through this, it was possible to confirm the possibility of practical supervision work and improve the efficiency of the work, and furthermore, to see the possibility of using convergence technology. [ABSTRACT FROM AUTHOR]

With the growing interest in smart factories, defect-prediction algorithms using data analysis techniques are being developed and applied to solve problems caused by defects at manufacturing sites. Cost benefit is an important factor to consider, and can be obtained by applying such algorithms. Existing defect-prediction algorithms usually aim to reduce the error rate of the prediction model, rather than focusing on the cost benefit for the practical application of defect-prediction models. Therefore, this study develops a defect-prediction algorithm considering costs and systematization for field application. To this end, a type error-weighted deep neural network (TEW-DNN) is proposed that applies a loss function to set a different weight for each type error, and cost analysis is conducted to search the optimal type error weight. A cost analysis-based defect-prediction system is designed considering the TEW-DNN algorithm and a cyber-physical system environment. The efficacy of the designed system is demonstrated through a case study involving the application of the system in a die-casting factory in South Korea. [ABSTRACT FROM AUTHOR]

Background: The method by which mental health screening result reports are given affects the user's health behavior. Lists with the distribution of scores in various mental health areas is difficult for users to understand, and if the results are negative, they may feel more embarrassed than necessary. Therefore, we propose using group-tailored feedback, grouping people of similar mental health types by cluster analysis for comprehensive explanations of multidimensional mental health. Methods: This cross-sectional, observational study was conducted using a qualitative approach based on cluster analysis. Data were collected via a developed mental screening website, with depression, anxiety, sleep problems, perfectionism, procrastination, and attention assessed for 2 weeks in January 2020 in Korea. Participants were randomly recruited, and sample size was 174. Total was divided into 25 with severe depression/anxiety (SDA+) and 149 without severe depression/anxiety (SDA-) according to the PHQ-9 and GAD-7 criteria. Cluster analysis was conducted in each group, and an ANOVA was performed to find significant clusters. Thereafter, structured discussion was performed with mental health professionals to define the features of the clusters and construct the feedback content initially. Thirteen expert counselors were interviewed to reconstruct the content and validate the effectiveness of the developed feedback. Results: SDA- was divided into 3 using the k-means algorithm, which showed the best performance (silhouette score = 0.32, CH score = 91.67) among the clustering methods. Perfectionism and procrastination were significant factors in discretizing the groups. SDA+ subgroups were integrated because only 25 people belonged to this group, and they need professional help rather than self-care. Mental status and treatment recommendations were determined for each group, and group names were assigned to represent their features. The developed feedback was assessed to improve mental health literacy (MHL) through integrative and understandable explanations of multidimensional mental health. Moreover, it appeared that a sense of belonging was induced to reduce reluctance to face the feedback. Conclusions: This study suggests group-tailored feedback using cluster analysis, which identifies groups of university students by integrating multidimensions of mental health. These methods can help students increase their interest in mental health and improve MHL to enable timely help. [ABSTRACT FROM AUTHOR]

We aimed to develop a novel prediction model for early neurological deterioration (END) based on an interpretable machine learning (ML) algorithm for atrial fibrillation (AF)-related stroke and to evaluate the prediction accuracy and feature importance of ML models. Data from multicenter prospective stroke registries in South Korea were collected. After stepwise data preprocessing, we utilized logistic regression, support vector machine, extreme gradient boosting, light gradient boosting machine (LightGBM), and multilayer perceptron models. We used the Shapley additive explanation (SHAP) method to evaluate feature importance. Of the 3,213 stroke patients, the 2,363 who had arrived at the hospital within 24 h of symptom onset and had available information regarding END were included. Of these, 318 (13.5%) had END. The LightGBM model showed the highest area under the receiver operating characteristic curve (0.772; 95% confidence interval, 0.715–0.829). The feature importance analysis revealed that fasting glucose level and the National Institute of Health Stroke Scale score were the most influential factors. Among ML algorithms, the LightGBM model was particularly useful for predicting END, as it revealed new and diverse predictors. Additionally, the effects of the features on the predictive power of the model were individualized using the SHAP method. [ABSTRACT FROM AUTHOR]

One of the biggest uncertainties in numerical weather predictions (NWPs) comes from treating the subgrid-scale physical processes. For more accurate regional weather and climate prediction by improving physics parameterizations, it is important to optimize a combination of physics schemes and unknown parameters in NWP models. We have developed an interface system between a micro-genetic algorithm (µ -GA) and the WRF model for the combinatorial optimization of cumulus (CU), microphysics (MP), and planetary boundary layer (PBL) schemes in terms of quantitative precipitation forecast for heavy rainfall events in Korea. The µ -GA successfully improved simulated precipitation despite the nonlinear relationship among the physics schemes. During the evolution process, MP schemes control grid-resolving-scale precipitation, while CU and PBL schemes determine subgrid-scale precipitation. This study demonstrates that the combinatorial optimization of physics schemes in the WRF model is one possible solution to enhance the forecast skill of precipitation. [ABSTRACT FROM AUTHOR]

This study first compares how different formulations of a reservoir operation problem with conflicting objectives affect the quality of the generated solution set. Six models were developed for comparative analysis: three using dynamic programming and three using the evolutionary multi-objective direct policy search (EMODPS) algorithm. Subsequently, to improve the quality of the generated solution set, an EMODPS model was selected and coupled with a zone-based hedging policy that has been currently applied in real-world reservoir operations. The proposed methodology was applied to a multipurpose reservoir in South Korea. Among the different models, the EMODPS-Gaussian model with three parameters outperformed dynamic programming models. Moreover, coupling the status quo zone-based hedging rule with the optimization model improved the average duration of failure from the supply side by 37.4%. On the other hand, when measured from the demand side, the results indicated that the magnitude of failure also improved by 4.15% at the cost of frequency of water deficit. The overall results of this study suggest that the integrative use of optimization models with hedging rules is potentially applicable in future drought mitigation measures. [ABSTRACT FROM AUTHOR]

Global warming, one of the most serious aspects of climate change, can be expected to cause rising sea levels. These have in turn been linked to unprecedentedly large typhoons that can cause flooding of low-lying land, coastal invasion, seawater flows into rivers and groundwater, rising river levels, and aberrant tides. To prevent typhoon-related loss of life and property damage, it is crucial to accurately estimate storm-surge risk. This study therefore develops a statistical model for estimating such surges' probability based on surge data pertaining to Typhoon Maemi, which struck South Korea in 2003. Specifically, estimation of non-exceedance probability models of the typhoon-related storm surge was achieved via clustered separated peaks-over-threshold simulation, while various distribution models were fitted to the empirical data for investigating the risk of storm surges reaching particular heights. To explore the non-exceedance probability of extreme storm surges caused by typhoons, a threshold algorithm with clustering methodology was applied. To enhance the accuracy of such non-exceedance probability, the surge data were separated into three different components: predicted water level, observed water level, and surge. Sea-level data from when Typhoon Maemi struck were collected from a tidal-gauge station in the city of Busan, which is vulnerable to typhoon-related disasters due to its geographical characteristics. Fréchet, gamma, log-normal, generalized Pareto, and Weibull distributions were fitted to the empirical surge data, and the researchers compared each one's performance at explaining the non-exceedance probability. This established that Weibull distribution was better than any of the other distributions for modelling Typhoon Maemi's peak total water level. Although this research was limited to one city on the Korean Peninsula and one extreme weather event, its approach could be used to reliably estimate non-exceedance probabilities in other regions where tidal-gauge data are available. In practical terms, the findings of this study and future ones adopting its methodology will provide a useful reference for designers of coastal infrastructure. [ABSTRACT FROM AUTHOR]

In the early 2000s, shipyards in South Korea were the most competitive in the world for commercial vessels because of their accumulated production and quality management capabilities. In the mid-2000s, the rising trend of international oil prices and predicted market growth of offshore structures caused large shipyards in South Korea to start focusing on the construction of offshore structures. However, these shipyards suffered massive losses because they did not properly reflect the characteristics of offshore structures, which differ from those of commercial vessels. Such losses can largely be classified into engineering losses and production losses. This study aimed to address problems related to outfitting installation work from a production perspective. An algorithm was developed to define an efficient spool installation sequence and was verified through actual data of offshore structure. The developed algorithm should make it possible to plan spool installation work by determining an efficient spool installation sequence. In addition, the algorithm can assist in prompt decision making and eliminate wasted cost and time by providing with an efficient spool installation sequence. [ABSTRACT FROM AUTHOR]

With the rapid expansion of renewable energy, the penetration rate of behind-the-meter (BTM) solar photovoltaic (PV) generators is increasing in South Korea. The BTM solar PV generation is not metered in real-time, distorts the electric load and increases the errors of load forecasting. In order to overcome the problems caused by the impact of BTM solar PV generation, an extreme gradient boosting (XGBoost) load forecasting algorithm is proposed. The capacity of the BTM solar PV generators is estimated based on an investigation of the deviation of load using a grid search. The influence of external factors was considered by using the fluctuation of the load used by lighting appliances and data filtering based on base temperature, as a result, the capacity of the BTM solar PV generators is accurately estimated. The distortion of electric load is eliminated by the reconstituted load method that adds the estimated BTM solar PV generation to the electric load, and the load forecasting is conducted using the XGBoost model. Case studies are performed to demonstrate the accuracy of prediction for the proposed method. The accuracy of the proposed algorithm was improved by 21% and 29% in 2019 and 2020, respectively, compared with the MAPE of the LSTM model that does not reflect the impact of BTM solar PV. [ABSTRACT FROM AUTHOR]

Precipitation is a crucial component of the water cycle and plays a key role in hydrological processes. Recently, satellite-based precipitation products (SPPs) have provided grid-based precipitation with spatiotemporal variability. However, SPPs contain a lot of uncertainty in estimated precipitation, and the spatial resolution of these products is still relatively coarse. To overcome these limitations, this study aims to generate new grid-based daily precipitation based on a combination of rainfall observation data with multiple SPPs for the period of 2003–2017 across South Korea. A Random Forest (RF) machine-learning algorithm model was applied for producing a new merged precipitation product. In addition, several statistical linear merging methods have been adopted to compare with the results achieved from the RF model. To investigate the efficiency of RF, rainfall data from 64 observed Automated Synoptic Observation System (ASOS) installations were collected to analyze the accuracy of products through several continuous as well as categorical indicators. The new precipitation values produced by the merging procedure generally not only report higher accuracy than a single satellite rainfall product but also indicate that RF is more effective than the statistical merging method. Thus, the achievements from this study point out that the RF model might be applied for merging multiple satellite precipitation products, especially in sparse region areas. [ABSTRACT FROM AUTHOR]