Search

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]

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]

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]

Featured Application: The underwater target classification algorithm proposed in this paper can be applied to an active sonar system to detect long-range targets. Detection and classification of unidentified underwater targets maneuvering in complex underwater environments are critical for active sonar systems. In previous studies, many detection methods were applied to separate targets from the clutter using signals that exceed a preset threshold determined by the sonar console operator. This is because the high signal-to-noise ratio target has enough feature vector components to separate. However, in a real environment, the signal-to-noise ratio of the received target does not always exceed the threshold. Therefore, a target detection algorithm for various target signal-to-noise ratio environments is required; strong clutter energy can lead to false detection, while weak target signals reduce the probability of detection. It also uses long pulse repetition intervals for long-range detection and high ambient noise, requiring classification processing for each ping without accumulating pings. In this study, a target classification algorithm is proposed that can be applied to signals in real underwater environments above the noise level without a threshold set by the sonar console operator, and the classification performance of the algorithm is verified. The active sonar for long-range target detection has low-resolution data; thus, feature vector extraction algorithms are required. Feature vectors are extracted from the experimental data using Power-Normalized Cepstral Coefficients for target classification. Feature vectors are also extracted with Mel-Frequency Cepstral Coefficients and compared with the proposed algorithm. A convolutional neural network was employed as the classifier. In addition, the proposed algorithm is to be compared with the result of target classification using a spectrogram and convolutional neural network. Experimental data were obtained using a hull-mounted active sonar system operating on a Korean naval ship in the East Sea of South Korea and a real maneuvering underwater target. From the experimental data with 29 pings, we extracted 361 target and 3351 clutter data. It is difficult to collect real underwater target data from the real sea environment. Therefore, the number of target data was increased using the data augmentation technique. Eighty percent of the data was used for training and the rest was used for testing. Accuracy value curves and classification rate tables are presented for performance analysis and discussion. Results showed that the proposed algorithm has a higher classification rate than Mel-Frequency Cepstral Coefficients without affecting the target classification by the signal level. Additionally, the obtained results showed that target classification is possible within one ping data without any ping accumulation. [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]

This paper is about lead-lag robot fish swimming control by image processing. In robot fish aquariums, fish can generally move randomly in any path. This irregular movement may cause collisions between the fish, damaging them. Hence, an effective swimming control method is necessary. We thus proposed a lead-lag swimming control system for robot fish. Here, we simply study the detection of moving objects in an aquarium because we need to find the positions of moving robot fish. The locations of the robot fish are recognized using an image processing technique employing image and position sensors. This method is used to obtain the velocity for each pixel in an image and assumes a constant velocity in each video frame to obtain the positions of robot fish by comparing consecutive video frames. By using the position data, we compute the distance between robot fish and determine which robot fish is the lead fish and which fish is the lagging fish. The lead fish then waits for the lagging fish to catch up. The results of this proposed system are satisfactory in preventing collisions between robot fish. This system is exhibited in Busan Science Museum in South Korea. [ABSTRACT FROM AUTHOR]

In this paper, we present a fast Monte Carlo simulation (MCS) algorithm for pricing equity-linked securities (ELS). The ELS is one of the most popular and complex financial derivatives in South Korea. We consider a step-down ELS with a knock-in barrier. This derivative has several intermediate and final automatic redemptions when the underlying asset satisfies certain conditions. If these conditions are not satisfied until the expiry date, then it will be checked whether the stock path hits the knock-in barrier. The payoff is given depending on whether the path hits the knock-in barrier. In the proposed algorithm, we first generate a stock path for redemption dates only. If the generated stock path does not satisfy the early redemption conditions and is not below the knock-in barrier at the redemption dates, then we regenerate a daily path using Brownian bridge. We present numerical algorithms for one-, two-, and three-asset step-down ELS. The computational results demonstrate the efficiency and accuracy of the proposed fast MCS algorithm. The proposed fast MCS approach is more than 20 times faster than the conventional standard MCS. [ABSTRACT FROM AUTHOR]

A millimetre‐wave cloud radar has limitations for observing heavy rainfall because the short wavelength leads to strong attenuation from raindrops. However, recent studies have attempted to estimate the rain rate using attenuation, which becomes greater as the rain intensity increases. The rain‐rate‐retrieval algorithm is developed in the present paper using the Ka‐band cloud radar (KaCR) installed at the Boseong Global Standard Observatory (BGSO) in the Republic of Korea. First, rain profiles were identified using the threshold of reflectivity (Z) and Doppler velocity (DV) averaged for the analysis of layer that minimized the effects of the receiver saturation and classified as low or high rain‐rate cases using the averaged DV. The reflectivity and rain‐rate (Z‐R) relationship was then derived for low rain‐rate cases that showed insignificant effects for signal attenuation. On the other hand, the attenuation and rain‐rate (A‐R) relationship was derived using high rain‐rate cases that showed the dominant effects of attenuation. The attenuation was calculated using a reflectivity gradient between the upper and lower boundaries of the attenuated layer. Finally, the rain‐rate‐retrieval algorithm was designed using the derived Z‐R and A‐R relationship and then applied back to the KaCR. The estimated rain rate in the KaCR was a similar trend to the observed rain rate in the optical rain gauge (ORG), but slightly underestimated. [ABSTRACT FROM AUTHOR]

As the number of researchers in South Korea has grown, there is increasing dissatisfaction with the selection process for national research and development (R&D) projects among unsuccessful applicants. In this study, we designed a system that can recommend the best possible R&D evaluators using big data that are collected from related systems, refined, and analyzed. Our big data recommendation system compares keywords extracted from applications and from the full-text of the achievements of the evaluator candidates. Weights for different keywords are scored using the term frequency–inverse document frequency algorithm. Comparing the keywords extracted from the achievement of the evaluator candidates', a project comparison module searches, scores, and ranks these achievements similarly to the project applications. The similarity scoring module calculates the overall similarity scores for different candidates based on the project comparison module scores. To assess the performance of the evaluator candidate recommendation system, 61 applications in three Review Board (RB) research fields (system fusion, organic biochemistry, and Korean literature) were recommended as the evaluator candidates by the recommendation system in the same manner as the RB's recommendation. Our tests reveal that the evaluator candidates recommended by the Korean Review Board and those recommended by our system for 61 applications in different areas, were the same. However, our system performed the recommendation in less time with no bias and fewer personnel. The system requiresrevisions to reflect qualitative indicators, such as journal reputation, before it can entirely replace the current evaluator recommendation process. [ABSTRACT FROM AUTHOR]

Microwave radiometers are widely used for the retrieval of Liquid Water Path (LWP) and Integrated Water Vapor (IWV) in the context of cloud and precipitation studies. This paper presents a new site-independent retrieval algorithm for LWP and IWV, relying on a single-frequency 89-GHz ground-based radiometer. A statistical approach is used, based on a neural network, which is trained and tested on a synthetic data set constructed from radiosonde profiles worldwide. In addition to 89-GHz brightness temperature, the input features include surface measurements of temperature, pressure and humidity, as well as geographical information and, when available, estimates of IWV and LWP from reanalysis data. An analysis of the algorithm is presented to assess its accuracy, the impact of the various input features, as well as its sensitivity to radiometer calibration and its stability across geographical locations. The new method is then implemented on real data that were collected during a field deployment in Switzerland and during the ICE-POP 2018 campaign in South Korea. The new algorithm is shown to be quite robust, especially in mid-latitude environments with a moderately moist climate, although its accuracy is inevitably lower than that obtained with state-of-the-art multi-channel radiometers. [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]

In 2012, the Korea Institute of Oriental Medicine proposed an objective and comprehensive physical diagnostic model to address quantification problems in the existing Sasang constitutional diagnostic method. However, certain issues have been raised regarding a revision of the proposed diagnostic model. In this paper, we propose various methodological approaches to address the problems of the previous diagnostic model. Firstly, more useful variables are selected in each component. Secondly, the least absolute shrinkage and selection operator is used to reduce multicollinearity without the modification of explanatory variables. Thirdly, proportions of SC types and age are considered to construct individual diagnostic models and classify the training set and the test set for reflecting the characteristics of the entire dataset. Finally, an integrated model is constructed with explanatory variables of individual diagnosis models. The proposed integrated diagnostic model significantly improves the sensitivities for both the male SY type (36.4% → 62.0%) and the female SE type (43.7% → 64.5%), which were areas of limitation of the previous integrated diagnostic model. The ideas of these new algorithms are expected to contribute not only to the scientific development of Sasang constitutional medicine in Korea but also to that of other diagnostic methods for traditional medicine. [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]

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]

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]

Accurate diagnosis of acute appendicitis is a difficult problem in practice especially when the patient is too young or women in pregnancy. In this paper, we propose a fully automatic appendix extractor from ultrasonography by applying a series of image processing algorithms and an unsupervised neural learning algorithm, self-organizing map. From the suggestions of clinical practitioners, we define four shape patterns of appendix and self-organizing map learns those patterns in pixel clustering phase. In the experiment designed to test the performance for those four frequently found shape patterns, our method is successful in 3 types (1 failure out of 45 cases) but leaves a question for one shape pattern (80% correct). [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]

A lot of bankruptcy forecasting model has been studied. Most of them uses corporate finance data and is intended for general companies. It may not appropriate for forecasting bankruptcy of construction companies which has big liquidity. It has a different capital structure, and the model to judge the financial risk of general companies can be difficult to apply the construction companies. The existing studies such as traditional Z -score and bankruptcy prediction using machine learning focus on the companies of non-specific industries. The characteristics of companies are not considered at all. In this paper, we showed that AdaBoost (adaptive boosting) is an appropriate model to judge the financial risk of Korean construction companies. We classified construction companies into three groups – large, middle, and small based on the capital of a company. We analyzed the predictive ability of the AdaBoost and other algorithms for each group of companies. The experimental results showed that the AdaBoost has more predictive power than others, especially for the large group of companies that has the capital more than 50 billion won. [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]

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]

An arc fault is an electrical breakdown of the insulating medium in an electrical system. When arc faults occur, they cause electrical fires with local sparks and temperatures of over 5000 °C. A series arc is generated in series with a load due to an incomplete connection between cords or a loose connection between a cord and terminal. However, it is hard to detect series arc faults with arc protection devices because the fault current flowing by series arc in the circuit is not higher than the load current. Especially in Korea, preventing electrical fires by series arc is rarely applied because there is no national standard for arc fault circuit interrupters (AFCI) and arc fault detection devices (AFDD). Therefore, many studies for reliable arc detection and analysis are still necessary to prevent electrical fires. In this study, phase analyses of series arc signals for low-voltage electrical devices such as heaters, computers, refrigerators, and air conditioners were conducted. The arc generator was fabricated according to UL 6199 and an optimal filter was designed to detect series arc signals without any attenuation. The phase of detected series arc signals was analyzed according to load types and finally a new algorithm was proposed based on the result of phase-resolved series arc (PRSA) analysis to identify types of loads. [ABSTRACT FROM AUTHOR]

Background: The recent pandemic of CoVID-19 has emerged as a threat to global health security. There are very few prognostic models on CoVID-19 using machine learning. Objectives: To predict mortality among confirmed CoVID-19 patients in South Korea using machine learning and deploy the best performing algorithm as an open-source online prediction tool for decision-making. Materials and Methods: Mortality for confirmed CoVID-19 patients (n = 3,524) between January 20, 2020 and May 30, 2020 was predicted using five machine learning algorithms (logistic regression, support vector machine, K nearest neighbor, random forest and gradient boosting). The performance of the algorithms was compared, and the best performing algorithm was deployed as an online prediction tool. Results: The logistic regression algorithm was the best performer in terms of discrimination (area under ROC curve = 0.830), calibration (Matthews Correlation Coefficient = 0.433; Brier Score = 0.036) and. The best performing algorithm (logistic regression) was deployed as the online CoVID-19 Community Mortality Risk Prediction tool named CoCoMoRP (https://ashis-das.shinyapps.io/CoCoMoRP/). Conclusions: We describe the development and deployment of an open-source machine learning tool to predict mortality risk among CoVID-19 confirmed patients using publicly available surveillance data. This tool can be utilized by potential stakeholders such as health providers and policymakers to triage patients at the community level in addition to other approaches. [ABSTRACT FROM AUTHOR]

Reverse logistics include all operations related to the reuse of products and materials. In this study, we focus on collection, which is the first operation of reverse logistics, and on the strength of using the sensor data and the concept of Industry 4.0. Previously, the collection activities of electronic wastes (e-wastes) was conducted by a fixed schedule without consideration of the fulfillment level of the collection boxes. However, due to the progress of IoT(internet of things) technology and sensor technology, it is possible to consider the fulfillment level of the collection boxes in order to make the collection schedule. To utilize the sensor data and IoT technology in reverse logistics, a collection signal algorithm is required to treat the rate of fulfilment of collection boxes. However, the collection signal algorithm for the disposal of small and medium (S&M)-sized e-wastes have not yet been developed in South Korea. This study uses a collection box to develop the collection algorithm based on an experimental design method with multiple sensors. The proposed algorithm can be utilized to solve the current collection problems and to save logistics costs. Furthermore, proper collection of e-wastes will lead to more recycling activities, which can further create and sustain a safer environment on Earth. [ABSTRACT FROM AUTHOR]

Background: Previous scoring models such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) and the Sequential Organ Failure Assessment (SOFA) scoring systems do not adequately predict mortality of patients undergoing continuous renal replacement therapy (CRRT) for severe acute kidney injury. Accordingly, the present study applies machine learning algorithms to improve prediction accuracy for this patient subset.Methods: We randomly divided a total of 1571 adult patients who started CRRT for acute kidney injury into training (70%, n = 1094) and test (30%, n = 477) sets. The primary output consisted of the probability of mortality during admission to the intensive care unit (ICU) or hospital. We compared the area under the receiver operating characteristic curves (AUCs) of several machine learning algorithms with that of the APACHE II, SOFA, and the new abbreviated mortality scoring system for acute kidney injury with CRRT (MOSAIC model) results.Results: For the ICU mortality, the random forest model showed the highest AUC (0.784 [0.744-0.825]), and the artificial neural network and extreme gradient boost models demonstrated the next best results (0.776 [0.735-0.818]). The AUC of the random forest model was higher than 0.611 (0.583-0.640), 0.677 (0.651-0.703), and 0.722 (0.677-0.767), as achieved by APACHE II, SOFA, and MOSAIC, respectively. The machine learning models also predicted in-hospital mortality better than APACHE II, SOFA, and MOSAIC.Conclusion: Machine learning algorithms increase the accuracy of mortality prediction for patients undergoing CRRT for acute kidney injury compared with previous scoring models. [ABSTRACT FROM AUTHOR]

Media manipulation of breaking news through article selection, ranking and tweaking of social media data and comment streams is a growing concern for society. We argue that the combination of human and machine curation on media portals marks a new period for news media and journalism. Although intermediary platforms routinely claim that they are merely the neutral technological platform which facilitates news and information flows, rejecting any criticisms that they are operating as de facto media organisations; instead, we argue for an alternative, more active interpretation of their roles. In this article we provide a contemporary account of the South Korean ('Korean') online news media ecology as an exemplar of how contemporary media technologies, and in particular portals and algorithmic recommender systems, perform a powerful role in shaping the kind of news and information that citizens access. By highlighting the key stakeholders and their positions within the production, publication and distribution of news media, we argue that the overall impact of the major portal platforms of Naver and Kakao is far more consequential than simply providing an entertaining media diet for consumers. These portals are central in designing how and which news is sourced, produced and then accessed by Korean citizens. From a regulatory perspective the provision of news on the portals can be a somewhat ambiguous and moving target, subject to soft and harder regulatory measures. While we investigate a specific case study of the South Korean experience, we also trace out connections with the larger global media ecology. We have relied on policy documents, stakeholder interviews and portal user 'walk throughs' to understand the changing role of news and its surfacing on a distinctive breed of media platforms. [ABSTRACT FROM AUTHOR]

Purpose: The Mini-Mental State Examination (MMSE) is one of the most frequently used bedside screening measures of cognition. However, the Korean Dementia Screening Questionnaire (KDSQ) is an easier and more reliable screening method. Instead, other clinical variables and raw data were used for this study without the consideration of a cutoff value. The objective of this study was to develop a machine-learning algorithm for the detection of cognitive impairment (CI) based on the KDSQ and the MMSE.Patients and methods: The original dataset from the Clinical Research Center for Dementia of South Korea study was obtained. In total, 9,885 and 300 patients were randomly allocated to the training and test datasets, respectively. We selected up to 24 variables including sex, age, education duration, diabetes mellitus, and hypertension. We trained a machine-learning algorithm using TensorFlow based on the training dataset and then calculated its accuracy using the test dataset. The cost was calculated by conducting a logistic regression.Results: The accuracy of the model in predicting CI based on the KDSQ only, the MMSE only, and the combination of the KDSQ and MMSE was 84.3%, 88.3%, and 86.3%, respectively. For the KDSQ, the sensitivity for detecting CI was 91.50% and the specificity for detecting normal cognition (NL) was 59.60%. The sensitivity of the MMSE was 94.35%, and the specificity was 59.62%. When combining the KDSQ and the MMSE, the sensitivity for detecting CI was 91.5% and the specificity for detecting NL was 61.5%.Conclusion: The algorithm predicting CI based on the MMSE is superior. However, the KDSQ can be administered more easily in clinical practice and the algorithm using KDSQ is a comparable screening tool. [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]

Lightning is one of the most troubling weather phenomena for weather forecasters at space centers. In this study, proximity sounding and lightning data were used to evaluate the utility of thermodynamic and kinematic parameters for forecasting lightning prior to launch operations. Various parameters from 4138 radio sounding observations at five sites and cloud-to-ground (CG) stroke data from the Korea Meteorological Administration's Lightning Detection Network (KLDN) over South Korea during 2004-09 were used. To support launch operations, forecasts of the total membership function for lightning (TMF) were derived from the combination of membership functions of selected thermodynamic and kinematic parameters with each objective weight using a fuzzy logic algorithm. The forecast skill of TMF was evaluated by computing several skill statistics, which include probability of detection (POD), false alarm rate (FAR), percent correct (PC), critical success index (CSI), and the true skill statistic (TSS). The lightning forecasting method for Gwangju, South Korea (site nearest to the Naro Space Center), was found to have a POD of 0.68, an FAR of 0.45, a PC of 0.76, a CSI of 0.44, and a TSS of 0.47. [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]

Estimating the damaged area after a forest fire is important for responding to this natural catastrophe. With the support of aerial remote sensing, typically with unmanned aerial vehicles (UAVs), the aerial imagery of forest-fire areas can be easily obtained; however, retrieving the burnt area from the image is still a challenge. We implemented a new approach for segmenting burnt areas from UAV images using deep learning algorithms. First, the data were collected from a forest fire in Andong, the Republic of Korea, in April 2020. Then, the proposed two-patch-level deep-learning models were implemented. A patch-level 1 network was trained using the UNet++ architecture. The output prediction of this network was used as a position input for the second network, which used UNet. It took the reference position from the first network as its input and refined the results. Finally, the final performance of our proposed method was compared with a state-of-the-art image-segmentation algorithm to prove its robustness. Comparative research on the loss functions was also performed. Our proposed approach demonstrated its effectiveness in extracting burnt areas from UAV images and can contribute to estimating maps showing the areas damaged by forest fires. [ABSTRACT FROM AUTHOR]

Land surface temperature (LST) is an important geophysical element for understanding Earth systems and land–atmosphere interactions. In this study, we developed a nonlinear split-window LST retrieval algorithm for the observation area of GEO-KOMPSAT-2A (GK2A), the next-generation geostationary satellite in Korea. To develop the GK2A LST retrieval algorithm, radiative transfer model simulation data, considering various impacting factors, were constructed. The LST retrieval algorithm was developed with a total of six equations as per day/night and atmospheric conditions (dry/normal/wet), considering the effects of diurnal variation of LST and atmospheric conditions on LST retrieval. The emissivity of each channel required for LST retrieval was calculated in real-time with the vegetation cover method using the consecutive 8-day cycle vegetation index provided by GK2A. The indirect validation of the results of GK2A LST with Moderate Resolution Imaging Spectroradiometer (MODIS) LST Collection 6 showed a high correlation coefficient (0.969), slightly warm bias (+1.227 K), and root mean square error (RMSE) (2.281 K). Compared to the MODIS LST, the GK2A LST showed a warm bias greater than +1.8 K during the day, but a relatively small bias (<+0.7 K) at night. Based on the results of the validation with in situ measurements from the Tateno station of the Baseline Surface Radiation Network, the correlation coefficient was 0.95, bias was +0.523 K, and RMSE was 2.021 K. [ABSTRACT FROM AUTHOR]

With the spread of COVID-19, the "untact" culture in South Korea is expanding and customers are increasingly seeking for online services. A recommendation system serves as a decision-making indicator that helps users by suggesting items to be purchased in the future by exploring the symmetry between multiple user activity characteristics. A plethora of approaches are employed by the scientific community to design recommendation systems, including collaborative filtering, stereotyping, and content-based filtering, etc. The current paradigm of recommendation systems favors collaborative filtering due to its significant potential to closely capture the interest of a user as compared to other approaches. The collaborative filtering harnesses features like user-profile details, visited pages, and click information to determine the interest of a user, thereby recommending the items that are related to the user's interest. The existing collaborative filtering approaches exploit implicit and explicit features and report either good classification or prediction outcome. These systems fail to exhibit good results for both measures at the same time. We believe that avoiding the recommendation of those items that have already been purchased could contribute to overcoming the said issue. In this study, we present a collaborative filtering-based algorithm to tackle big data of user with symmetric purchasing order and repetitive purchased products. The proposed algorithm relies on combining extreme gradient boosting machine learning architecture with word2vec mechanism to explore the purchased products based on the click patterns of users. Our algorithm improves the accuracy of predicting the relevant products to be recommended to the customers that are likely to be bought. The results are evaluated on the dataset that contains click-based features of users from an online shopping mall in Jeju Island, South Korea. We have evaluated Mean Absolute Error, Mean Square Error, and Root Mean Square Error for our proposed methodology and also other machine learning algorithms. Our proposed model generated the least error rate and enhanced the prediction accuracy of the recommendation system compared to other traditional approaches. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) is very important for planning and operating power systems and markets. Various algorithms have been developed for STLF. However, numerous utilities still apply additional correction processes, which depend on experienced professionals. In this study, an STLF algorithm that uses a similar day selection method based on reinforcement learning is proposed to substitute the dependence on an expert's experience. The proposed algorithm consists of the selection of similar days, which is based on the reinforcement algorithm, and the STLF, which is based on an artificial neural network. The proposed similar day selection model based on the reinforcement learning algorithm is developed based on the Deep Q-Network technique, which is a value-based reinforcement learning algorithm. The proposed similar day selection model and load forecasting model are tested using the measured load and meteorological data for Korea. The proposed algorithm shows an improvement accuracy of load forecasting over previous algorithms. The proposed STLF algorithm is expected to improve the predictive accuracy of STLF because it can be applied in a complementary manner along with other load forecasting algorithms. [ABSTRACT FROM AUTHOR]