Search

Influenced by cultural background, economic development, social system, education system, and other factors, there is still a big gap between Chinese institutions and developed countries in flute teaching, even with our neighbors, South Korea and Japan. Under the influence of cultural background, economic development, social system, and educational system, there is still a very big gap between Chinese colleges and universities and developed countries in flute teaching, even with our neighbors, South Korea and Japan. Because of its local perception and weight-sharing structure, the convolutional neural network is closer to the biological neural network in the real world. The weight-sharing structure reduces the complexity of the neural network, which can avoid the complexity of feature extraction and classification process in data reconstruction. This paper studies the analysis and optimization of flute playing and teaching system based on a convolutional neural network. By applying local perception field and parameter sharing in a convolutional neural network at the same time and adding multiple filters, it can not only effectively reduce the number of parameters but also extract features layer by layer. In the process of convolution, the parameters of the characteristic map obtained by each layer decrease layer by layer, but the number increases gradually. Based on the analysis of the problems faced by the flute performance teaching, this paper puts forward the corresponding solutions in order to promote the flute performance teaching in China to achieve better results. [ABSTRACT FROM AUTHOR]

Machine learning-based time-series forecasting has recently been intensively studied. Deep learning (DL), specifically deep neural networks (DNN) and long short-term memory (LSTM), are the popular approaches for this purpose. However, these methods have several problems. First, DNN needs a lot of data to avoid over-fitting. Without sufficient data, the model cannot be generalized so it may not be good for unseen data. Second, impaired data affect forecasting accuracy. In general, one trains a model assuming that normal data enters the input. However, when anomalous data enters the input, the forecasting accuracy of the model may decrease substantially, which emphasizes the importance of data integrity. This paper focuses on these two problems. In time-series forecasting, especially for photovoltaic (PV) forecasting, data from solar power plants are not sufficient. As solar panels are newly installed, a sufficiently long period of data cannot be obtained. We also find that many solar power plants may contain a substantial amount of anomalous data, e.g., 30%. In this regard, we propose a data preprocessing technique leveraging convolutional autoencoder and principal component analysis (PCA) to use insufficient data with a high rate of anomaly. We compare the performance of the PV forecasting model after applying the proposed anomaly detection in constructing a virtual power plant (VPP). Extensive experiments with 2517 PV sites in the Republic of Korea, which are used for VPP construction, confirm that the proposed technique can filter out anomaly PV sites with very high accuracy, e.g., 99%, which in turn contributes to reducing the forecasting error by 23%. [ABSTRACT FROM AUTHOR]

The smart intersection (SI) systems, as they are named in the Republic of Korea, are part of the ITS services implemented under local government projects with financial support from the central government. They collect real-time traffic data available at signalized intersections with advanced detection systems for surveillance purposes only. A traffic signal method utilizing such valuable data has been desirable but unavailable as yet in practice. This paper proposes a new approach to designing traffic signal timings, reflecting the demand changing in real time, by utilizing SI surveillance data. The proposed artificial neural network model generates suitable traffic signal timings trained to be near optimum based on surveillance data for each directional movement. [ABSTRACT FROM AUTHOR]

In general, the created era of a literary work is significant information for understanding the background and the literary interpretation of the work. However, in the case of literary works of old Korea, especially works created in Hangul, there are few works of which the era of creation are known. In this paper, the created era of old Korean documents was estimated based on artificial intelligence. Hangul, a Korean letter system where one syllable is one character, has more than 10,000 combinations of characters, so it is available to predict changes in the structure or grammar of Hangul by analyzing the frequency of characters. Accordingly, a deep neural network model was constructed based on the term frequency of each character in Hangul. Model training was performed based on 496 documents with known publication years, and the mean-absolute-error of the test set for the entire prediction range from 1447 to 1934 was 13.77 years for test sets and 15.8 years for validation sets, which is less than an error ratio of 3.25% compared to the total year range. In addition, the predicted results of works from which only the approximate creation time was inferred were also within the range, and the predicted creation years for other divisions of the identical novel were similar. These results show that the deep neural network model based on character term frequency predicted the creation era of old Korean documents properly. This study is expected to support the literary history of Korea within the period from 15C to 19C by predicting the period of creation or enjoyment of the work. In addition, the method and algorithm using syllable term frequency are believed to have the potential to apply in other language documents. [ABSTRACT FROM AUTHOR]

Exposure to air pollutants, such as PM2.5 and ozone, has a serious adverse effect on health, with more than 4 million deaths, including early deaths. Air pollution in ports is caused by exhaust gases from various elements, including ships, and to reduce this, the International Maritime Organization (IMO) is also making efforts to reduce air pollution by regulating the sulfur content of fuel used by ships. Nevertheless, there is a lack of measures to identify and minimize the effects of air pollution. The Community Multiscale Air Quality (CMAQ) model is the most used to understand the effects of air pollution. In this paper, we propose a hybrid model combining the CMAQ model and RNN-LSTM, an artificial neural network model. Since the RNN-LSTM model has very good predictive performance, combining these two models can improve the spatial distribution prediction performance of a large area at a relatively low cost. In fact, as a result of prediction using the hybrid model, it was found that IOA improved by 0.235~0.317 and RMSE decreased by 4.82~8.50 μg/m3 compared to the case of using only CMAQ. This means that when PM2.5 is predicted using the hybrid model, the accuracy of the spatial distribution of PM2.5 can be improved. In the future, if real-time prediction is performed using the hybrid model, the accuracy of the calculation of exposure to air pollutants can be increased, which can help evaluate the impact on health. Ultimately, it is expected to help reduce the damage caused by air pollution through accurate predictions of air pollution. [ABSTRACT FROM AUTHOR]

Due to the outstanding strength of advanced machine-learning techniques, they have become increasingly common in predictive studies in recent years, particularly in predicting ship energy performance. In constructing predictive models, prior studies have mostly employed vessels' technical parameters to establish machine-learning algorithms. To bridge this research gap and enable wider applications, this paper presents the design of a multilayer perceptron artificial neural network (MLP ANN) as a machine-learning technique to estimate ship fuel consumption. We utilized the real operational data from 100–143 container ships to estimate fuel consumption for five different container ships grouped by size. We compared the performance of two ANN models and two multiple-regression models. Four input parameters (sailing time, speed, cargo weight, and capacity) were included in the first ANN and the first regression model, while the other two models only consider two inputs from physical function. The mean absolute percentage error of the ANN models with four inputs was the smallest and less than those in extended statistical models, demonstrating the MLP's superiority over the statistical model. The MLP ANN model can thus be applied to confirm the effectiveness of the slow-steaming method for achieving energy efficiency. [ABSTRACT FROM AUTHOR]

In Korea, weather forecasts for fundamental weather factors, such as temperature, precipitation, wind direction and speed, humidity, and cloudiness, are provided for a three-day period in each region. This can facilitate predicting photovoltaic power generation based on weather forecasting. For this purpose, in the present paper, we aim to propose corresponding model. However, the Korea Meteorological Administration does not forecast the amount of solar radiation and sunshine that mostly influence the results of photovoltaic power generation prediction. In this study, we predict these parameters considering various input/output (I/O) variables and learning algorithms applied to weather forecasts on hourly weather data. Finally, we predict photovoltaic power generation based on the best sunshine and solar radiation prediction results. The data structure underlying all predictions relies on four models applied to fundamental weather factors on sunshine and solar radiation data two hours ago. Then, the photovoltaic power generation prediction is implemented using four models depending on whether to add the predicted sunshine and solar radiation data obtained at the previous step. The prediction algorithm relies on an adaptive neuro-fuzzy inference system and artificial neural network (ANN) techniques, including dynamic neural network (DNN), recurrent neural network (RNN), and long short-term memory (LSTM). The results of the conducted experiment indicate that ANN perform better than the neuro-fuzzy approach. Moreover, we demonstrate that RNN and LSTM are more suitable for the time series data structures compared with DNN. Furthermore, we report that the weather forecast structure and the model 4 structure, which includes sunshine and solar radiation data two hours ago, achieve the best prediction results. [ABSTRACT FROM AUTHOR]

Artificial neural network is considered one of the most efficient methods in processing huge data sets that can be analyzed computationally to reveal patterns, trends, prediction, forecasting etc. It has a great prospective in engineering as well as in medical applications. The present work employs artificial neural network-based curve fitting techniques in prediction and forecasting of the Covid-19 number of rising cases and death cases in India, USA, France, and UK, considering the progressive trends of China and South Korea. In this paper, three cases are considered to analyze the outbreak of Covid-19 pandemic viz., (i) forecasting as per the present trend of rising cases of different countries (ii) forecasting of one week following up with the improvement trends as per China and South Korea, and (iii) forecasting if followed up the progressive trends as per China and South Korea before a week. The results have shown that ANN can efficiently forecast the future cases of COVID 19 outbreak of any country. The study shows that the confirmed cases of India, USA, France and UK could be about 50,000 to 1,60,000, 12,00,000 to 17,00,000, 1,40,000 to 1,50,000 and 2,40,000 to 2,50,000 respectively and may take about 2 to 10 months based on progressive trends of China and South Korea. Similarly, the death toll for these countries just before controlling could be about 1600 to 4000 for India, 1,00,000 to 1,35,000 for USA, 40,000 to 55,000 for France, 35,000 to 47,000 for UK during the same period of study. [ABSTRACT FROM AUTHOR]

The technology of interiors is currently developing around the world. According to various studies, the use of plants to create an environment in the home interior is increasing. However, households using furniture are designed as environment-friendly environment interiors, and in Korea and abroad, plants are used for home interiors. Unexpected accidents are occurring. As a result, there were books and broadcasts about the dangers of specific plants, but until now, accidents continue to occur because they do not properly recognize the dangers of specific plants. Therefore, in this paper, we propose a toxic plant identification system based on a multiplicative neural network model that identifies common toxic plants commonly found in Korea. We propose a high efficiency model. Through this, toxic plants can be identified with higher accuracy and safety accidents caused by toxic plants. [ABSTRACT FROM AUTHOR]

Kim, J. and Kim, J., 2020. Estimation of water surface flow velocity using coastal video imagery by visual tracking with deep learning. In: Malvárez, G. and Navas, F. (eds.), Global Coastal Issues of 2020. Journal of Coastal Research, Special Issue No. 95, pp. 522-526. Coconut Creek (Florida), ISSN 0749-0208. This paper describes the method of flow velocity estimation of water surface in video imagery by tracking waves using deep neural network for visual object tracking with unsupervised learning. The model of deep neural network consists of two stages for scene separation and image registration to extract waves only and track the propagated waves, respectively. The dataset of video imagery acquired at Anmok beach of south Korea has been used to training the model and it learns the behavior of propagated waves. The performance of model is evaluated by measuring image similarity using test dataset. And the estimated flow velocity of water surface in propagated waves is compared with the flow from conventional image processing method of particle image velocity. The results show that our proposed approach with deep learning method is very promising to measure and predict coastal waves especially in the surf zone. [ABSTRACT FROM AUTHOR]

This paper is concerned with posture recognition using ensemble convolutional neural networks (CNNs) in home environments. With the increasing number of elderly people living alone at home, posture recognition is very important for helping elderly people cope with sudden danger. Traditionally, to recognize posture, it was necessary to obtain the coordinates of the body points, depth, frame information of video, and so on. In conventional machine learning, there is a limitation in recognizing posture directly using only an image. However, with advancements in the latest deep learning, it is possible to achieve good performance in posture recognition using only an image. Thus, we performed experiments based on VGGNet, ResNet, DenseNet, InceptionResNet, and Xception as pre-trained CNNs using five types of preprocessing. On the basis of these deep learning methods, we finally present the ensemble deep model combined by majority and average methods. The experiments were performed by a posture database constructed at the Electronics and Telecommunications Research Institute (ETRI), Korea. This database consists of 51,000 images with 10 postures from 51 home environments. The experimental results reveal that the ensemble system by InceptionResNetV2s with five types of preprocessing shows good performance in comparison to other combination methods and the pre-trained CNN itself. [ABSTRACT FROM AUTHOR]

In South Korea, rice is the most important grain crop that it is crucial to develop yield estimation model for supporting sustainable agriculture and national food security. The main objectives of this paper are (1) to propose a Deep Learning (DL) algorithm, the Stacked Sparse Auto-encoder (SSAE), for rice-yield estimation using climatic and Moderate Resolution Imaging Spectroradiometer (MODIS) data; (2) to choose scenarios showing the best combined performance in terms of length of crop season (before and after harvest) and aggregation periods (7, 10, 15, and 30 days) of climatic data; and (3) to analyse the results in both the temporal and spatial perspectives. In this procedure, the SSAE model was built around the study objectives and compared with the artificial neural network (ANN) model for evaluation of its performance. According to the results, the combined 15-day-aggregated climatic data (between June and August) and MODIS data were selected as the optimal feature set for rice-yield estimation in the study area, Jeolla-do; the SSAE model outperformed ANN, showing root mean square error (RMSE) and RMSE% of 33.09 kg(10a)−1 (5.21 kg(10a)−1lower than ANN) and 6.89% (1.14% lower than ANN). Throughout the experiments, the rice-yield-estimation potentiality of a DL algorithm, namely the SSAE, was substantiated. [ABSTRACT FROM AUTHOR]

Multiscale forecasting of groundwater levels (GWLs) is essential for ensuring the sustainable management of groundwater resources, particularly considering the potential impacts of climate change. Such forecasting requires a model that is not only accurate in predicting GWLs but also computationally efficient, ensuring its suitability for practical applications. In this study, a temporal convolutional network (TCN) is implemented to forecast GWLs for 17 monitoring wells possessing diverse hydrogeological characteristics, located across South Korea. Using deep learning, the influence of meteorological variables (i.e., temperature, precipitation) on the forecasted GWLs was investigated by dividing the input features into three categories. Additionally, the models were developed for three forecast intervals (at 1-, 3-, and 6-month lead times) using each category input. When compared with state-of-the-art models, that is, long short-term memory (LSTM) and artificial neural network (ANN), the TCN model showed superior performance and required much less computational complexity. On average, the TCN model outperformed the LSTM model by 24%, 21%, and 25%, and the ANN model by 24%, 37%, and 47%, respectively, for 1-, 3-, and 6-month lead times. Based on these results, the proposed TCN model can be used for real-time GWL forecasting in hydrological applications. [ABSTRACT FROM AUTHOR]

Outdoor stone cultural properties are continuously affected by the external environment such as wind, rain, and earthquakes. These cause damage to the cultural properties by not only threatening structural stability but also damaging the aesthetic value. Quick detection of these damages is important to enable appropriate preservation treatment in terms of cultural property conservation management. Even though conventional manual damage detection methods are widely used, they are limited by manpower, cost, and other external conditions. In this paper, we propose a system that automatically detects and classifies damage occurring in cultural properties using deep-learning technique to settle these drawbacks. In detail, the damages are classified into four types (i.e., crack, loss, detachment, biological colonization) based on Faster region-based convolutional neural network (R-CNN) algorithm. In addition, we construct an image dataset of stone damage, which is collected by the regular report of the National Designated Cultural Property in 2017 conducted by the Cultural Heritage Administration of S. Korea, and augment its dataset to enhance damage detection performance. From the experiment conducted, we achieved an average confidence score of 94.6 % or more on the 20 test images. [ABSTRACT FROM AUTHOR]

This paper is concerned with the temporal variation characteristics of two meteorological factors (temperature and humidity) in four metropolitan cities (Seoul, Busan, Daegu, Daejeon) in South Korea. Data are extracted from seven years (2008 to 2014) of hourly time series data in meteorological offices of the Korea Meteorological Administration. Using the detrended cross-correlation analysis (DCCA) method, the DCCA coefficient of temperature is compared to that of humidity from daily time series data during four seasons in the four metropolitan cities. In particular, as window size s increases, the DCCA cross-correlation coefficient approaches 0.034 at a time lag of 14 days in the case of spring in Seoul. We find the weak cross-correlation between temperature and humidity at different time lags of 14, 21 and 28 days in spring in Seoul, and the errors E T in the ANN are relatively larger values than that of any other season in both the ANN and the MRM. Particularly, in the ANN model, there exist relatively a large error value of temperature as the characteristics of the non-stationary, deterministically chaotic and noisy meteorological data extracted for the short-term prediction rather than the long-term prediction. • The temporal variation characteristics of two meteorological factors are studied in four metropolitan cities. • This presents the status of simulations and analyses relevant to the DCCA, ANN, and MRM. • The DCCA coefficients for temperature and humidity in all seasons are estimated and compared in four metropolitan cities. • The error EH for humidity had a smaller value compared to the error ET for temperature. • We find that the MRM outperforms the ANN for two meteorological factors. [ABSTRACT FROM AUTHOR]

This paper investigates the influence of incorporating spatiotemporal wind data on the performance of wind forecasting neural networks. While previous studies have shown that including spatial data enhances the accuracy of such models, limited research has explored the impact of different spatial and temporal scales of input wind data on the learnability of neural network models. In this study, convolutional neural networks (CNNs) are employed and trained using various scales of spatiotemporal wind data. The research demonstrates that using spatiotemporally correlated data from the surrounding area and past time steps for training a CNN favorably affects the predictive performance of the model. The study proposes correlation analyses, including autocorrelation and Pearson correlation analyses, to unveil the influence of spatiotemporal wind characteristics on the predictive performance of different CNN models. The spatiotemporal correlations and performances of CNN models are investigated in three regions: Korea, the USA, and the UK. The findings reveal that regions with smaller deviations of autocorrelation coefficients (ACC) are more favorable for CNNs to learn the regional and seasonal wind characteristics. Specifically, the regions of Korea, the USA, and the UK exhibit maximum standard deviations of ACCs of 0.100, 0.043, and 0.023, respectively. The CNNs wind prediction performances follow the reverse order of the regions: UK, USA, and Korea. This highlights the significant impact of regional and seasonal wind conditions on the performance of the prediction models. [Display omitted] • 3D CNN-based wind velocity prediction. • Estimation of CNN learnability through spatiotemporal wind correlation analysis. • Discovery of influence of local geometric and seasonal wind on CNN prediction. • The proposed correlation analysis can aid in selecting yaw-control wind farm sites. [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]

Background: Korea's aging population and the lack of older adult participation in sports are increasing medical expenses. Aims: This study aimed to segment older adult sports participants based on their demographic characteristics and exercise practice behavior and applied artificial neural network and logistic regression models to these segments to best predict the effect of medical cost reduction. It presents strategies for older adult sports participation. Methods: A sample comprising data on 1,770 older adults aged 50 years and above was drawn from the 2019 National Sports Survey. The data were analyzed through frequency analysis, hierarchical and K-means clustering, artificial neural network, logistic regression, cross-tabulation analyses, and one-way ANOVA using SPSS 23 and Modeler 14.2. Results: The participants were divided into five clusters. The artificial neural network and logistic analysis models showed that the cluster comprising married women in their 60s who participated in active exercise had the highest possibility of reducing medical expenses. Discussion: Targeting women in their 60s who actively participate in sports, the government should expand the supply of local gymnasiums, community centers, and sports programs. If local gymnasiums and community centers run sports programs and appoint appropriate sports instructors, the most effective medical cost reduction effect can be obtained. Conclusions: This study contributes to the field by providing insights into the specific demographic segments to focus on for measures to reduce medical costs through sports participation. [ABSTRACT FROM AUTHOR]

Scaling rain attenuation parameters will significantly benefit the quick monitoring of rain attenuation in a particular channel with previously known results or in situ setup attenuation measurements. Most of the rain attenuation scaling techniques have been derived for slant links. In this study, we also applied frequency and polarization scaling techniques for terrestrial link applications. We collected real measured datasets from research paper publications and examined those datasets using International Telecommunication Union-Radiocommunication sector (ITU-R) models (P.530-17, P.618-13). Our analyzed results show that existing long-term frequency and polarization scaling rain attenuation models (ITU-R P.618-13 for slant links and ITU-R P.530-17 for terrestrial links) show reduced performance for frequency and polarization scaling measured locations in South Korea. Hence, we proposed a new scaling technique using artificial neural networks from the measured rain attenuation data of slant and terrestrial links in South Korea. The experimental results confirm that the proposed Artificial Neural Network (ANN)-based scaling model shows satisfactory performance to predict attenuation for frequency and vertical polarization scaling. [ABSTRACT FROM AUTHOR]

• Development of a prediction model for airborne chloride depositions with surrounding environmental information. • Bayesian regularization-based artificial neural network considering the high data variance. • Average 35% performance improvement with Bayesian regularization compared to conventional ANN. This paper suggests an artificial neural network model combining Bayesian regularization (BRANN) to estimate concentrations of airborne chlorides, which would be useful in the design of reinforced concrete structures and for estimating environmental effects on long-term structural performance. Meteorological and topographical data were collected, and airborne chlorides were measured at 19 areas all over Korea. Data were classified for the three major coasts, and then prepared for training. To investigate the relationship between each input feature and output and then construct a model for estimating airborne chlorides with only meteorological and topographical information, both the standard artificial NN (ANN) and BRANN models were examined. The 3 or 4-layered BRANN model with 64 nodes at each layer showed the best and most robust performance. This BRANN model successfully predicted airborne chloride content with reasonable values of MSE and R-square although the input data and the airborne chlorides had quite low correlation. The results showed that the BRANN was better able to solve this problem than ANN. It is expected to be broadly applicable for predicting the penetration of chlorides into concrete and even the evaluation of concrete durability. [ABSTRACT FROM AUTHOR]

Growth factors affect farm owners, environmental conditions, nutrient adaptation, and resistance to chrysanthemum diseases. Healthy chrysanthemum plants can overcome all these factors and provide farms owners with a lot of income. Chrysanthemum white rust disease is a common disease that occurs worldwide; if not treated promptly, the disease spreads to the entire leaf surface, causing the plant's leaves to burn, turn yellow, and fall prematurely, reducing the photosynthetic performance of the plant and the appearance of the flower branches. In Korea, chrysanthemum white rust disease most often occurs during the spring and autumn seasons, when temperature varies during the summer monsoon, and when ventilation is poor in the winter. Deep neural networks were used to determine healthy and unhealthy plants. We applied the Raspberry Pi 3 module to recognize white rust and test four neural network models. The five main deep neural network processes utilized for a dataset of non-diseased and white rust leaves include: (1) data collection; (2) data partitioning; (3) feature extraction; (4) feature engineering; and (5) prediction modeling based on the train–test loss of 35 epochs within 20 min using Linux. White rust recognition is performed for comparison using four models, namely, DenseNet-121, ResNet-50, VGG-19, and MobileNet v2. The qualitative white rust detection system is achieved using a Raspberry Pi 3 module. All models accomplished an accuracy of over 94%, and MobileNet v2 achieved the highest accuracy, precision, and recall at over 98%. In the precision comparison, DenseNet-121 obtained the second highest recognition accuracy of 97%, whereas ResNet-50 and VGG-19 achieved slightly lower accuracies at 95% and 94%, respectively. Qualitative results were obtained using the Raspberry Pi 3 module to assess the performance of the seven models. All models had accuracies of over 91%, with ResNet-50 obtaining a value of 91%, VGG-19 reaching a value of 93%, DenseNet-121 reaching 95%, SqueezeNet obtaining over 95%, MobileNet obtaining over 96%, and MobileNetv2-YOLOv3 reaching 92%. The highest accuracy rate was 97% (MobileNet v2). MobileNet v2 was validated as the most effective model to recognize white rust in chrysanthemums using the Raspberry Pi 3 system. Raspberry Pi 3 module was considered, in conjunction with the MobileNet v2 model, to be the best application system. MobileNet v2 and Raspberry Pi require a low cost for the recognition of chrysanthemum white rust and the diagnosis of chrysanthemum plant health conditions, reducing the risk of white rust disease and minimizing costs and efforts while improving floral production. Chrysanthemum farmers should consider applying the Raspberry Pi module for detecting white rust, protecting healthy plant growth, and increasing yields with low-cost. [ABSTRACT FROM AUTHOR]

Automatic age estimation using panoramic dental radiographic images is an important procedure for forensics and personal oral healthcare. The accuracies of the age estimation have increased recently with the advances in deep neural networks (DNN), but DNN requires large sizes of the labeled dataset which is not always available. This study examined whether a deep neural network is able to estimate tooth ages when precise age information is not given. A deep neural network model was developed and applied to age estimation using an image augmentation technique. A total of 10,023 original images were classified according to age groups (in decades, from the 10s to the 70s). The proposed model was validated using a 10-fold cross-validation technique for precise evaluation, and the accuracies of the predicted tooth ages were calculated by varying the tolerance. The accuracies were 53.846% with a tolerance of ±5 years, 95.121% with ±15 years, and 99.581% with ±25 years, which means the probability for the estimation error to be larger than one age group is 0.419%. The results indicate that artificial intelligence has potential not only in the forensic aspect but also in the clinical aspect of oral care. [ABSTRACT FROM AUTHOR]

Although various linear log-distance path loss models have been developed for wireless sensor networks, advanced models are required to more accurately and flexibly represent the path loss for complex environments. This paper proposes a machine learning framework for modeling path loss using a combination of three key techniques: artificial neural network (ANN)-based multi-dimensional regression, Gaussian process-based variance analysis, and principle component analysis (PCA)-aided feature selection. In general, the measured path loss dataset comprises multiple features such as distance, antenna height, etc. First, PCA is adopted to reduce the number of features of the dataset and simplify the learning model accordingly. ANN then learns the path loss structure from the dataset with reduced dimension, and Gaussian process learns the shadowing effect. Path loss data measured in a suburban area in Korea are employed. We observe that the proposed combined path loss and shadowing model is more accurate and flexible compared to the conventional linear path loss plus log-normal shadowing model. [ABSTRACT FROM AUTHOR]

Remote sensing image retrieval (RSIR) is the process of searching for identical areas by investigating the similarities between a query image and the database images. RSIR is a challenging task owing to the time difference, viewpoint, and coverage area depending on the shooting circumstance, resulting in variations in the image contents. In this paper, we propose a novel method based on a coarse-to-fine strategy, which makes a deep network more robust to the variations in remote sensing images. Moreover, we propose a new triangular loss function to consider the whole relation within the tuple. This loss function improves the retrieval performance and demonstrates better performance in terms of learning the detailed information in complex remote sensing images. To verify our methods, we experimented with the Google Earth South Korea dataset, which contains 40,000 images, using the evaluation metric Recall@n. In all experiments, we obtained better performance results than those of the existing retrieval training methods. Our source code and Google Earth South Korea dataset are available online. [ABSTRACT FROM AUTHOR]

This study introduces a method that can evaluate the efficiency of leakage management practices and devises a formula to set leakage management goals. To develop the evaluation method for deriving leakage reduction factors, real data from small- and medium-sized cities in South Korea were collected. With the data collected, four leakage management factors (or activities) that could improve revenue water ratio or reduce leakage ratio were identified. With the leakage management factors, correlation analysis was carried out to identify the relationship between independent and dependent variables and within independent variables. Once the relationships were identified, standardization of the data using T-score conversion was carried out to scale all data with different units into similar ranges. Finally, the efficiency of leakage management actions was determined by the formulation of leakage using various data analysis approaches using multiple linear regression analysis and deep neural networks. As a result, pipe replacement was determined as an essential activity to decrease the leakage ratio or increase the revenue water ratio. In addition, annual water loss management actions of the small cities were more actively performed. Furthermore, the performance of data analysis using DNN is more appropriate in data classification, considering the characteristics of time series rather than independent data analysis. Through comparison of the above data classification approaches, the increase or decrease in the leakage ratio/revenue water ratio by the water loss management activity of local water distribution systems can be used to construct a more effective model for classification considering both local and temporal characteristics. [ABSTRACT FROM AUTHOR]

Economic and social progress in the Republic of Korea resulted in an increased standard of living, which subsequently produced more waste. The Korean government implemented a volume-based trash disposal system that may modify waste disposal characteristics to handle vast volumes of waste efficiently. However, the inconvenience of having to purchase standard garbage bags on one's own led to passive participation by citizens and instances of illegally dumping waste in non-standard plastic bags. As a result, there is a need for the development of automatic detection and reporting of illegal acts of garbage dumping. To achieve this, we suggest a system for tracking unlawful rubbish disposal that is based on deep neural networks. The proposed monitoring approach obtains the articulation points (joints) of a dumper through OpenPose and identifies the type of garbage bag through the object detection model, You Only Look Once (YOLO), to determine the distance of the dumper's wrist to the garbage bag and decide whether it is illegal dumping. Additionally, we introduced a method of tracking the IDs issued to the waste bags using the multi-object tracking (MOT) model to reduce the false detection of illegal dumping. To evaluate the efficacy of the proposed illegal dumping monitoring system, we compared it with the other systems based on behavior recognition. As a result, it was validated that the suggested approach had a higher degree of accuracy and a lower percentage of false alarms, making it useful for a variety of upcoming applications. [ABSTRACT FROM AUTHOR]

Although ultrasound plays an important role in the diagnosis of chronic kidney disease (CKD), image interpretation requires extensive training. High operator variability and limited image quality control of ultrasound images have made the application of computer-aided diagnosis (CAD) challenging. This study assessed the effect of integrating computer-extracted measurable features with the convolutional neural network (CNN) on the ultrasound image CAD accuracy of CKD. Ultrasound images from patients who visited Severance Hospital and Gangnam Severance Hospital in South Korea between 2011 and 2018 were used. A Mask regional CNN model was used for organ segmentation and measurable feature extraction. Data on kidney length and kidney-to-liver echogenicity ratio were extracted. The ResNet18 model classified kidney ultrasound images into CKD and non-CKD. Experiments were conducted with and without the input of the measurable feature data. The performance of each model was evaluated using the area under the receiver operating characteristic curve (AUROC). A total of 909 patients (mean age, 51.4 ± 19.3 years; 414 [49.5%] men and 495 [54.5%] women) were included in the study. The average AUROC from the model trained using ultrasound images achieved a level of 0.81. Image training with the integration of automatically extracted kidney length and echogenicity features revealed an improved average AUROC of 0.88. This value further increased to 0.91 when the clinical information of underlying diabetes was also included in the model trained with CNN and measurable features. The automated step-wise machine learning–aided model segmented, measured, and classified the kidney ultrasound images with high performance. The integration of computer-extracted measurable features into the machine learning model may improve CKD classification. [ABSTRACT FROM AUTHOR]

This study proposes a deep-learning-based model to generate synthetic compressional wave velocity (Vp) from well-logging data with application to the Ulleung Basin Gas Hydrate (UBGH) in the East Sea, Republic of Korea. Because a bottom-simulating reflector (BSR) is a key indicator to define the presence of gas hydrate, this study generates the Vp for identifying the BSR by detecting the morphology of the hydrate in terms of the change in acoustic velocity. Conventional easy-to-acquire logging parameters, such as gamma-ray, neutron porosity, bulk density, and photoelectric absorption, were selected as model inputs based on a sensitivity analysis. Long short-term memory (LSTM) and an artificial neural network (ANN) were used to design an efficient learning-based predictive model with sensitivity analysis for hyperparameters. The LSTM model outperforms the ANN model by preserving the geological sequence of the well-logging data. Ten-fold cross-validation was conducted to verify the consistency of the LSTM model and yielded satisfactory results, with an average coefficient of determination greater than 0.8. These numerical results imply that generating synthetic well-logging via deep learning can accurately estimate missing well-logging data, contributing to the reservoir characterization of gas-hydrate-bearing sediments. [ABSTRACT FROM AUTHOR]

Despite recent progress of numerical air quality models, accurate prediction of fine particulate matter (PM 2.5) is still challenging because of uncertainties in physical and chemical parameterizations, meteorological data, and emission inventory databases. Recent advances in artificial neural networks can be used to overcome limitations in numerical air quality models. In this study, a deep neural network (DNN) model was developed for a 3 d forecasting of 6 h average PM 2.5 concentrations: the day of prediction (D+0), 1 d after prediction (D+1), and 2 d after prediction (D+2). The DNN model was evaluated against the currently operational Community Multiscale Air Quality (CMAQ) modeling system in South Korea. Our study demonstrated that the DNN model outperformed the CMAQ modeling results. The DNN model provided better forecasting skills by reducing the root-mean-squared error (RMSE) by 4.1, 2.2, and 3.0 µ g m -3 for the 3 consecutive days, respectively, compared with the CMAQ. Also, the false-alarm rate (FAR) decreased by 16.9 %p (D+0), 7.5 %p (D+1), and 7.6 %p (D+2), indicating that the DNN model substantially mitigated the overprediction of the CMAQ in high PM 2.5 concentrations. These results showed that the DNN model outperformed the CMAQ model when it was simultaneously trained by using the observation and forecasting data from the numerical air quality models. Notably, the forecasting data provided more benefits to the DNN modeling results as the forecasting days increased. Our results suggest that our data-driven machine learning approach can be a useful tool for air quality forecasting when it is implemented with air quality models together by reducing model-oriented systematic biases. [ABSTRACT FROM AUTHOR]

South Koreas National Groundwater Monitoring Network (NGMN) was installed during the early 1990s to detect the trends in groundwater levels; however, a revised NGMN plan is required in consideration of climate change and human activities. Linear trend analyses of the groundwater levels, Cl concentration, and NO3-N concentration of 521 monitoring wells were conducted to define the downward and upward trends. The attributes of 14 items relating to topography, stream proximity, land use, soil, hydrogeology, and well density were extracted from thematic maps for each monitoring site. An artificial neural network (ANN) model for groundwater level trends was developed using these 14 input variables to predict the downward (output variable: 1) and non-downward (output variable: 0) trends at any grid point in a standard watershed. Candidate sites for new groundwater monitoring wells were suggested based on the probability of the existence of two trends for groundwater levels. Candidate sites were excluded if they showed upward trends of Cl and NO3-N because the primary objective of the NGMN was not to observe changes in water quality but to observe the background conditions of water quality. It was proposed to install a total of 1475 groundwater monitoring wells (existing plus new wells) by 2045, and the percentage contributions of non-downward and downward trends of groundwater levels to the total number of trends (i.e., wells) were projected to be 61.5% and 38.5%, respectively. The NGMN will play an important role in recognizing climate change, observing groundwater level declines caused by human activities, and assessing the relationship between surface water and groundwater in standard watersheds. [ABSTRACT FROM AUTHOR]

Group learning is commonly used in a wide range of classes. However, effective methods used to form groups are not thoroughly understood. In this study, we explore a quantitative method for creating project teams based on student knowledge and interests expressed in project proposals. The proposals are encoded to vector representations, ensuring that closely related proposals yield similar vectors. During this step, two widely used natural language processing algorithms are used. The first algorithm is based solely on the frequency of words used in the text, while the other considers context information using a deep neural network. The similarity scores for the proposals generated by the two algorithms are compared with those generated by human evaluators. The proposed method was applied to a group of senior students in a capstone design course in South Korea based on their project proposals on autonomous cars written in Korean. The results indicate that the contextualized encoding scheme produces more human-like text similarity vectors compared to the word frequency-based encoding scheme. This discrepancy is discussed from a context information standpoint in this study. [ABSTRACT FROM AUTHOR]

Given trends in more frequent and severe natural disaster events, developing effective risk mitigation strategies is crucial to reduce negative economic impacts, due to the limited budget for rehabilitation. To address this need, this study aims to develop a strategic framework for natural disaster risk mitigation, highlighting two different strategic implementation processes (SIPs). SIP-1 is intended to improve the predictability of natural disaster-triggered financial losses using deep learning. To demonstrate SIP-1, SIP-1 explores deep neural networks (DNNs) that learn storm and flood insurance loss ratios associated with selected major indicators and then develops an optimal DNN model. SIP-2 underlines the risk mitigation strategy at the project level, by adopting a cost–benefit analysis method that quantifies the cost effectiveness of disaster prevention projects. In SIP-2, a case study of disaster risk reservoir projects in South Korea was adopted. The validated result of SIP-1 confirmed that the predictability of the developed DNN is more accurate and reliable than a traditional parametric model, while SIP-2 revealed that maintenance projects are economically more beneficial in the long term as the loss amount becomes smaller after 8 years, coupled with the investment in the projects. The proposed framework is unique as it provides a combinational approach to mitigating economic damages caused by natural disasters at both financial loss and project levels. This study is its first kind and will help practitioners quantify the loss from natural disasters, while allowing them to evaluate the cost effectiveness of risk reduction projects through a holistic approach. [ABSTRACT FROM AUTHOR]

Monitoring and preserving natural habitats has become an essential activity in many countries today. As a native tree species in Korea, Paulownia coreana has periodically been surveyed in national ecological surveys and was identified as an important target for conservation as well as habitat monitoring and management. This study explores habitat suitability models (HSMs) for Paulownia coreana in conjunction with national ecological survey data and various environmental factors. Together with environmental variables, the national ecological survey data were run through machine learning algorithms such as Artificial Neural Network and Decision Tree & Rules, which were used to identify the impact of individual variables and create HSMs for Paulownia coreana, respectively. Unlike other studies, which used remote sensing data to create HSMs, this study employed periodical on-site survey data for enhanced validity. Moreover, localized environmental resources such as topography, soil, and rainfall were taken into account to project habitat suitability. Among the environment variables used, the study identified critical attributes that affect the habitat conditions of Paulownia coreana. Therefore, the habitat suitability modelling methods employed in this study could play key roles in planning, monitoring, and managing plants species in regional and national levels. Furthermore, it could shed light on existing challenges and future research needs. [ABSTRACT FROM AUTHOR]

Understanding the concentration and distribution of cyanobacteria blooms is an important aspect of managing water quality problems and protecting aquatic ecosystems. Airborne hyperspectral imagery (HSI)—which has high temporal, spatial, and spectral resolutions—is widely used to remotely sense cyanobacteria bloom, and it provides the distribution of the bloom over a wide area. In this study, we determined the input spectral bands that were relevant in effectively estimating the main two pigments (PC, Phycocyanin; Chl-a, Chlorophyll-a) of cyanobacteria by applying data-driven algorithms to HSI and then evaluating the change in the spatio-temporal distribution of cyanobacteria. The input variables for the algorithms consisted of reflectance band ratios associated with the optical properties of PC and Chl-a, which were calculated by the selected hyperspectral bands using a feature selection method. The selected input variable was composed of six reflectance bands (465.7–589.6, 603.6–631.8, 641.2–655.35, 664.8–679.0, 698.0–712.3, and 731.4–784.1 nm). The artificial neural network showed the best results for the estimation of the two pigments with average coefficients of determination 0.80 and 0.74. This study proposes relevant input spectral information and an algorithm that can effectively detect the occurrence of cyanobacteria in the weir pool along the Geum river, South Korea. The algorithm is expected to help establish a preemptive response to the formation of cyanobacterial blooms, and to contribute to the preparation of suitable water quality management plans for freshwater environments. [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]

Purpose: It is important to forecast local trading volumes as well as global trading volumes because the real estate market is always characterized as a localized market. The house trading volume at the local level is forecast through appropriate models to enhance the predictive accuracy. Design/methodology/approach: Four representative housing submarkets in South Korea are selected, and their trading volumes are forecast. A well-established time-series model and a deep learning algorithm are employed: the autoregressive integrated moving average (ARIMA) model and the recurrent neural network (RNN), respectively. The trading volumes in adjacent areas are utilized as covariates, and an ensemble prediction is applied additionally to improve the model performance. Findings: The results indicate no significant difference in prediction performance between the ARIMA model and the RNN, which can be attributed to the insufficient amount of data used. It is discovered that the spillover effects of trading volumes across the study areas can be exploited to improve the predictive accuracy, and that the diversity of the predicted values from the candidate models can be used to increase the forecasting accuracy further. Originality/value: Whereas property prices have been investigated extensively, the discussion on forecasting trading activity of properties is limited in the literature. The results of this study are expected to promote more interest in adopting a local perspective and using a diversity of predicted values when forecasting house trading volumes. [ABSTRACT FROM AUTHOR]

Reliable estimates of peak particle velocity (PPV) from blasting-induced vibrations at a construction site play a crucial role in minimizing damage to nearby structures and maximizing blasting efficiency. However, reliably estimating PPV can be challenging due to complex connections between PPV and influential factors such as ground conditions. While many efforts have been made to estimate PPV reliably, discrepancies remain between measured and predicted PPVs. Here, we analyzed various methods for assessing PPV with several key relevant factors and 1191 monitored field blasting records at 50 different open-pit sites across South Korea to minimize the discrepancies. Eight prediction models are used based on artificial neural network, conventional empirical formulas, and multivariable regression analyses. Seven influential factors were selected to develop the prediction models, including three newly included and four already formulated in empirical formulas. The three newly included factors were identified to have a significant influence on PPV, as well as the four existing factors, through a sensitivity analysis. The measured and predicted PPVs were compared to evaluate the performances of prediction models. The assessment of PPVs by an artificial neural network yielded the lowest errors, and site factors, K and m were proposed for preliminary open-pit blasting designs. [ABSTRACT FROM AUTHOR]

The Youngsan River estuary, located on the southwest coast of South Korea, has transitioned from a natural to an artificial estuary since dike construction in 1981 separated freshwater and seawater zones. This artificial transition has induced changes in the physical properties and circulation within the estuary, which has led to hypoxia and algal blooms. In this study, an artificial neural network (ANN) model was employed to simulate phytoplankton variations, including algal blooms and size fractions based on chlorophyll a, using data obtained by long-term monitoring (2008–2018) of the seawater zone of the Youngsan River estuary. The model was validated through statistical analyses, and the validated model was used to determine the contribution of the environmental factors on size-fractionated phytoplankton variations. The statistical validation of the model showed extremely low sum square error (SSE ≤ 0.0003) and root mean square error (RMSE ≤ 0.0173) values, with R2 ≥ 0.9952. The accuracy of the model predictions was high, despite the considerable irregularity and wide range of phytoplankton variations in the estuary. With respect to phytoplankton size structure, the contribution of seasonal environmental factors such as water temperature and solar radiation was high for net-sized chlorophyll a, whereas the contribution of factors such as freshwater discharge and salinity was high for nano-sized chlorophyll a, which includes typical harmful algae. Notably, because the Youngsan River estuary is influenced by a monsoon climate—characterized by high precipitation in summer—the contribution of freshwater discharge to harmful algal blooms is predicted to increase during this period. Our results suggest that the ANN model can be an important tool for understanding the influence of freshwater discharge, which is essential for managing algal blooms and maintaining the ecosystem health of altered estuaries. [ABSTRACT FROM AUTHOR]

Introduction: This scoping review aims to provide an overview of the existing evidence on the use of artificial intelligence (AI) and machine learning (ML) in orthodontics, its translation into clinical practice, and what limitations do exist that have precluded their envisioned application. Methods: A scoping review of the literature was carried out following the PRISMA-ScR guidelines. PubMed was searched until July 2020. Results: Sixty-two articles fulfilled the inclusion criteria. A total of 43 out of the 62 studies (69.35%) were published this last decade. The majority of these studies were from the USA (11), followed by South Korea (9) and China (7). The number of studies published in non-orthodontic journals (36) was more extensive than in orthodontic journals (26). Artificial Neural Networks (ANNs) were found to be the most commonly utilized AI/ML algorithm (13 studies), followed by Convolutional Neural Networks (CNNs), Support Vector Machine (SVM) (9 studies each), and regression (8 studies). The most commonly studied domains were diagnosis and treatment planning—either broad-based or specific (33), automated anatomic landmark detection and/or analyses (19), assessment of growth and development (4), and evaluation of treatment outcomes (2). The different characteristics and distribution of these studies have been displayed and elucidated upon therein. Conclusion: This scoping review suggests that there has been an exponential increase in the number of studies involving various orthodontic applications of AI and ML. The most commonly studied domains were diagnosis and treatment planning, automated anatomic landmark detection and/or analyses, and growth and development assessment. [ABSTRACT FROM AUTHOR]

Drought is among the most hazardous climatic disasters that significantly influence various aspects of the environment and human life. Qualitative and reliable drought forecasting is important worldwide for effective planning and decision-making in disaster-prone regions. Data-driven models have been extensively used for drought forecasting, but due to the inadequacy of information on model performance, the selection of an appropriate forecasting model remains a challenge. This study concerns a comparative analysis of six machine learning (ML) techniques widely used for hydrological drought forecasting. The standardized runoff index (SRI) was calculated at a seasonal (3-month) time scale for the period 1973 to 2016 in four selected watersheds of the Han River basin in South Korea. The ML models employed were built-ins, using precipitation, temperature, and humidity as input variables and the SRI as the target variable. The results indicated that all the ML models were able to map the relationship for seasonal SRI using the applied input vectors. The decision tree (DT) technique outperformed in all the watersheds with an average mean absolute error (MAE)=0.26 , root mean square error (RMSE)=0.34 , Nash-Sutcliffe efficiency (NSE)=0.87 , and coefficient of determination (R2)=0.89. The performances of the support vector machine (SVM) and deep learning neural network (DLNN) were similar, whereas the fuzzy rule-based system (FRBS) performed very well compared to the artificial neural network (ANN) and the adaptive neuro-fuzzy inference system (ANFIS). The overall findings of this study indicate that, considering performance criteria and computation time, the DT was the most accurate ML technique for hydrological drought forecasting in the Han River basin. [ABSTRACT FROM AUTHOR]

Understanding the global distribution of atmospheric black carbon (BC) is essential for unveiling its climatic effect. However, there are still large uncertainties regarding the simulation of BC transport due to inadequate information about the removal process. We accessed the wet removal rate of BC in East Asia based on long-term measurements over the 2010–2016 period at three representative background sites (Baengnyeong and Gosan in South Korea and Noto in Japan). The average wet removal rate, represented by transport efficiency (TE), i.e., the fraction of undeposited BC particles during transport, was estimated to be 0.73 in East Asia from 2010 to 2016. According to the relationship between accumulated precipitation along trajectory and TE, the wet removal efficiency was lower in East and North China but higher in South Korea and Japan, implying the importance of the aging process and frequency of exposure to below- and in-cloud scavenging conditions during air mass transport. Moreover, the wet scavenging in winter and summer showed the highest and lowest efficiency, respectively, although the lowest removal efficiency in summer was primarily associated with a reduced BC aging process because the in-cloud scavenging condition was dominant. The average half-life and e -folding lifetime of BC were 2.8 and 7.1 d , respectively, which is similar to previous studies, but those values differed according to the geographical location and meteorological conditions of each site. Next, by comparing TE from the FLEXible PARTicle (FLEXPART) Lagrangian transport model (version 10.4), we diagnosed the scavenging coefficients (s -1) of the below- and in-cloud scavenging scheme implemented in FLEXPART. The overall median TE from FLEXPART (0.91) was overestimated compared to the measured value, implying the underestimation of wet scavenging coefficients in the model simulation. The median of the measured below-cloud scavenging coefficient showed a lower value than that calculated according to FLEXPART scheme by a factor of 1.7. On the other hand, the overall median of the calculated in-cloud scavenging coefficients from the FLEXPART scheme was highly underestimated by 1 order of magnitude, compared to the measured value. From an analysis of artificial neural networks, the convective available potential energy, which is well known as an indicator of vertical instability, should be considered in the in-cloud scavenging process to improve the representative regional difference in BC wet scavenging over East Asia. For the first time, this study suggests an effective and straightforward evaluation method for wet scavenging schemes (both below and in cloud), by introducing TE along with excluding effects from the inaccurate emission inventories. [ABSTRACT FROM AUTHOR]

East Asian summer monsoon (EASM)-driven rapid hydroclimatic variation is a crucial factor with major socioeconomic impacts. Nevertheless, decadal- to centennial-scale EASM variability over the last two millennia is still poorly understood. Pollen-based quantitative annual precipitation (PqPann) and annual precipitation reconstructed by artificial neural networks (ANNs) for the period 650–1940 CE were reconstructed from a paleo-reservoir in South Korea. ANNs reconstruction was performed to compensate for a hiatus section. On a decadal timescale, 10 high-precipitation periods were identified, and PqPann and ANNs reconstructions were comparable to local instrumental rainfall and historic drought records. Biotic lags to rapid climatic changes ranging from 25 to 100 years were recognized by asynchronous pollen and speleothem responses to precipitation. We suggest that PqPann-based decadal- to centennial-scale climatic change reconstruction should take biotic lags into account, although the lags can be ignored on the millennial scale. The position of the EASM rainband influenced rainfall magnitude. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) have been extensively used to forecast monthly precipitation for water resources management over the past few decades. Efforts to produce more accurate and stable forecasts face ongoing challenges as the so‐called single‐ANN (S‐ANN) approach has several limitations, particularly regarding uncertainty. Many attempts have been made to deal with different types of uncertainties by applying ensemble approaches. Here, we propose a new ANN ensemble model (ANN‐ENS) dealing with uncertainty in model structure and input variable selection to provide a more accurate and stable forecasting performance. This model is structured by generating various input layers, considering all the candidate input variables (i.e.,large‐scale climate indices and lagged precipitation). We developed a modified backward elimination method to select the preliminary input variables from all the candidate input variables. Then, we tested and validated the proposed ANN‐ENS using observed monthly precipitation from 10 meteorological stations in the Han River basin, South Korea. Our results demonstrated that the ANN‐ENS enhanced the forecasting performance in terms of both accuracy and stability. Although a significant uncertainty was introduced by using all the candidate input variables, the forecasting result outperformed S‐ANNs for all employed stations. Additionally, the ANN‐ENS provided a more stable forecasting performance in comparison with S‐ANNs, which are highly sensitive. Moreover, the generated ensemble members were slightly biased at some stations but were generally reliable. Key Points: We develop a new artificial neural network (ANN) ensemble model (ANN‐ENS) to deal with uncertainty in model structure and input variable selectionThis is based on a modified backward elimination method that improves preliminary input variables for the ANN‐ENSThe resulting ANN‐ENS demonstrated remarkable performance in terms of forecasting accuracy, stability, and ensemble reliability [ABSTRACT FROM AUTHOR]

In order to protect human lives and infrastructure, as well as to minimize the risk of damage, it is important to predict and respond to natural disasters in advance. However, currently, the standardized disaster response system in South Korea still needs further advancement, and the response phase systems need to be improved to ensure that they are properly equipped to cope with natural disasters. Existing studies on intelligent disaster management systems (IDSSs) in South Korea have focused only on storms, floods, and earthquakes, and they have not used past data. This research proposes a new conceptual framework of an IDSS for disaster management, with particular attention paid to wildfires and cold/heat waves. The IDSS uses big data collected from open application programming interface (API) and artificial intelligence (AI) algorithms to help decision-makers make faster and more accurate decisions. In addition, a simple example of the use of a convolutional neural network (CNN) to detect fire in surveillance video has been developed, which can be used for automatic fire detection and provide an appropriate response. The system will also consider connecting to open source intelligence (OSINT) to identify vulnerabilities, mitigate risks, and develop more robust security policies than those currently in place to prevent cyber-attacks. [ABSTRACT FROM AUTHOR]

While the exchange of data files or programs on the Internet grows exponentially, most users are vulnerable to infected files, especially to malicious non-executables. Due to the circumstances between South and North Korea, many malicious actions have recently been found in Hangul Word Processor (HWP) non-executable files because the HWP is widely used in schools, military facilities, and government institutions of South Korea. The HWP file usually has one or more byte streams that are often used for the malicious actions. Based on an assumption that infected byte streams have particular patterns, we design a convolutional neural network (CNN) to grasp such patterns. We conduct experiments on our prepared 534 HWP files, and demonstrate that the proposed CNN achieves the best performance compared to other machine learning models. As new malicious attacks keep emerging, we will keep collecting such HWP files and investigate better model structures. [ABSTRACT FROM AUTHOR]

A deep recurrent neural network system based on a long short-term memory (LSTM) model was developed for daily PM 10 and PM 2.5 predictions in South Korea. The structural and learnable parameters of the newly developed system were optimized from iterative model training. Independent variables were obtained from ground-based observations over 2.3 years. The performance of the particulate matter (PM) prediction LSTM was then evaluated by comparisons with ground PM observations and with the PM concentrations predicted from two sets of 3-D chemistry-transport model (CTM) simulations (with and without data assimilation for initial conditions). The comparisons showed, in general, better performance with the LSTM than with the 3-D CTM simulations. For example, in terms of IOAs (index of agreements), the PM prediction IOAs were enhanced from 0.36–0.78 with the 3-D CTM simulations to 0.62–0.79 with the LSTM-based model. The deep LSTM-based PM prediction system developed at observation sites is expected to be further integrated with 3-D CTM-based prediction systems in the future. In addition to this, further possible applications of the deep LSTM-based system are discussed, together with some limitations of the current system. [ABSTRACT FROM AUTHOR]

Inter-floor noise, i.e., noise transmitted from one floor to another floor through walls or ceilings in an apartment building or an office of a multi-layered structure, causes serious social problems in South Korea. Notably, inaccurate identification of the noise type and position by human hearing intensifies the conflicts between residents of apartment buildings. In this study, we propose a robust approach using deep convolutional neural networks (CNNs) to learn and identify the type and position of inter-floor noise. Using a single mobile device, we collected nearly 2000 inter-floor noise events that contain 5 types of inter-floor noises generated at 9 different positions on three floors in a Seoul National University campus building. Based on pre-trained CNN models designed and evaluated separately for type and position classification, we achieved type and position classification accuracy of 99.5% and 95.3%, respectively in validation datasets. In addition, the robustness of noise type classification with the model was checked against a new test dataset. This new dataset was generated in the building and contains 2 types of inter-floor noises at 10 new positions. The approximate positions of inter-floor noises in the new dataset with respect to the learned positions are presented. [ABSTRACT FROM AUTHOR]

The temporal variability monthly precipitation time series for Korea is decomposed using singular spectrum analysis (SSA) to detect hidden periodicity information in the data, and to compare the forecasting performance of combining linear recurrent formulas (LRFs) and artificial neural networks (ANNs). The SSA technique is used on monthly precipitation data to decompose and reconstruct the components, including a special inerratic feature for reconstruction and successful forecasting using LRF and ANN analysis. These components obtained using SSA indicate the behavior of the monthly precipitation data as a trend, or as periodic and/or quasi-periodic oscillations. The LRF and ANN methods were applied to several leading components to forecast the monthly precipitation. Results show that reconstruction and forecasting using the SSA-ANN model is more accurate than using the SSA-LRF model, especially for peak value forecasting. This validates the use of the SSA-ANN combined model for effective reconstruction and forecasting of monthly precipitation. [ABSTRACT FROM AUTHOR]

Colorectal cancer (CRC) is a major global health concern. Its early diagnosis is extremely important, as it determines treatment options and strongly influences the length of survival. Histologic diagnosis can be made by pathologists based on images of tissues obtained from a colonoscopic biopsy. Convolutional neural networks (CNNs)—i.e., deep neural networks (DNNs) specifically adapted to image data—have been employed to effectively classify or locate tumors in many types of cancer. Colorectal histology images of 28 normal and 29 tumor samples were obtained from the National Cancer Center, South Korea, and cropped into 6806 normal and 3474 tumor images. We developed five modifications of the system from the Visual Geometry Group (VGG), the winning entry in the classification task in the 2014 ImageNet Large Scale Visual Recognition Competition (ILSVRC) and examined them in two experiments. In the first experiment, we determined the best modified VGG configuration for our partial dataset, resulting in accuracies of 82.50%, 87.50%, 87.50%, 91.40%, and 94.30%, respectively. In the second experiment, the best modified VGG configuration was applied to evaluate the performance of the CNN model. Subsequently, using the entire dataset on the modified VGG-E configuration, the highest results for accuracy, loss, sensitivity, and specificity, respectively, were 93.48%, 0.4385, 95.10%, and 92.76%, which equates to correctly classifying 294 normal images out of 309 and 667 tumor images out of 719. [ABSTRACT FROM AUTHOR]

Cochlodinium polykrikoides (C. polykrikoides) is a phytoplankton that causes red tides every year in the middle of the South Sea of Korea. C. polykrikoides is a harmful Algae that has migratory ability and causes the fisheries damage over a long period of wide sea area if it causes red tide once. To minimize red tide damage, it is important to anticipate and prepare the red tide occurrence timing and location in advance. In this study, we predicted the occurrence of red tide of C. polykrikoides using machine learning techniques and compared the results of each algorithm. Logistic regression model, decision tree model, and multilayer neural network model were used for prediction of red tide occurrence. To produce the data set for model learning, we used the red tide occurrence map provided by the National Institute of Fisheries Science, the Local Data Assimilation and Prediction System (LDAPS) provided by the Korea Meteorological Agency, and the G1SST provided by the National Oceanic and Atmospheric Administration (NOAA). The feature vectors used for modeling consisted of 59 elements, which were made by using temperature, water temperature, precipitation, solar radiation, wind direction and wind speed. Only a very small number of red tide cases can be collected compared to the case of no red tide cases. Thus, an imbalance data problem arises in the data set. To overcome this imbalanced data problem, we used adding noise after oversampling to data of red tide occurrence to solve the difference of data between two classes.The data set is divided into 8 : 2 to prevent over-fitting and 80% is used as the learning data. The remaining 20% was used to evaluate the performance of each model. As a result of evaluating the prediction performance of each model, the multilayer neural network model showed the highest prediction accuracy. [ABSTRACT FROM AUTHOR]