• Atmosphere
• /
• v.29 no.3
• /
• pp.295-309
• /
• 2019

Due to frequent occurrence of abnormal weather, the need to improve the accuracy of subseasonal prediction has increased. Here we analyze the performance of weekly predictions out to 6 weeks by GloSea5 climate model. The performance in circulation field from January 1991 to December 2010 is first analyzed at each grid point using the 500-hPa geopotential height. The anomaly correlation coefficient and mean-square skill score, calculated each week against the ECWMF ERA-Interim reanalysis data, illustrate better prediction skills regionally in the tropics and over the ocean and seasonally during winter. Secondly, we evaluate the predictability of 7 major teleconnection patterns in the Northern Hemisphere: North Atlantic Oscillation (NAO), East Atlantic (EA), East Atlantic/Western Russia (EAWR), Scandinavia (SCAND), Polar/Eurasia (PE), West Pacific (WP), Pacific-North American (PNA). Skillful predictability of the patterns turns out to be approximately 1~2 weeks. During summer, the EAWR and SCAND, which exhibit a wave pattern propagating over Eurasia, show a considerably lower skill than the other 5 patterns, while in winter, the WP and PNA, occurring in the Pacific region, maintain the skill up to 2 weeks. To account for the model's bias in reproducing the teleconnection patterns, we measure the similarity between the teleconnection patterns obtained in each lead time. In January, the model's teleconnection pattern remains similar until lead time 3, while a sharp decrease of similarity can be seen from lead time 2 in July.

• Atmosphere
• /
• v.32 no.2
• /
• pp.149-162
• /
• 2022

This study investigated the prediction skill of the Asian dust seasonal forecasting model (GloSea5-ADAM) on the Asian dust and meteorological variables related to the dust generation for the period of 1991~2016. Additionally, we evaluated the prediction skill of those variables depending on the combination of the initial dates in the sub-seasonal scale for the dust source region affecting South Korea. The Asian dust and meteorological variables (10 m wind speed, 1.5 m relative humidity, and 1.5 m air temperature) from GloSea5-ADAM were compared to that from Synoptic observation and European Centre for medium range weather forecasts reanalysis v5, respectively, based on Mean Bias Error (MBE), Root Mean Square Error (RMSE), and Anomaly Correlation Coefficient (ACC) as evaluation criteria. In general, the Asian dust and meteorological variables in the source region showed high ACC in the prediction scale within one month. For all variables, the use of the initial dates closest to the prediction month led to the best performances based on MBE, RMSE, and ACC, and the performances could be improved by adjusting the number of ensembles considering the combination of the initial date. ACC was as high as 0.4 in Spring when using the closest two initial dates. In particular, the GloSea5-ADAM shows the best performance of Asian dust generation with an ACC of 0.60 in the occurrence frequency of Asian dust in March when using the closest initial dates for initial conditions.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.30-37
• /
• 2022

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

• Journal of the Korean earth science society
• /
• v.43 no.4
• /
• pp.511-519
• /
• 2022

Given the significant social and economic impact caused by heat waves, there is a pressing need to predict them with high accuracy and reliability. In this study, we analyzed the real-time forecast data from six models constituting the Subseasonal-to-Seasonal (S2S) prediction project, to elucidate the key mechanisms contributing to the prediction of the recent record-breaking Korean heat wave event in 2018. Weekly anomalies were first obtained by subtracting the 2017-2020 mean values for both S2S model simulations and observations. By comparing four Korean heat-wave-related indices from S2S models to the observed data, we aimed to identify key climate processes affecting prediction accuracy. The results showed that superior performance at predicting the 2018 Korean heat wave was achieved when the model showed better prediction performance for the anomalous anticyclonic activity in the upper troposphere of Eastern Europe and the cyclonic circulation over the Western North Pacific (WNP) region compared to the observed data. Furthermore, the development of upper-tropospheric anticyclones in Eastern Europe was closely related to global warming and the occurrence of La Niña events. The anomalous cyclonic flow in the WNP region coincided with enhancements in Madden-Julian oscillation phases 4-6. Our results indicate that, for the accurate prediction of heat waves, such as the 2018 Korean heat wave, it is imperative for the S2S models to realistically reproduce the variabilities over the Eastern Europe and WNP regions.

• Journal of the Korean Geosynthetics Society
• /
• v.22 no.1
• /
• pp.67-74
• /
• 2023

In order to monitor the stability of slopes, research on data-based slope failure prediction and early warning is increasing. However, most papers overlook the quality of data. Poor data quality can cause problems such as false alarms. Therefore, this paper proposes a two-step hybrid approach consisting of rules and machine learning models for quality control of data collected from slopes. The rule-based has the advantage of high accuracy and intuitive interpretation, and the machine learning model has the advantage of being able to derive patterns that cannot be explicitly expressed. The hybrid approach was able to take both of these advantages. Through a case study, the performance of using the two methods alone and the case of using the hybrid approach was compared, and the hybrid method was judged to have high performance. Therefore, it is judged that using a hybrid method is more appropriate than using the two methods alone for data quality control.

• Journal of Information Technology Services
• /
• v.22 no.5
• /
• pp.99-108
• /
• 2023

As the computerization of hospitals becomes more advanced, security issues regarding data generated from various medical devices within hospitals are gradually increasing. For example, because hospital data contains a variety of personal information, attempts to attack it have been continuously made. In order to safely protect data from external attacks, each hospital has formed an internal team to continuously monitor whether the computer network is safely protected. However, there are limits to how humans can monitor attacks that occur on networks within hospitals in real time. Recently, artificial intelligence models have shown excellent performance in detecting outliers. In this paper, an experiment was conducted to verify how well an artificial intelligence model classifies normal and abnormal data in network traffic data generated from medical devices. There are several models used for outlier detection, but among them, Random Forest and Tabnet were used. Tabnet is a deep learning algorithm related to receive and classify structured data. Two algorithms were trained using open traffic network data, and the classification accuracy of the model was measured using test data. As a result, the random forest algorithm showed a classification accuracy of 93%, and Tapnet showed a classification accuracy of 99%. Therefore, it is expected that most outliers that may occur in a hospital network can be detected using an excellent algorithm such as Tabnet.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.48-56
• /
• 2024

In the livestock industry, detecting environmental outliers and predicting data are crucial tasks. Outliers in livestock environment data, typically gathered through time-series methods, can signal rapid changes in the environment and potential unexpected epidemics. Prompt detection and response to these outliers are essential to minimize stress in livestock and reduce economic losses for farmers by early detection of epidemic conditions. This study employs two methods to experiment and compare performances in setting thresholds that define outliers in livestock environment data outlier detection. The first method is an outlier detection using Mean Squared Error (MSE), and the second is an outlier detection using a Dynamic Threshold, which analyzes variability against the average value of previous data to identify outliers. The MSE-based method demonstrated a 94.98% accuracy rate, while the Dynamic Threshold method, which uses standard deviation, showed superior performance with 99.66% accuracy.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.6
• /
• pp.543-551
• /
• 2023

As climate change continues to prompt an increasing demand for advancements in disaster and safety management technologies to address abnormal high water temperatures, typhoons, floods, and droughts, sea surface temperature has emerged as a pivotal factor for swiftly assessing the impacts of summer harmful algal blooms in the seas surrounding Korean Peninsula and the formation and dissipation of cold water along the East Coast of Korea. Therefore, this study sought to gauge predictive performance by leveraging statistical methods and deep learning algorithms to harness sea surface temperature data effectively for marine anomaly research. The sea surface temperature data employed in the predictions spans from 2018 to 2022 and originates from the Heuksando Tidal Observatory. Both traditional statistical ARIMA methods and advanced deep learning models, including long short-term memory (LSTM) and gated recurrent unit (GRU), were employed. Furthermore, prediction performance was evaluated using the attention LSTM technique. The technique integrated an attention mechanism into the sequence-to-sequence (s2s), further augmenting the performance of LSTM. The results showed that the attention LSTM model outperformed the other models, signifying its superior predictive performance. Additionally, fine-tuning hyperparameters can improve sea surface temperature performance.

• The Journal of the Korea Contents Association
• /
• v.16 no.3
• /
• pp.81-90
• /
• 2016

This study aims to investigate the association between stock performance and credit ratings, and credit rating changes using a sample of 1,691 KRX firm-years that acquire equity in the form of long-term bonds from 2002 to 2013. Previous U.S. literature is mixed with regard to the relation between credit ratings and stock price. On one hand, there is evidence of a positive relation between credit ratings and stock prices, an anomaly established in U.S. studies. On the other hand, the CAPM model suggests a negative relation between stock prices and credit ratings, implying that investors expect financial rewards for bearing additional risk. To our knowledge, we are the first to examine the relationship between stock price and default risk proxied by credit ratings in period t+1. We find a negative (positive) relation between credit ratings (risk) in period t+1 and stock returns in period t, suggesting that credit rating agencies do not consider stock returns as a metric with the potential to influence default risk. Our results suggest that market participants may prefer firms with higher credit risk because of expected higher returns.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_2
• /
• pp.567-576
• /
• 2013

The determination of the geoid in South Korea is a national imperative for the modernization of height datums, specifically the orthometric height and the dynamic height, that are used to monitor hydrological systems and environments with accuracy and easy revision, if necessary. The geometric heights above a reference ellipsoid, routinely obtained by GPS, lead immediately to vertical control with respect to the geoid for hydrological purposes if the geoid height above the ellipsoid is known accurately. The geoid height is determined from gravimetric data, traditionally ground data, but in recent times also from airborne data. This paper illustrates the basic concepts for combining these two types of data and gives a preliminary performance assessment of either set or their combination for the determination of the geoid in South Korea. It is shown that the most critical aspect of the combination is the gravitational effect of the topographic masses above the geoid, which, if not properly taken into account, introduces a significant bias of about 8 mgal in the gravity anomalies, and which can lead to geoid height bias errors of up to 10 cm. It is further confirmed and concluded that achieving better than 5 cm precision in geoid heights from gravimetry remains a challenge that can be surmounted only with the proper combination of terrestrial and airborne data, thus realizing higher data resolution over most of South Korea than currently available solely from the airborne data.