• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.5
• /
• pp.533-542
• /
• 2021

The main objective of this article is to investigate the existence of the lunar effect during the full moon period (FM period) and the new moon period (NM period) on the selected Islamic stock market returns and volatilities. For this purpose, the Ordinary Least Squares model, Autoregressive Conditional Heteroscedasticity model, Generalised Autoregressive Conditional Heteroscedasticity model and Generalised Autoregressive Conditional Heteroscedasticity-in-Mean model are employed using the mean daily returns data between January 2010 and December 2019. Next, the log-likelihood, Akaike Information Criterion and Schwarz Information Criterion value are analyzed to determine the best models for explaining the returns and volatility of returns. The empirical results have deduced that, during the NM period, excluding Malaysia, the total mean daily returns for all of the selected countries have increased mean daily returns in contrast to the mean daily returns during the FM period. The volatility shocks are intense and conditional volatility is persistent in all countries. Subsequently, the volatility behavior tends to have lower volatility during the FM period and NM period in the Islamic stock market, except Malaysia. This article also concluded that the ARCH (1) model is the preferred model for stock returns whereas GARCH-M (1, 1) is preferred for the volatility of returns.

• 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.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.5
• /
• pp.91-104
• /
• 2003

A masquerader is someone who pretends to be another user while invading the target user's accounts, directories, or files. The masquerade attack is the most serious computer misuse. Because, in most cases, after securing the other's password, the masquerader enters the computer system. The system such as IDS could not detect or response to the masquerader. The masquerade detection is the effort to find the masquerader automatically. This system will detect the activities of a masquerader by determining that user's activities violate a profile developed for that user with his audit data. From 1988, there are many efforts on this topic, but the success of the offers was limited and the performance was unsatisfactory. In this report we propose efficient masquerade detection system using SVM which create the user profile.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.1
• /
• pp.115-122
• /
• 2006

The most methods for intrusion detection are based on the misuse detection which accumulates hewn intrusion information and makes a decision of an attack against any behavior data. However it is very difficult to detect a new or modified aoack with only the collected patterns of attack behaviors. Therefore, if considering that the method of anomaly behavior detection actually has a high false detection rate, a new approach is required for very huge intrusion patterns based on sequence. The approach can improve a possibility for intrusion detection of known attacks as well as modified and unknown attacks in addition to the similarity measurement of intrusion patterns. This paper proposes a method which applies the multiple sequence alignments technique to the similarity matching of the sequence based intrusion patterns. It enables the statistical analysis of sequence patterns and can be implemented easily. Also, the method reduces the number of detection alerts and false detection for attacks according to the changes of a sequence size.

• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.17-26
• /
• 2021

Recently, COVID-19 has spread and time to stay at home has been increasing in accordance with quarantine guidelines of the government such as recommendations to refrain from going out. As a result, the number of single-person households staying at home is also increasingsingle-person households are less likely to be notified to the outside world in times of emergency than multi-person households. This study collects various situations occurring in the home with lidar, image, and voice sensors and analyzes the data according to the sensors through their respective algorithms. Using this method, we analyzed abnormal patterns such as emergency situations and conducted research to detect abnormal signs in humans. Artificial intelligence algorithms that detect abnormalities in people by each sensor were studied and the accuracy of anomaly detection was measured according to the sensor. Furthermore, this work proposes a fusion method that complements the pros and cons between sensors by experimenting with the detectability of sensors for various situations.

• 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 Korea Institute of Information Security & Cryptology
• /
• v.32 no.1
• /
• pp.25-38
• /
• 2022

With the diversification of payment methods and games, related financial accidents are causing serious problems for users and game companies. Recently, game companies have introduced an Fraud Detection System (FDS) for game payment systems to prevent financial incident. However, FDS is ineffective and cannot provide major evidence based on judgment results, as it requires constant change of detection patterns. In this paper, we analyze abnormal transactions among payment log data of real game companies to generate related features. One of the unsupervised learning models, Autoencoder, was used to build a model to detect abnormal transactions, which resulted in over 85% accuracy. Using X-FDS (Explainable FDS) with XAI-SHAP, we could understand that the variables with the highest explanation for anomaly detection were the amount of transaction, transaction medium, and the age of users. Based on X-FDS, we derive an improved detection model with an accuracy of 94% was finally derived by fine-tuning the importance of features that adversely affect the proposed model.

• Journal of Korea Foundry Society
• /
• v.42 no.6
• /
• pp.369-376
• /
• 2022

The die-casting process is an important process for various industries, but there are limitations in the profitability and productivity of related companies due to the high defect rate. In order to overcome this, this study has developed die-casting fault detection modules based on industrial AI technologies. The developed module is constructed from three-stage models depending on the characteristics of the dataset. The first-stage model conducts fault detection based on supervised learning from the dataset without labels. The second-stage model realizes one-class classification based on semi-supervised learning, where the dataset only has production success labels. The third-stage model corresponds to fault detection based on supervised learning, where the dataset includes a small amount of production failure cases. The developed fault detection module exhibited outstanding performance with roughly 96% accuracy for actual process data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.143-143
• /
• 2023

최근 대청댐('17), 평림댐('19) 등 광역 취수원에서 망간의 먹는 물 수질기준(0.05mg/L 이하) 초과 사례가 발생되어, 다수의 민원이 제기되는 등 취수원의 망간 관리 중요성이 부각되고 있다. 특히, 동절기 전도(Turn-over)시기에 고농도 망간이 발생되는 경우가 많은데, 현재 정수장에서는 망간을 처리하기 위해 유입구간에 필터를 설치하고 주기적으로 교체하는 방식으로 처리하고 있다. 그러나 단기간에 고농도 망간 다량 유입 시 처리용량의 한계 등 정수장에서의 공정관리가 어려워지므로 사전 예측에 의한 대응 체계 고도화가 필요한 실정이다. 본 연구는 광역취수원인 주암댐을 대상으로 망간 예측의 정확도 향상 및 예측기간 확대를 위해 다양한 머신러닝 기법들을 적용하여 비교 분석하였으며, 독립변수 및 초매개변수 최적화를 진행하여 모형의 정확도를 개선하였다. 머신러닝 모형은 수심별 탁도, 저수위, pH, 수온, 전기전도도, DO, 클로로필-a, 기상, 수문 자료 등의 독립변수와 화순정수장에 유입된 망간 농도를 종속변수로 각 변수에 해당하는 실측치를 학습데이터로 사용하였다. 그리고 데이터기반 모형의 정확도를 개선하기 위해서 성층의 수준을 판별하는 지표로서 PEA(Potential Energy Anomaly)를 도입하여 데이터 분석에 활용하고자 하였다. 분석 결과, 망간 유입률은 계절 주기에 따라 농도가 달라지는 것을 확인하였고 동절기 전도시점과 하절기 장마기간 난류생성 시기에 저층의 고농도 망간이 유입이 되는 것을 분석하였다. 또한, 두 시기의 망간 농도의 변화 패턴이 상이하므로 예측 모델은 각 계절별로 구축해 학습을 진행함으로써 예측의 정확도를 향상할 수 있었다. 다양한 머신러닝 모델을 구축하여 성능 비교를 진행한 결과, 동절기에는 Gradient Boosting Machine, 하절기에는 eXtreme Gradient Boosting의 기법이 우수하여 추론 모델로 활용하고자 하였다. 선정 모델을 통한 단기 수질예측 결과, 전도현상 발생 시기에 대한 추종 및 예측력이 기존의 데이터 모형만 적용했을 경우대비 약 15% 이상 예측 효율이 향상된 것으로 나타났다. 본 연구는 머신러닝 모델을 활용한 망간 농도 예측으로 정수장의 신속한 대응 체계 마련을 지원하고, 수처리 공정의 효율성을 높이는 데 기여할 것으로 기대되며, 후속 연구로 과거 시계열 자료 활용 및 물리모형과의 연결 등을 통해 모델의 신뢰성을 제고 할 계획이다.