• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• The Journal of Engineering Geology
• /
• v.28 no.2
• /
• pp.217-246
• /
• 2018

During the selection and characterization of target formations in the Small-scale Offshore $CO_2$ Storage Demonstration Project in the Pohang Basin, we have carefully investigated the possibility of induced earthquakes and leakage of $CO_2$ during the injection, and have designed the storage processes to minimize these effects. However, people in Pohang city have a great concern on $CO_2$-injection-intrigued seismicity, since they have greatly suffered from the 5.4 magnitude earthquake on Nov. 15, 2017. The research team of the project performed an extensive self-investigation on the safety issues, especially on the possible $CO_2$ leakage from the target formation and induced earthquakes. The target formation is 10 km apart from the epicenter of the Pohang earthquake and the depth is also quite shallow, only 750 to 800 m from the sea bottom. The project performed a pilot injection in the target formation from Jan. 12 to Mar. 12, 2017, which implies that there are no direct correlation of the Pohang earthquake on Nov. 15, 2017. In addition, the $CO_2$ injection of the storage project does not fracture rock formations, instead, the supercritical $CO_2$ fluid replaces formation water in the pore space gradually. The self-investigation results show that there is almost no chance for the injection to induce significant earthquakes unless injection lasts for a very long time to build a very high pore pressure, which can be easily monitored. The amount of injected $CO_2$ in the project was around 100 metric-tonne that is irrelevant to the Pohang earthquake. The investigation result on long-term safety also shows that the induced earthquakes or the reactivation of existing faults can be prevented successfully when the injection pressure is controlled not to demage cap-rock formation nor exceed Coulomb stresses of existing faults. The project has been performing extensive studies on critical stress for fracturing neighboring formations, reactivation stress of existing faults, well-completion processes to minimize possible leakage, transport/leakage monitoring of injected $CO_2$, and operation procedures for ensuring the storage safety. These extensive studies showed that there will be little chance in $CO_2$ leakage that affects human life. In conclusion, the Small-scale Offshore $CO_2$ Storage Demonstration Project in the Pohang Basin would not cause any induced earthquakes nor signifiant $CO_2$ leakage that people can sense. The research team will give every effort to secure the safety of the storage site.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.93-108
• /
• 2014

To support business decision making, interests and efforts to analyze and use transaction data in different perspectives are increasing. Such efforts are not only limited to customer management or marketing, but also used for monitoring and detecting fraud transactions. Fraud transactions are evolving into various patterns by taking advantage of information technology. To reflect the evolution of fraud transactions, there are many efforts on fraud detection methods and advanced application systems in order to improve the accuracy and ease of fraud detection. As a case of fraud detection, this study aims to provide effective fraud detection methods for auction exception agricultural products in the largest Korean agricultural wholesale market. Auction exception products policy exists to complement auction-based trades in agricultural wholesale market. That is, most trades on agricultural products are performed by auction; however, specific products are assigned as auction exception products when total volumes of products are relatively small, the number of wholesalers is small, or there are difficulties for wholesalers to purchase the products. However, auction exception products policy makes several problems on fairness and transparency of transaction, which requires help of fraud detection. In this study, to generate fraud detection rules, real huge agricultural products trade transaction data from 2008 to 2010 in the market are analyzed, which increase more than 1 million transactions and 1 billion US dollar in transaction volume. Agricultural transaction data has unique characteristics such as frequent changes in supply volumes and turbulent time-dependent changes in price. Since this was the first trial to identify fraud transactions in this domain, there was no training data set for supervised learning. So, fraud detection rules are generated using outlier detection approach. We assume that outlier transactions have more possibility of fraud transactions than normal transactions. The outlier transactions are identified to compare daily average unit price, weekly average unit price, and quarterly average unit price of product items. Also quarterly averages unit price of product items of the specific wholesalers are used to identify outlier transactions. The reliability of generated fraud detection rules are confirmed by domain experts. To determine whether a transaction is fraudulent or not, normal distribution and normalized Z-value concept are applied. That is, a unit price of a transaction is transformed to Z-value to calculate the occurrence probability when we approximate the distribution of unit prices to normal distribution. The modified Z-value of the unit price in the transaction is used rather than using the original Z-value of it. The reason is that in the case of auction exception agricultural products, Z-values are influenced by outlier fraud transactions themselves because the number of wholesalers is small. The modified Z-values are called Self-Eliminated Z-scores because they are calculated excluding the unit price of the specific transaction which is subject to check whether it is fraud transaction or not. To show the usefulness of the proposed approach, a prototype of fraud transaction detection system is developed using Delphi. The system consists of five main menus and related submenus. First functionalities of the system is to import transaction databases. Next important functions are to set up fraud detection parameters. By changing fraud detection parameters, system users can control the number of potential fraud transactions. Execution functions provide fraud detection results which are found based on fraud detection parameters. The potential fraud transactions can be viewed on screen or exported as files. The study is an initial trial to identify fraud transactions in Auction Exception Agricultural Products. There are still many remained research topics of the issue. First, the scope of analysis data was limited due to the availability of data. It is necessary to include more data on transactions, wholesalers, and producers to detect fraud transactions more accurately. Next, we need to extend the scope of fraud transaction detection to fishery products. Also there are many possibilities to apply different data mining techniques for fraud detection. For example, time series approach is a potential technique to apply the problem. Even though outlier transactions are detected based on unit prices of transactions, however it is possible to derive fraud detection rules based on transaction volumes.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.1
• /
• pp.51-60
• /
• 2014

In this study, ICT medical service provider's level of knowledge fire fighting safety and methods on coping with fires in the regions of Gwangju and Jeonam Province of Korea were investigated to determine the elements affecting such levels and provide basic information on the manuals for educating how to cope with the fire fighting safety in medical facilities. The data were analyzed using SPSS Win 14.0. The scores of level of knowledge fire fighting safety of ICT medical service provider's were 7.06(10 point scale), and the scores of level of recognizing how to cope with fire fighting safety were 6.61(11 point scale). level of recognizing how to cope with fire fighting safety were significantly different according to gender(t=4.12, p<.001), age(${\chi}^2$=17.24, p<.001), length of career(${\chi}^2$=22.76, p<.001), experience with fire fighting safety education(t=6.10, p<.001), level of subjective knowledge on fire fighting safety(${\chi}^2$=53.83, p<.001). In order to enhance the level of understanding of fire fighting safety and methods of coping by the ICT medical service providers it is found that: self-directed learning through avoiding the education just conveying knowledge by lecture tailored learning for individuals fire fighting education focused on experiencing actual work by developing various contents emphasizing cooperative learning deploying patients by classification systems using simulations and a study on the implementation of digital anti-fire monitoring system with multipoint communication protocol, a design and development of the smoke detection system using infra-red laser for fire detection in the wide space, video based fire detection algorithm using gaussian mixture mode developing an education manual for coping with fire fighting safety through multi learning approach at the medical facilities are required.

• Journal of Food Hygiene and Safety
• /
• v.29 no.3
• /
• pp.202-206
• /
• 2014

In this study, the bacteriological survey was examined on ice creams at manufacturing factories in Korea during the summer season of 2011. The nineteen selected among 166 samples by preliminary test were collected from 11 different manufacturing factories in four major manufacturers in May 2011. Samples from ice milk, ice creams, sherbets, and non milk fat ice creams were tested for the total aerobic bacteria, coliform bacteria, and five food borne pathogens, respectively. The results showed that the coliforms including E. coli O157:H7, Salmonella spp., Staphylococcus aureus, Clostridium perfringens, and Listeria monocytogenes were not detected on all the ice creams. The total aerobic bacteria of the packed samples examined ranged between $2.5{\times}10^3$ and $5.5{\times}10^5cfu/g$. One ice cream, two sherbets, and four ice milk samples exceeded the acceptable limits of total aerobic bacteria according to the Korean standards for ice cream ($1.0{\times}10^5cfu/g$) and others ($5.0{\times}10^4cfu/g$). The levels of these microorganisms from ice creams were higher in three original equipment manufacturers than seven self-manufacturers. Three of ten ice creams (30.0%), three of six ice milks (50.0%), and one of two sherbets (50%) exceeded the acceptable limits of total aerobic bacteria, respectively. The personnel hygiene procedures with chocolate and vanilla chip addition from the manufacturing process were the main sources of the microbial contamination of stick-bar type ice creams when being produced in a factory. Improvement of the hazard analysis critical control points (HACCP) system should be introduced into the ice cream factory to improve the microbial quality of the ice cream products in Korea.

• Tuberculosis and Respiratory Diseases
• /
• v.49 no.4
• /
• pp.412-420
• /
• 2000

Background : There is increasing concern in many countries about the problem of drug-resistant tuberculosis. Prevalence of primary drug-resistant tuberculosis is the optimal epidemiological indicator for long term monitoring of national tuberculosis control program. Our purpose was The purpose of our study is to assess clinical characteristics and socioeconomic status of patients with drug-resistant tuberculosis. Method : We studied 68 cases with drug-resistant Mycobacterium tuberculosis infection diagnosed at the Ewha Womans University Mokdong Hospital from March, 1995 to February, 2000. Results : Patients with primary drug-resistant tuberculosis(PDR) were younger (39.6$\pm$16.3 years vs. 48.2$\pm$16.5 years ; p<0.05), had more population of less than more were under the age of 40 years aged -group(62.9% vs. 36.4% ; p<0.05) and were more highly educated than those with acquired drug-resistant tuberculosis(ADR)(38.9% vs. 11.1% ; p<0.05). In patients with ADR, the rates of familial history of tuberculosis and living in a rented house residence in a rented house were increased higher than compared with to those of patients with PDR. Patients with ADR had more involved lobes(2.0$\pm$0.8 vs. 1.4$\pm$0.7 ; p<0.01) and longer treatment duration than those with PDR(18.3$\pm$7.2 months vs. 10.6$\pm$6.3 months ; p<0.05). Patients with ADR showed larger numbers of resistant were resistant to more number of drugs, lower hospitalization rate and higher rate of self-interruption of medication than those with PDR. In patients with PDR, mono-drug resistance was increased, whereas poly- and multi-drug resistances were decreased compared with those with ADR. Resistance to isoniazid was the highest among antituberculosis drugs, and resistance to isoniazid in patients with ADR was higher than that in patients with PDR(90.9% vs. 71.4% ; p<0.05). Conclusions : Patients with ADR were more likely to include more population be of lower socioeconomic class, and patients with PDR seem seemed to be young and socially active population. For control of drug-resistant Mycobacterium tuberculosis infection, proper isolation and prevention of patient with drug-resistant tuberculosis are needed.

• Tuberculosis and Respiratory Diseases
• /
• v.61 no.2
• /
• pp.121-128
• /
• 2006

Background: The "health-related quality of life" (HRQL) for patients with chronic respiratory disease has been emphasized, because chronic respiratory disease (CRD) is chronic and progressive, and it finally causes disability. HRQL instruments may be useful for monitoring patients' progress or for determining the most appropriate choice of treatment. We describe the adapting St George's Respiratory Questionnaire (SGRQ), which is a self-administered questionnaire developed by Jones et al. (1991), into the Korean version for covering three domains of health for the patients suffering with airways disease. Method: We obtained the original SGRQ from the author after gaining permission. For adaptation, we created an expert panel and translated the original questionnaire into Korean language. The translated questionnaire was then back-translated by bilingual experts and we compared it with the original questionnaire. After correction and feasibility testing, 74 patients with chronic respiratory disease (COPD, asthma, destroyed lung) completed the Korean version of the SGRQ. The clinical status of each patients was evaluated concurrently with measurement of their health status. Result: The Korean version of the SGRQ was acceptable and easy to understand. Cronbach's alpha reliability coefficient was 0.92 for the overall scale and 0.63 for the "Symptoms", subscale, 0.87 for the "Activity", subscale, and 0.89 for the "Impacts" subscales. The correlation coefficients between the overall score and the Borg scale score, oxygen saturation, and forced expiratory volume in one second ($FEV_1$) were 0.52, -0.32 and -0.26, respectively. These results support that the Korean SGRQ was correlated with other measurements. Conclusion: The Korean SGRQ was reliable and valid for patients with chronic respiratory disease, such as COPD, asthma, and destroyed lung. The SGRQ score was well correlated with other respiratory measurements as well. Although further studies should complete the adaptation work, our results suggest that the SGRQ may be used in Korea and also for international studies involving Korean CRD patients.

• KDI Journal of Economic Policy
• /
• v.32 no.4
• /
• pp.1-34
• /
• 2010

We conduct a comprehensive risk analysis of household debt in Korea for the first time using the whole sample credit bureau (CB) data of 2.2 million individual debtors. After analysing debt service capacity profiles of debtor groups classified by the borrower characteristics such as income, age, occupation, credit scoring, and the type of creditor business companies, we investigate the impact of interest rate and income changes on debt service-to-income ratios (DTIs) and default rates of respective debtor groups. Empirical results indicate that debt service burdens are relatively high for low income wage earners, high income self-employed, low income capital and card loan holders, and high income mutual savings loan holders. We also find that debtors from multiple financial companies are particularly weak in their debt service capacity. The scenario analysis indicates that financial companies, with the current level of capital buffers, may be able to absorb negative consequences arising from the increase in DTIs and loan default rates if the interest rate and income changes remain modest. However, the negative consequences may fall disproportionately on non-bank financial companies such as capital, credit card, and mutual savings banks, whose debtors' DTIs are already high. We also find that the refinancing risk of household debt is relatively high in Korea as more than half of household mortgage debts are bullet loans. As the DTIs of mortgage loan holders are already high, under the current DTI regulation, mortgage loans may not be readily refinanced especially when the interest rate rises. Disruptions in mortgage loan refinancing may put downward pressure on housing prices, which may in turn magnify refinancing risk under the current loan-to-value (LTV) regulation. Overall our analysis suggests that, for more effective monitoring of household debt risk, it is necessary to combine existing surveillance schemes based on macro aggregate indicators with more comprehensive and detailed risk analyses based on micro individual data.

• Korean journal of applied entomology
• /
• v.54 no.4
• /
• pp.401-407
• /
• 2015

This study describes the development of a method for monitoring Aphis gossypii in greenhouse cucumber fields that was used during 2013 and 2014. The dispersion pattern of A. gossypii was determined by commonly used methods: Taylor's power law (TPL) and Iwao's patchiness regression (IPR). The sample unit was determined by linear regression analysis between mean density of sample unit versus whole plant. The optimum sample unit for different plant growth stages was two leaves (median and the lowest + 1 leaf) when the total number of leaves was less than nine, and three leaves (4th, 7th from canopy, and the lowest +1 leaf) when the total number of leaves was greater than nine. A. gossypii showed an aggregated distribution pattern, as the slopes of both TPL and IPR lines were greater than 1. TPL provided a better description of the mean-variance relationship than did IPR. The slopes and intercepts of TPL and IPR from leaf samples did not differ between the surveyed years. Fixed precision levels (D) for a sequential sampling plan were developed using Green's and Kuno's equations based on the number of aphid in a leaf sample. Green's method was more efficient than Kuno's to stop sampling. The number of samples needed to estimate the density of A. gossypii increased at higher D levels and lower mean densities. The cumulative number of aphids needed to stop sampling increased at higher D levels and with fewer plants sampled. Thus to estimate 10 aphids per leaf, 13 plants needed to be sampled, and the cumulative number of aphids to stop sampling was 131.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1B
• /
• pp.51-60
• /
• 2006

Water quality improvement in mattress/filter system using porous material like slag from industrial activity and zeolite that has been studied for environment improvement and pollution abatement is very useful in polluted stagnant stream channel. Slag is consisted of CaO, $SiO_2$, $Al_2O_3$ and $Fe_2O_3$. Slag with large specific surface area of porosity has been used such as sludge settling and adsorptive materials. Because slag is porous, it can be used for purification filter. As slag is used as filled materials of mattress/filter system and the system has good advantages for the waste water treatment, water recycling, and the improvement of water quality at the same time and so on. Because zeolite has much advantage of cation exchange, adsorption, catalyst and dehydration characteristics, It is used for environment improvement of livestock farms, treatment of artificial sewage and waste water, improvement of drinking water quality, radioactive waste disposal and radioactive material pollution control. In this study, according to verifying effects of water quality improvement of fill materials by porosity that 38.6%, 45.8% and 49.8% respectively in the stagnant stream channel, water quality monitoring of inflow and outflow was conducted on pH, DO, BOD, COD, SS, T-N and T-P. Mattress/filter system was able to accelerate water quality improvement by biofilter as waste water flows through gap of mattress/filter fill materials and by contact catalysis, absorption, catabolism by biofilm. Mattress/filter system used slag and zeolite forms biofilm easily and accelerates adsorption of organic matter. As a result, mattress/filter system increases water self-purification and accelerates water quality improvement available for stream water clean-up.