• 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.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.111-126
• /
• 2020

Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.

• (The) Research of the performance art and culture
• /
• no.41
• /
• pp.5-38
• /
• 2020

The current state of performance halls in South Korea is closely related to the performance art and culture of the nation as the culture of putting on and enjoying a performance is deeply rooted in public culture and arts halls representing each area at the local government level. Today, public culture and arts halls have multiple management purposes, and the subjects of their management are in the public domain including the central and local governments or investment and donation foundations in overwhelming cases. Public culture and arts halls thus have close correlations with the institutional aspect of cultural policies as the objects of culture and art policies at the central and local government level. The full-blown era of public culture and arts halls opened up in the 1980s~1990s, during which multi-purpose performance halls of a similar structure became universal around the nation. Public culture and arts halls of the uniform shape were distributed around the nation with no premise of genre characteristics or local environments for arts, and this was attributed to the cultural policies of the military regime. The Park Chung-hee regime proclaimed Yusin that was beyond the Constitution and enacted the Culture and Arts Promotion Act(September, 1972), which was the first culture and arts act in the nation. Based on the act, a five-year plan for the promotion of culture and arts(1973) was made and led to the construction of cultural facilities. "Public culture and arts" halls or "culture" halls were built to serve multiple purposes around the nation because the Culture and Arts Promotion Act, which is called the starting point of the nation's legal system for culture and arts, defined "culture and arts" as "matters regarding literature, art, music, entertainment, and publications." The definition became a ground for the current "multi-purpose" concept. The organization of Ministry of Culture and Public Information set up a culture and administration system to state its supervision of "culture and arts" and distinguish popular culture from the promotion of arts. During the period, former President Park exhibited his perception of "culture=arts=culture and arts" in his speeches. Arts belonged to the category of culture, but it was considered as "culture and arts." There was no department devoted to arts policies when the act was enacted with a broad scope of culture accepted. This ambiguity worked as a mechanism to mobilize arts in ideological utilizations as a policy. Against this backdrop, the Sejong Center for the Performing Arts, a multi-purpose performance hall, was established in 1978 based on the Culture and Arts Promotion Act under the supervision of Ministry of Culture and Public Information. There were, however, conflicts of value over the issue of accepting the popular music among the "culture and arts = multiple purposes" of the system, "culture ≠ arts" of the cultural organization that pushed forward its establishment, and "culture and arts = arts" perceived by the powerful class. The new military regime seized power after Coup d'état of December 12, 1979 and failed at its culture policy of bringing the resistance force within the system. It tried to differentiate itself from the Park regime by converting the perception into "expansion of opportunities for the people to enjoy culture" to gain people's supports both from the side of resistance and that of support. For the Chun Doo-hwan regime, differentiating itself from the previous regime was to secure legitimacy. Expansion of opportunities to enjoy culture was pushed forward at the level of national distribution. This approach thus failed to settle down as a long-term policy of arts development, and the military regime tried to secure its legitimacy through the symbolism of hardware. During the period, the institutional ground for public culture and arts halls was based on the definition of "culture and arts" in the Culture and Arts Promotion Act enacted under the Yusin system of the Park regime. The "multi-purpose" concept, which was the management goal of public performance halls, was born based on this. In this context of the times, proscenium performance halls of a similar structure and public culture and arts halls with a similar management goal were established around the nation, leading to today's performance art and culture in the nation.

• Korean Journal of Acupuncture
• /
• v.31 no.2
• /
• pp.66-78
• /
• 2014

Objectives : The specificity of acupuncture point has been a highly controversial subject. Existing researches said that ion-distribution differences are observed on the acupuncture point. This study was conducted under the assumption that multiple ionic changes induced by muscle fatigue would be different between the acupuncture point with non-acupuncture point. Methods : To induce the identical fatigue, twenty subjects performed the knee extension/flexion exercise using the Biodex System 3. ST32 and ST33 as well as adjacent non-acupuncture points were selected. We measured blood lactate and analyzed the median frequency(MF) and peak torque. To obtain the information on the extracellular fluid(ECW), intracellular fluid(ICW) and cell membrane indirectly, we used the multi-frequency bioelectrical impedance analysis(MF-BIA) method. Results : MF, peak torque and blood lactate level of all measurement sites were gradually returned to normal. Re resistance of ST32 had a stronger response, but a non-acupuncture point adjacent to ST33 had a larger response up to 20 minutes post exercise. Ri resistances were similar for both acupoints and non-acupoints. The $C_m$ capacitance of ST32 had a stronger response after inducing fatigue, but ST33 had a smaller response than a non-acupuncture point adjacent to it. Conclusions : In comparison with before and after inducing fatigue, the specificity of acupuncture points was not clearly observed. Hence, we concluded that the body composition factors extraction method had the limitation as a method of finding the specificity of acupuncture points by inducing fatigue.

• Journal of Veterinary Clinics
• /
• v.24 no.4
• /
• pp.479-485
• /
• 2007

A retrospective study of 94 hypercalcemic dogs was performed to find out most common causes that lead to hypercalcemia through investigating dogs referred to the Veterinary Teaching Hospital of Konkuk University from 2002 to 2004. During the study period, hypercalcemia was found in 94 dogs of 19 breeds, and they were evaluated as case group. Control group was made up of 94 dogs of 18 breeds without hypercalcemia admitted for the same study period. For general signalments, there were no significant differences between case and control group with the exception of age distribution. Shih-tzu(17.02%) and Yorkshire terrier(26.60%) was the most common breed in case and control group, respectively. The most common diseases associated with hypercalcemia were chronic renal failure (18.09%), acute renal failure(14.89%), and renal calculi(6.38%). Malignant neoplasia(lymphoma, hemangiosarcoma, chronic lymphocytic leukemia, mammary gland tumor, and multiple myeloma) and endocrinopathies(hyperadrenocorticism, hyperthyroidism, hypoadrenocorticism, and hypothyroidism) occupied 8.5% and 6.4%, respectively. This report is a first retrospective study of hypercalcemic dogs in South Korea.

• Korean Journal of Environmental Agriculture
• /
• v.15 no.1
• /
• pp.91-104
• /
• 1996

The viability loss or death of weed seeds buried in soil can be induced by infrared irradiation which has good penetration in moist soil. By using this principle of pre-emergence soil-treatment, the study was carried out to obtain basic information needed to develop the effective weed control method for the production of less polluted agricultural products. An apparatus for irradiating infrared was constructed by using ceramic material with high emissivity. The LPG was used as fuel for producing infrared by heating ceramic material. The soil heated in this study was loam with four levels of moisture contents (0.6, 5.7, 10.7, 15.1 % wb). The temperature distribution was measured at various soil depths when soil with different moisture content was irradiated with infrared for three different times (30, 60, 90 sec). The soil depths with duration time of minimum 3 minutes over $80^{\circ}C$, temperature inducing viability loss of weed seeds, were investigated. When the moisture content of soil was 0.6 and 5.7 % wb, the soil depths which can induce viability loss of weed seeds was greatly increased with increasing irradiation time. However, any depths of soil tested in this study was not reached to the temperature of $80^{\circ}C$ when 30 seconds of irradiation time was applied on soil with moisture content of 10.7 or 15.1 % wb. Generally, the soil depth needed for viability loss of weed seeds was decreased with increasing moisture content of soil. Also, longer irradiation time was required to induce viability loss of weed seeds with increasing moisture content of soil.

• Korean Journal of Agricultural Science
• /
• v.13 no.1
• /
• pp.17-32
• /
• 1986

To obtain basic information needed for developing better pearl barley varieties, a total of 148 lines of pearl barley were collected from nationwide survey except for Kangwon and Chejoo provinces and classified by principal component analysis. The results are summarized as follows : 1. Variabilities of characters for all lines except for leaf width and 100 K. Wt.(Unpolished) were high enough to indicate variation of lines. 2. Correlation coefficients among 18 characters were high enough and they showed the shape of normal distribution, more or less, inclined toward positive values. 3. The lines could be classified into four groups by correlation coefficient for 18 characters : Group I was characterized as the lines composed of grain and plant type, Group II maturity, Group III the number of tillers, and Group IV the nature of germination, respectively. 4. About 60% of the total variation could be appreciated by the first four principal components and about 89% of the total variation by the first ten principal components. 5. Contribution of characters to principal components was variable and was high at upper principal components and low at lower principal components. 6. The value of eigen vector corresponding to those which had high significant correlation coefficient between characters was almost of the same value. 7. The lines were classified into four groups by principal component analysis. 8. The lines were also classified into four groups by taxonomic distance. Group I included 79 lines, Group II 40 lines, Group III 22 lines, and Group IV 7 lines, respectively. 9. Four groups classified by taxonomic distance could be characterized as follow : Group I : medium height plant, small kernels, medium maturity, and narrow and short leaf, Group II : short height plant, small kernels, early maturity, and narrow and short leaf. Group III : tall height plant, large kernels, late maturity, and broad and long leaf. Group IV : short height plant, large kernels, medium maturity, and narrow and short leaf.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.28-35
• /
• 2006

Statistical models of shape variability based on active shape models (ASMs) have been successfully utilized to perform segmentation and recognition tasks in two-dimensional (2D) images. Three-dimensional (3D) model-based approaches are more promising than 2D approaches since they can bring in more realistic shape constraints for recognizing and delineating the object boundary. For 3D model-based approaches, however, building the 3D shape model from a training set of segmented instances of an object is a major challenge and currently it remains an open problem in building the 3D shape model, one essential step is to generate a point distribution model (PDM). Corresponding landmarks must be selected in all1 training shapes for generating PDM, and manual determination of landmark correspondences is very time-consuming, tedious, and error-prone. In this paper, we propose a novel automatic method for generating 3D statistical shape models. Given a set of training 3D shapes, we generate a 3D model by 1) building the mean shape fro]n the distance transform of the training shapes, 2) utilizing a tetrahedron method for automatically selecting landmarks on the mean shape, and 3) subsequently propagating these landmarks to each training shape via a distance labeling method. In this paper, we investigate the accuracy and compactness of the 3D model for the human liver built from 50 segmented individual CT data sets. The proposed method is very general without such assumptions and can be applied to other data sets.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.1
• /
• pp.9-16
• /
• 2018

Landscape architecture is an indispensable professional service in building sustainable land and urban environments. The landscape architecture industry is closely related to the promotion of the health and welfare of the people, urban revitalization and residential environment improvement as well as job creation. Despite various public interest values of landscape architecture, the growth engine of the landscape architecture industry, which is supposed to improve the quality of landscape services, has stagnated. In 2015, the Landscape Architecture Promotion Act was enacted to provide a landscape architectural promotion facility and complex system to support revitalization through the integration of the landscape architecture industry. The purpose of this study is to suggest an improvement plan to enhance the effectiveness of the landscape architectural promotion facility and complex system. The results of the analysis are as follows: First, workers and experts in landscape architecture recognized the need for policies and projects to promote the landscape architecture industry. Second, the industrial types suitable for the landscape architectural promotion facility were landscape design, landscape maintenance and management, and landscape construction industry. Meanwhile the industrial types suitable for a landscape architectural promotion complex were landscape trees and landscape facilities production and distribution. Third, the expected effect of the designation of the landscape architectural facility was 'the increase of the business opportunity through the expansion of the network'. On the other hand, that of the landscape architectural promotion complex was 'the activation of various information sharing'. Fourth, 'the size of the local government landscape architecture industry and the capacity to cultivate' was the most important among the designation criteria of the landscape architectural promotion facility. As for that of the landscape architectural promotion complex, the 'feasibility of promotion plan' was the most crucial. Fifth, 'tax benefit and deductible exemption' was considered as a necessary support method for the activation of the landscape architectural promotion facility, and 'maintenance and management fee support' was recognized in the case of the landscape architectural promotion complex.