• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.29-45
• /
• 2015

Response modeling is a well-known research issue for those who have tried to get more superior performance in the capability of predicting the customers' response for the marketing promotion. The response model for customers would reduce the marketing cost by identifying prospective customers from very large customer database and predicting the purchasing intention of the selected customers while the promotion which is derived from an undifferentiated marketing strategy results in unnecessary cost. In addition, the big data environment has accelerated developing the response model with data mining techniques such as CBR, neural networks and support vector machines. And CBR is one of the most major tools in business because it is known as simple and robust to apply to the response model. However, CBR is an attractive data mining technique for data mining applications in business even though it hasn't shown high performance compared to other machine learning techniques. Thus many studies have tried to improve CBR and utilized in business data mining with the enhanced algorithms or the support of other techniques such as genetic algorithm, decision tree and AHP (Analytic Process Hierarchy). Ahn and Kim(2008) utilized logit, neural networks, CBR to predict that which customers would purchase the items promoted by marketing department and tried to optimized the number of k for k-nearest neighbor with genetic algorithm for the purpose of improving the performance of the integrated model. Hong and Park(2009) noted that the integrated approach with CBR for logit, neural networks, and Support Vector Machine (SVM) showed more improved prediction ability for response of customers to marketing promotion than each data mining models such as logit, neural networks, and SVM. This paper presented an approach to predict customers' response of marketing promotion with Case Based Reasoning. The proposed model was developed by applying different weights to each feature. We deployed logit model with a database including the promotion and the purchasing data of bath soap. After that, the coefficients were used to give different weights of CBR. We analyzed the performance of proposed weighted CBR based model compared to neural networks and pure CBR based model empirically and found that the proposed weighted CBR based model showed more superior performance than pure CBR model. Imbalanced data is a common problem to build data mining model to classify a class with real data such as bankruptcy prediction, intrusion detection, fraud detection, churn management, and response modeling. Imbalanced data means that the number of instance in one class is remarkably small or large compared to the number of instance in other classes. The classification model such as response modeling has a lot of trouble to recognize the pattern from data through learning because the model tends to ignore a small number of classes while classifying a large number of classes correctly. To resolve the problem caused from imbalanced data distribution, sampling method is one of the most representative approach. The sampling method could be categorized to under sampling and over sampling. However, CBR is not sensitive to data distribution because it doesn't learn from data unlike machine learning algorithm. In this study, we investigated the robustness of our proposed model while changing the ratio of response customers and nonresponse customers to the promotion program because the response customers for the suggested promotion is always a small part of nonresponse customers in the real world. We simulated the proposed model 100 times to validate the robustness with different ratio of response customers to response customers under the imbalanced data distribution. Finally, we found that our proposed CBR based model showed superior performance than compared models under the imbalanced data sets. Our study is expected to improve the performance of response model for the promotion program with CBR under imbalanced data distribution in the real world.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.161-177
• /
• 2015

With the rapid evolution of technology, the size, number, and the type of databases has increased concomitantly, so data mining approaches face many challenging applications from databases. One such application is discovery of fraud patterns from agricultural product wholesale transaction instances. The agricultural product wholesale market in Korea is huge, and vast numbers of transactions have been made every day. The demand for agricultural products continues to grow, and the use of electronic auction systems raises the efficiency of operations of wholesale market. Certainly, the number of unusual transactions is also assumed to be increased in proportion to the trading amount, where an unusual transaction is often the first sign of fraud. However, it is very difficult to identify and detect these transactions and the corresponding fraud occurred in agricultural product wholesale market because the types of fraud are more intelligent than ever before. The fraud can be detected by verifying the overall transaction records manually, but it requires significant amount of human resources, and ultimately is not a practical approach. Frauds also can be revealed by victim's report or complaint. But there are usually no victims in the agricultural product wholesale frauds because they are committed by collusion of an auction company and an intermediary wholesaler. Nevertheless, it is required to monitor transaction records continuously and to make an effort to prevent any fraud, because the fraud not only disturbs the fair trade order of the market but also reduces the credibility of the market rapidly. Applying data mining to such an environment is very useful since it can discover unknown fraud patterns or features from a large volume of transaction data properly. The objective of this research is to empirically investigate the factors necessary to detect fraud transactions in an agricultural product wholesale market by developing a data mining based fraud detection model. One of major frauds is the phantom transaction, which is a colluding transaction by the seller(auction company or forwarder) and buyer(intermediary wholesaler) to commit the fraud transaction. They pretend to fulfill the transaction by recording false data in the online transaction processing system without actually selling products, and the seller receives money from the buyer. This leads to the overstatement of sales performance and illegal money transfers, which reduces the credibility of market. This paper reviews the environment of wholesale market such as types of transactions, roles of participants of the market, and various types and characteristics of frauds, and introduces the whole process of developing the phantom transaction detection model. The process consists of the following 4 modules: (1) Data cleaning and standardization (2) Statistical data analysis such as distribution and correlation analysis, (3) Construction of classification model using decision-tree induction approach, (4) Verification of the model in terms of hit ratio. We collected real data from 6 associations of agricultural producers in metropolitan markets. Final model with a decision-tree induction approach revealed that monthly average trading price of item offered by forwarders is a key variable in detecting the phantom transaction. The verification procedure also confirmed the suitability of the results. However, even though the performance of the results of this research is satisfactory, sensitive issues are still remained for improving classification accuracy and conciseness of rules. One such issue is the robustness of data mining model. Data mining is very much data-oriented, so data mining models tend to be very sensitive to changes of data or situations. Thus, it is evident that this non-robustness of data mining model requires continuous remodeling as data or situation changes. We hope that this paper suggest valuable guideline to organizations and companies that consider introducing or constructing a fraud detection model in the future.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.39-57
• /
• 2012

Recently, due to the introduction of high-tech equipment in interactive exhibits, many people's attention has been concentrated on Interactive exhibits that can double the exhibition effect through the interaction with the audience. In addition, it is also possible to measure a variety of audience reaction in the interactive exhibition. Among various audience reactions, this research uses the change of the facial features that can be collected in an interactive exhibition space. This research develops an artificial neural network-based prediction model to predict the response of the audience by measuring the change of the facial features when the audience is given stimulation from the non-excited state. To present the emotion state of the audience, this research uses a Valence-Arousal model. So, this research suggests an overall framework composed of the following six steps. The first step is a step of collecting data for modeling. The data was collected from people participated in the 2012 Seoul DMC Culture Open, and the collected data was used for the experiments. The second step extracts 64 facial features from the collected data and compensates the facial feature values. The third step generates independent and dependent variables of an artificial neural network model. The fourth step extracts the independent variable that affects the dependent variable using the statistical technique. The fifth step builds an artificial neural network model and performs a learning process using train set and test set. Finally the last sixth step is to validate the prediction performance of artificial neural network model using the validation data set. The proposed model is compared with statistical predictive model to see whether it had better performance or not. As a result, although the data set in this experiment had much noise, the proposed model showed better results when the model was compared with multiple regression analysis model. If the prediction model of audience reaction was used in the real exhibition, it will be able to provide countermeasures and services appropriate to the audience's reaction viewing the exhibits. Specifically, if the arousal of audience about Exhibits is low, Action to increase arousal of the audience will be taken. For instance, we recommend the audience another preferred contents or using a light or sound to focus on these exhibits. In other words, when planning future exhibitions, planning the exhibition to satisfy various audience preferences would be possible. And it is expected to foster a personalized environment to concentrate on the exhibits. But, the proposed model in this research still shows the low prediction accuracy. The cause is in some parts as follows : First, the data covers diverse visitors of real exhibitions, so it was difficult to control the optimized experimental environment. So, the collected data has much noise, and it would results a lower accuracy. In further research, the data collection will be conducted in a more optimized experimental environment. The further research to increase the accuracy of the predictions of the model will be conducted. Second, using changes of facial expression only is thought to be not enough to extract audience emotions. If facial expression is combined with other responses, such as the sound, audience behavior, it would result a better result.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.4
• /
• pp.57-65
• /
• 2016

This study was conducted a visual landscape resources inventory and grade assessment on natural resources and cultural resources of Chiaksan National Park. Landscapes of National Parks are categorized into four types: seascape, mountain landscape, village landscape, and temple historical landscape. Landscape lists were constructed for each district for a total of 120 lists through field research on 7 trails. The landscape list per trail has Guryong~Birobong(31%), Seungnam~Namdaebong(22%), Geumdae~Namdaebong(16%), Bugok~Hanenggu(165), Hwanggol~Ipseoksa(6%), Hyangrobong~Nandaebong(5%) and Godeunjae~Wontonggol(4%). Landscape Assessment items were divided into five characteristics of view, unique, use, history culture, natural reflected by item. Items were divided into three grades of landscape by 4, 3, 2, 1 for each item of the assessment criteria and Delphi survey. Mountain landscapes were assessed in I grade of 72 sites, II grade of 26 sites, III grade of 7 sites. Temple Historical landscapes were assessed in I grade of 4 sites, II grade of 7 sites, III grade of 4 sites. The study results can be used as a basis for mountain parks management. It is necessary to focus on managing the landscape of I grade site. The higher ratings of the Mountain landscapes are related to the view and natural score. Also, the grading of Temple Historical landscapes is related to the history cultural, natural and use score. In addition, the mountain landscape were identified as being included outside landscape resources, the place of landscape resources with outside ratings were higher and the view was related. Landscape management is needed for the conservation of Mountain landscape and Temple Historical landscape type rating as excellent areas on the basis of the results of the inventory and assessment. For future improvement the Guryong-Birobong trail is judged as a harmonious representative landscape of the Mountain and Temple Historical landscape and will require conservation as a focus management area. In the case of Mountain landscape improvements, maintenance such as pruning trees, wood observatory and interpretation sign for a landscape with minimal inhibitory landscaping is needed. When installing artificial facilities in the Temple Historical landscapes, the use of materials harmonizing with the surroundings landscape must be considered as well as the standards of facilities limitation.

• Journal of Korean Society of Forest Science
• /
• v.101 no.1
• /
• pp.163-174
• /
• 2012

CBI(Composite Burn Index) developed by USDA Forest Service is a index to measure burn severity based on remote sensing. In Korea, the CBI has been used to investigate the burn severity of fire sites for the last few years. However, it has been an argument on that CBI is not adequate to capture unique characteristics of Korean forests, and there has been a demand to develop KCBI(Korean Composite Burn Index). In this regard, this study aimed to develop KCBI by adjusting the CBI and to validate its applicability by using remote sensing technique. Uljin and Youngduk, two large fire sites burned in 2011, were selected as study areas, and forty-four sampling plots were assigned in each study area for field survey. Burn severity(BS) of the study areas were estimated by analyzing NDVI from SPOT images taken one month later of the fires. Applicability of KCBI was validated with correlation analysis between KCBI index values and NDVI values and their confusion matrix. The result showed that KCBI index values and NDVI values were closely correlated in both Uljin (r = -0.54 and p<0.01) and Youngduk (r = -0.61 and p<0.01). Thus this result supported that proposed KCBI is adequate index to measure burn severity of fire sites in Korea. There was a number of limitations, such as the low correlation coefficients between BS and KCBI and skewed distribution of KCBI sampling plots toward High and Extreme classes. Despite of these limitations, the proposed KCBI showed high potentials for estimating burn severity of fire sites in Korea, and could be improved by considering the limitations in further studies.

• Journal of radiological science and technology
• /
• v.27 no.2
• /
• pp.35-43
• /
• 2004

Radioprotective effects of ginseng extracts on liver damage induced by high energy x-ray were studied. To one group of ICR male mice were given white(50 mg/kg/day for 7days, orally) and fermenta ginseng extracts(500 mg/kg/day for 7days, orally) before irrdiation. To another group were irradiated by 5 Gy dose of high energy x-ray. Contrast group were given with saline(0.1 ml). This study also investigated the radioprotective effect between SOD, CAT, hydrogen peroxide and ginseng extracts on hepatic damage. This study measured the level of superoxide dismutase(SOD), catalase(CAT), hydrogen peroxide($H_2O_2$) in liver tissue. Administrating orally white (50 mg/kg/day for 7days, orally) and fermenta ginseng extracts(500 mg/kg/day), the activity of SOD, CAT were generally increased and the hydrogen peroxide($H_2O_2$) was decreased. After irradiation, the activity of SOD, CAT were generally decreased and the hydrogen peroxide($H_2O_2$) was increased. Therefore, ginseng extracts increased antioxidative enzyme activity. And We know that the antioxidatant effect of extracts from white and fermenta ginseng protect radiation damage by direct antioxidant effect involving SOD, CAT. It was included that ginseng can protect against radiation damage through its antioxidatant properties.

• Korean Journal of Soil Science and Fertilizer
• /
• v.17 no.2
• /
• pp.125-133
• /
• 1984

To obtain the basic date for the improvement of cultural and managemental problems caused by soil characteristics and soil productivity in rice cultivation of Honam area, morphological characteristics of rice soils were investigated in Mangeng-Dongjin and Yeongsan Water-sheds, and compaired differences between two major Watersheds. The results obtained are summarized as follows: 1. According to U.S.D.A. Soil Taxonomy Classification System, eight great groups are distributed in rice soils of two major Watersheds. More than 50% of rice paddy soils are classified as Haplaquepts. 2. Two Watersheds are quite different in soil parent materials. In Mangeong-Dongjin Watershed, most soils (55.1%) are derived from fluvic-marine deposits. Remainders are derived from local alluvium (24.7%) and alluvium (14.2%). But in Yeongsan Watershed, the order is local alluvium>alluvium>fluvio-marine deposits. 3. Rice soils occur mostly in coastal and inland flat-site with the slope of less than 2% (57.8%) in Mangeong-Dongjin Watersheds. However, in Yeongsan Watershed, flat-site and low undulating terrace are mostly distributed (52.9%). 4. About 81.9, 61.4 and 53.3% of rice soils are classified as fine textured in Yeongsan, Dongjin, and Mangeong Watersheds, respectively. 5. More normal paddy soils and less sandy paddy soils are distributed in Yeongsan Watershed. The results indicate that more rice soils are classified as productivity classes of I and II in Yeongsan Watershed than in Mangeong-Dongjin Watersheds.

• Economic and Environmental Geology
• /
• v.38 no.4 s.173
• /
• pp.435-450
• /
• 2005

The purpose of the study is to analyze the hydrogeochemical characteristics by multivariate statistical method, to interpret the hydrogeochemical processes for the new variables calculated from principal components analysis (PCA), and to infer the groundwater flow and circulation mechanism by applying the geostatistical methods for each element and principal component. Chloride and nitrate are the most influencing components for groundwater quality, and the contents of $NO_3$ increased by the input of agricultural activities show the largest variation. The results of PCA, a multivariate statistical method, show that the first three principal components explain $73.9\%$ of the total variance. PC1 indicates the increase of dissolved ions, PC2 is related with the dissolution of carbonate minerals and nitrate contamination, and PC3 shows the effect of cation exchange process and silicate mineral dissolution. From the results of experimental semivariogram, the components of groundwater are divided into two groups: one group includes electrical conductivity (EC), Cl, Na, and $NO_3$, and the other includes $HCO_3,\;SiO_2,$ Ca, and Sr. The results for spatial distribution of groundwater components showed that EC, Cl, and Na increased with approaching the coastal line and nitrate has close relationship with the presence of agricultural land. These components are also correlated with the topographic features reflecting the groundwater recharge effect. The kriging analysis by using principal components shows that PC 1 has the different spatial distribution of Cl, Na, and EC, possibly due to the influence of pH, Ca, Sr, and $HCO_3$ for PC1. It was considered that the linear anomaly zone of PC2 in western area was caused by the dissolution of carbonate mineral. Consequently, the application of multivariate and geostatistical methods for groundwater in the study area is very useful for determining the quantitative analysis of water quality data and the characteristics of spatial distribution.

• Korean Journal of Dental Materials
• /
• v.44 no.1
• /
• pp.61-68
• /
• 2017

This study evaluated the effects of various cleaning methods on the shear bond strength of zirconia ceramics after saliva contamination. Eighty zirconia disk specimens were divided into 8 groups. All groups were treated with one coat of MDP primer. All specimens (except the negative control) were contaminated with human saliva on the zirconia surface. The positive control went through the bonding procedure immediately after contamination without any cleaning procedure. With the exception of control groups, the remaining six groups were rinsed with water and either applied with MDP recoating (WATER+MDP) or without MDP recoating (WATER). While some were cleaned with a Ivoclean with MDP recoating (IVOCLEAN+MDP) or not applied with MDP recoating(IVOCLEAN), others were cleaned with a 1% NaOCl solution with MDP recoating (NaOCl+MDP) or without MDP recoating (NaOCl). The shear bond strength of all specimens were measured after being stored in distilled water at $37^{\circ}C$ for 24 hours. The data was analyzed statistically by an analysis of ANOVA, Tukey's post hoc test and Student's t-test was used to compare the shear bond strength according to the re-coating of MDP after the cleaning procedure. The positive control group showed the lowest shear bond strength value, and the WATER group and NaOCl group showed no significant difference when compared to the positive control group. The IVOCLEAN group showed significantly higher shear bond strength when compared to Water group and NaOCl group but not with the group of negative control. After rinsing with water or the NaOCl solution, the comparison of the single coating of MDP and re-coating of MDP showed different shear bond strengths but there was no significant difference to the negative control. After rinsing with Ivoclean, there was no significant difference to the negative control regardless of the recoating of MDP. In conclusion, the shear bond strength was affected by the cleansing procedure and Ivoclean was found to be effective regardless of the re-coating of MDP. When water or the NaOCl solution is used to remove surface contaminants, the re-coating of MDP provides a positive effect on cementation.

• Korean Journal of Legislative Studies
• /
• v.22 no.2
• /
• pp.113-156
• /
• 2016

Media scholars take a lion stake in power circle. Not only do they take a part in media policies but seize prestigious positions like board members in Korea Communication Commission(KCC). Unfortunately, though, little has been known about who they are, what qualifications they have, and whether they meet public interests. This paper attempts to unveil the mechanism of those politicized intellectuals who are specialized on the media. Two categories divided into 'representative' and 'expertise' are employed for this purpose. On the one hand, the representative means the degree of committment into such public services as participation in conferences or non-profit organizations. On the other hand, the number of research articles, books and projects belong to the expertise. Evaluation levels consist of 'excellence, good and average' were allocated to those scholars who are(were) in 'Power Hole,' where decision makings come into being. Some interesting observations were made though this study. First of all, such criteria as representative and expertise vaguely suggested by the laws were hardly fit into those intellectuals, Rarely did they commit into public service let alone showing vigilance in academic activities. Secondly, both ideological loyalty and political activities in line with the government had much to do with taking such positions. Thirdly, not surprisingly, it showed that to graduate from Seoul National University and have Ph.D. degree from U.S.A. was one of the most essential factors. In final, most of them were very good at taking advantage of the press in way of boosting their publicity. To attend at policy making processes either in form of board members or advisers is inevitable for media experts. However, as shown in this study, such qualification of public service and academic eagerness shouldn't be underestimated. Academic integrity not selling intelligence solely for private interests needs to be protected as well. The authors hope this study to provide a valuable opportunity to establish a kind of ethical standards in participating into politics.