• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.795-801
• /
• 2013

Recently, support vector machine has been widely used in various application fields due to its superiority of classification performance comparing with decision tree and neural network. Since support vector machine is basically designed for the binary classification problem, output coding method to analyze the classification result of multiclass binary classifier is used for the application of support vector machine into the multiclass problem. However, previous feature selection method for output coding based support vector machine found the features to improve the overall classification accuracy instead of improving each classification accuracy of each classifier. In this paper, we propose the novel feature selection method to find the features for maximizing the classification accuracy of each binary classifier in output coding based support vector machine. Experimental result showed that proposed method significantly improved the classification accuracy comparing with previous feature selection method.

• Management & Information Systems Review
• /
• v.32 no.1
• /
• pp.43-62
• /
• 2013

In order to know the characteristics of high visit web sites that many people have visited, 37 high visit websites of plastic surgery were compared to 69 benchmark sites of same industry. We selected 36 web site attributes that can be measured objectively from existing studies and composed the data set of 36 attributes multiplied by 106 websites. For analysis, Multiple Discriminant Analysis(MDA) and Decision Tree Technique are conducted for searching what attributes divide two group definitely. The result of this study shows the dividing attributes fall into 3 categories like 'Community', 'Mobile', 'Up to date'. Thus, we are able to conclude that high visit plastic surgery web sites are community centric site but not contents centric, response a change to mobile environment rapidly and are maintained with tide up to date. The methodology employed in this study provides an efficient way of improving satisfaction of visitors of plastic surgery website.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.17 no.5
• /
• pp.553-561
• /
• 2015

In this study, the performance assessment criterion for reasonable maintenance of shield TBM tunnel was presented. The performance assessment items such as crack, leakage, breakage, spalling, exfoliation/detachment, efflorescence, quality condition, exposure of steel, carbonation, faulting step, bolts condition, drainage condition, ground condition, contact section condition and conduit condition were selected by analyzing domestic and foreign performance assessment criterions and investigating segment lining deterioration cases through the site investigation and in-depth inspection analysis result on the shield TBM tunnel. In addition, the reasonable weight using AHP (Analytic Hierarchy Process) were estimated.

• Korean Journal of Remote Sensing
• /
• v.19 no.4
• /
• pp.329-339
• /
• 2003

In this study, an approach of image fusion in decision level has been proposed for unsupervised image classification using the images acquired from multiple sensors with different characteristics. The proposed method applies separately for each sensor the unsupervised image classification scheme based on spatial region growing segmentation, which makes use of hierarchical clustering, and computes iteratively the maximum likelihood estimates of fuzzy class vectors for the segmented regions by EM(expected maximization) algorithm. The fuzzy class vector is considered as an indicator vector whose elements represent the probabilities that the region belongs to the classes existed. Then, it combines the classification results of each sensor using the fuzzy class vectors. This approach does not require such a high precision in spatial coregistration between the images of different sensors as the image fusion scheme of pixel level does. In this study, the proposed method has been applied to multispectral SPOT and AIRSAR data observed over north-eastern area of Jeollabuk-do, and the experimental results show that it provides more correct information for the classification than the scheme using an augmented vector technique, which is the most conventional approach of image fusion in pixel level.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.11B
• /
• pp.1030-1037
• /
• 2008

This paper presents an algorithm for the path-finding problem in unknown environments with cooperative and commutative multi-robots. To verify the algorithm, we investigate the problem of escaping through the exit of a randomly generated maze by muti-robots. For the purpose, we adopt the so called frontier cells and cell utility functions, which were used in the exploration problem for the multi-robots. For the wireless communications among the mobile robots, we modify and utilize the so called the random basket routing, a kind of hop-by-hop opportunistic routing. A mobile robot, once it finds the exit, will choose its next action, either escape immediately or stay-and-relay the exit information for the others, where the robot takes one action based on a given probability. We investigate the optimal probability that minimizes the average escaping time (out of the maze to the exit) of a mobile robot.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.353-366
• /
• 2015

The purpose of this study was to examine how region-specific characteristics affect the occurrence of cardiac arrest. To analyze, we combined a unique data set including key indicators of health condition and cardiac arrest occurrence at the 244 small administrative districts. Our data came from two main sources in Korea Center For Disease Control and Prevention (KCDC): 2010 Out-of-Hospital Cardiac Arrest Surveillance and Community Health Survey. We analyzed data by using multiple regression, geographically weighted regression and decision tree. Decision tree model is selected as the final model to explain regional variations of cardiac arrest. Factors of regional variations of cardiac arrest occurrence are population density, diagnosis rates of hypertension, stress level, participating screening level, high drinking rate, and smoking rate. Taken as a whole, accounting for geographical variations of health conditions, health behaviors and other socioeconomic factors are important when regionally customized health policy is implemented to decrease the cardiac arrest occurrence.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.64-67
• /
• 2002

인터넷 기반의 전자상거래에 참여하는 판매자와 구매자는 가격, 마진 등 다양한 거래조건들을 가지고 협상 (negotiation)을 진행하는 경우가 많다. 그러나, 기존연구에서는 대부분 가격과 거래량과 같은 두 개 미만의 정량적 (quantitative)인 거래조건을 중심으로 협상을 진행하는 방안을 중점적으로 다루었다. 그 결과, 단순한 실험적 문제에 대해서만 협상지원이 가능했고, 실세계의 전자상거래 협상과정에서 발생할 수 있는 다중 협상 요인들간의 동적인 변화를 고려하지 못했다는 지적을 피하기 어렵다. 본 연구에서는 이러한 점에 주목하여 전자상거래 판매자와 구매자가 웹 상에서 다차원적인 거래조건을 가지고 실시간으로 시뮬레이션을 하면서 보다 동적으로 협상을 수행할 수 있도록 퍼지 멤버심 함수와 AHP 추론기법을 이용한 전자상거래 협상지원 (Fuzzy AHP Negotiation support. FAHP-NEGO) 메커니즘을 제안하고자 한다. 실험결과, 협상에 필요한 정량적인 값과 판매자와 구매자의 주관적인 의사결정 행동양식이 반영된 보다 동적인 협상을 진행할 수 있었다. 따라서, 본 연구결과는 향후, 전자상거래 협상에 있어서 보다 현실적인 협상을 지원할 수 있을 것으로 기대한다.

• Journal of the Korea Institute of Building Construction
• /
• v.16 no.4
• /
• pp.331-339
• /
• 2016

According to high-rise, complexation, and enlargement of buildings, various construction methods are being developed, and the significance of construction method selection about main work types has emerged as a major interest. However, it has been pointed out that hand-on workers cannot consider project characteristics carefully, and they lack an objective standard or reference for main construction method selection. Hence, the selection is being made depending on hand-on workers' experience and intuition. To solve this problem, various studies have proceeded for construction method selection of main work types using Artificial Intelligence like Fuzzy, AHP and Case-based reasoning. It is difficult to apply many different kinds of construction method selection to every main work type with consideration for characteristics of work types and condition of a construction site when selecting construction method in the field. Accordingly, this study proposed the decision-making model which can apply to fields easily. Using matrix analysis and liner transformation, this study verified consistency of study models applied in the process of soil retaining selection with a case study.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.37 no.10
• /
• pp.1-8
• /
• 2000

In this paper, positioning schemes based on AOA(Angle of Arrival), TOA(Time of Arrival), and TDOA(Time Difference of Arrival) measurements are reviewed and analyzed. In the case of using those schemes in microcell structure with severe multipath fading and shadowing conditions, the rapid and unpredictable variation of signal level makes it difficult to estimate the position and velocity of mobiles. Therefore, we propose a novel mobile tracking method based on the multicriteria decision making, in which uncertain parameters such as RSS(Received Signal Strength), the distance between mobile and base station, the moving direction, and the previous location are participated in the decision process using aggregation function in fuzzy set theory. Through a simulation, we analysis the impaction of the frequent change of direction and speed of mobiles.