• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.145-154
• /
• 1999

An intelligent system embedded with multiple sources of knowledge may provide more robust intelligence with highly ill structured problems than the system with a single source of knowledge. This paper proposes th hybrid knowledge integration mechanism that yields the cooperated knowledge by integrating expert, user, and machine knowledge within the fuzzy logic-driven framework, and then refines it with a genetic algorithm (GA) to enhance the reasoning performance. The proposed knowledge integration mechanism is applied for the prediction of Korea stock price index (KOSPI). Empirical results show that the proposed mechanism can make an intelligent system with the more adaptable and robust intelligence.

• Journal of the Korean Society of Tobacco Science
• /
• v.22 no.2
• /
• pp.133-137
• /
• 2000

The bulk curing experiment to improve the quality of flue-cured leaves were carried out to evaluate relationship between the modified(3 step-up) drying and conventional drying method in bulk curing process. Modified drying method was somewhat higher values in yellowing color index of cured leaves, and less brittle than those in conventional drying program. As to the chemical properties, there was no difference in chemical component levels in cured leaves between the modified and the conventional methods, while the major chemical compounds in relation to aromatic essential oil of cured leaves showed mostly higher level in the modified method than that in conventional drying method. Additionally 3 step-up drying method increased the tobacco quality by 2 % in price per kg compared with conventional drying method.

• The Korean Journal of Financial Management
• /
• v.19 no.2
• /
• pp.211-231
• /
• 2002

본 연구의 목적은 VECM(Vector Error Correction Model)과 인공지능모형(Artificial Neural Networks)을 이용하여 우리나라 증권시장과 거시경제 변수들과의 장기적 관계에 대한 설명력을 비교해보고자 함에 있다. VECM이 APT(Arbitrage Pricing Theory)에 기초를 둔 선형동학모형이라고 한다면, 인공지능모형은 비모수적 비선형모형이라는 점에서, 두 방법론의 분석결과를 직접 비판하는 것은 의미있는 연구라고 할 수 있다. 인공지능모형을 주로 활용하는 선행연구들에 의하면, 증권시장은 시장의 특이패턴들로 인해 계량경제학적 접근인 선형 모형보다는 인공지능모형을 통해 증권시장의 움직임을 설명하고 예측하는 것이 더 바람직할 수도 있다는 것이다. 따라서, 본 연구에서는 VECM분석에서 자료의 안정성을 검증하고, 공적분 백터를 발견한 이후, 장기적 균형관계의 실증적 분석을 하였다. 그리고, 인공지능모형에서는 delta rule과 Sigmoid 함수를 이용한 GRNN(General Regression Neural Net)과 Back-Propagation등의 방법들을 활용하였다. 이러한 분석결과, Back-Propagation 모형이 다른 모든 모형들보다도 더 우수한 설명력을 보여주고 있었다. 이러한 결과들은 인공지능모형이 동태적인 선형 모형보다도 더 우수한 설명력을 제공할 수 있는 가능성을 보여주고 있었다.

• The Korean Journal of Community Living Science
• /
• v.19 no.4
• /
• pp.697-706
• /
• 2008

Generally, tourism environments are classified as macro or micro environments. Hotel revenues are influenced directly and indirectly by macro and micro environments. This study aims to examine the determinants of the change in macro-environments on hotel revenue. The explanatory variables in this research were wage, exchange rates (ER), consumer price index (CPI) and seasonality. The results of this study were as follows; The CPI and ER significantly affected the hotel food and beverage sales. The seasonality (summer and autumn) and wage significantly affected the hotel room sales. Wage and seasonality (summer and autumn) also significantly affected the total sale on the hotels.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.461-466
• /
• 2012

Customers want to have more convenient and comfortable vehicle. Motor-on-caliper EPB(Electrical Parking Brake) System is one of the new systems for customer's convenience. It is applied for Midsize vehicle for reducing weight/price compared to cable puller type EPB. In this paper we studied sound quality improvement of motor-on-caliper EPB system. We developed the sound quality index and suggested the interior sound quality target value. To meet the target value cascading target was also suggested. EPB motor vibration level & sound radiation level, vibro-acoustic transfer function level from EPB to interior was defined. To find out effective way of sound quality improvement and find cascading target, TPA(Transfer Path Analysis) was carried out.

• The Korean Journal of Applied Statistics
• /
• v.17 no.2
• /
• pp.219-228
• /
• 2004

In this paper we construct prediction intervals for nonlinear time series models using the bootstrap. We compare these prediction intervals to traditional asymptotic prediction intervals using quasi-score estimation function and M-quasi-score estimating function comprising bounded functions. Simulation results show that the bootstrap method leads to improved accuracy. The accuracy of the bootstrap is empirically demonstrated with the consumer price index.

• Journal of the Korean Society of Costume
• /
• v.52 no.3
• /
• pp.123-137
• /
• 2002

The purpose of this study is to analyze the actual condition and problems of current ready-made shrouds. Current shrouds were formed after the 20th century and therefore are quite apart from its traditional precedents of Chosun Dynasty. In this respect, several problems can be pointed out. 1. The use of natural colored hemp as a primary textile of current shrouds is far from our tradition. Silk, ramie, and cotton have to be used together with hemp. Also, more variety of colors can be used other than natural white. 2. The size of ready-made shrouds has to be categorized at least into three: large, medium and small 3. The pattern and sowing method of Dopo(도포) and Wonsam(원삼) should be corrected in line with those of the traditional Dopo(도포) and Wonsam(원삼). 4. The design and items of current ready-made shrouds have to break away from the standardized convention and should seek more of a variety that our rich tradition provide. 5. The rational index should be suggested so that consumers can compared the quality and price of ready-made shrouds available at their hands.

• Korean journal of food and cookery science
• /
• v.17 no.4
• /
• pp.380-390
• /
• 2001

Utilization practice of garlic and seasonings in industry foodservice was surveyed by questionnaire. Statistical data analysis was performed with SAS package program in order to have frequencies, means, t-test, ANOVA and Duncan's multiple range test. The results of this study can be summarized as follows; The mean value of Food Processing Index(FPI) score for purchased vegetable and seasonings is 3.5 which indicates the prepreparation is between partially preprepared and completely preprepared. The garlic was mainly purchased from brokers(51.0%), on a daily basis(58.8%) and peeled-form(74.5%). The average purchased amount is 6.66㎏ at a time. The unit price of the garlic makes significant differences(p＜0.05) by the scale and location of foodservice establishments. As for the storage method and Period, in room temperature, no storage(2.1%) and for one day(2.1%) and in refrigeration, for one day(39.6%) and fer three days(18.7%).

• Korean System Dynamics Review
• /
• v.4 no.1
• /
• pp.5-31
• /
• 2003

Customer satisfaction is generally assumed to be a significant determinant of repeat sales, positive word-of-mouth, and customer loyalty. Therefore most companies in telecommunication industry have tried to satisfy customers with high quality at low price in Korea. Even though these efforts have been tried by companies, customers are not satisfied with discrepancy between their expectation and perceived quality. Moreover, the expectation has dynamic and variable characteristics in results from various effects such n technical progress, improved quality and promotions by companies, word-of-mouth, and so on, Therefore, there are not political leverages in assessing the quality and surveying customer satisfaction index in a point of time. As an initial attempt to tackle the questions listed above, this paper puts an effort to make a dynamic customer satisfaction model to understand customer satisfaction in variable situations by introducing 'systems thinking'.

• East Asian Journal of Business Economics (EAJBE)
• /
• v.2 no.2
• /
• pp.58-67
• /
• 2014

If we compare the GDP per Capita for the last 20 years between Philippines and other ASEAN countries, Philippines remains in the lowest on GDP per Capita. This paper is trying to find out the possible reasons for the low growth rate of the GDP per Capita in the Philippines. 53 years data from the World Bank are used explore the relationships between the GDP per Capita and eight economic indicators to run three time series models and one to one regression. Three indicators, namely, consumer price index, gross capital formation as a percentage of GDP and population are remarked with possible contribution to the low growth rate of the GDP per capita of the Philippines.