http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
표적 마케팅을 위한 사례기반추론 시스템의 유사 임계치 및 커버리지의 동시 최적화 모형
안현철(Hyunchul Ahn) 성신여자대학교 경영연구소 2008 경영관리연구 Vol.1 No.1
사례기반추론(CBR)은 적용이 쉽고 간편하여, 지금까지 다양한 경영분야 문제 해결에 응용되어 온 인공지능 기법이다. 그럼에도 불구하고, 효과적인 사례기반추론 시스템을 활용하기 위해서는 적절한 유사도 측정이나 유사사례간 결합 등 여러 설계상의 문제들이 존재한다. 본 연구에서는 이러한 CBR의 여러 설계요소들 중, 결합할 유사사례의 선택과 관련하여 새로운 모형을 제시한다. 본 연구에서는 결합할 유사사례를 선택하는 기준으로 특정 사례수(k-NN)나 유사도의 상대적 비율을 사용하는 기존의 CBR과 달리 0에서 1사이의 값을 갖는 절대적 유사 임계치를 적용하고 있다. 다만, 절대적 유사 임계치를 사용할 때, 그 값이 작아지면 예측결과의 생성이 과도하게 이루어지지 않을 수 있으므로, 커버리지 변수를 제약조건으로 함께 반영함으로서 사용자가원하는 수준의 커버리지는 유지한 상태에서 가장 효과적인 유사 사례를 찾을 수 있도록 설계하였다. 제안모형을 검증하기 위해, 본 연구에서는 이를 실제 인터넷 쇼핑몰의 표적 마케팅 사례에 적용해 보았으며, 이를 통해 제안모형의 적용가능성을 확인하고, 향후 추가연구가 요구되는 개선방향을 고찰해 보았다. Case-based reasoning(CBR) is a problem solving technique that is quite simple to implement in general, but often handles complex and unstructured decision making problems very effectively. Thus, it has been applied to various problem-solving areas including manufacturing, finance and marketing. Nonetheless, it is never easy to design effective CBR systems because they have several factors for design including issues on "combining similar cases". This study proposes a novel CBR model, which explores similar cases in an innovative way. Conventional CBR models determine similar cases according to fixed number of neighbors to combine, or relative similarity ratios. However, our model selects similar cases based on similarity threshold - an absolute value ranging from 0 to 1 - and coverage. To validate the usefulness of our model, we applied it to a case for target marketing of an Internet shopping mall in Korea. As a result, we found that our model might be applied to find appropriate prospects for target marketing in an effective way.
안현철(Hyunchul Ahn) 한국데이타베이스학회 2014 Journal of information technology applications & m Vol.21 No.4
This study proposes a novel context-aware recommender system, which is designed to recommend the items according to the customer’s responses to the previously recommended item. In specific, our proposed system predicts the user’s emotional state from his or her responses (such as facial expressions and movements) to the previous recommended item, and then it recommends the items that are similar to the previous one when his or her emotional state is estimated as positive. If the customer’s emotional state on the previously recommended item is regarded as negative, the system recommends the items that have characteristics opposite to the previous item. Our proposed system consists of two sub modules-(1) emotion prediction module, and (2) responsive recommendation module. Emotion prediction module contains the emotion prediction model that predicts a customer’s arousal level-a physiological and psychological state of being awake or reactive to stimuli-using the customer’s reaction data including facial expressions and body movements, which can be measured using Microsoft’s Kinect Sensor. Responsive recommendation module generates a recommendation list by using the results from the first module-emotion prediction module. If a customer shows a high level of arousal on the previously recommended item, the module recommends the items that are most similar to the previous item. Otherwise, it recommends the items that are most dissimilar to the previous one. In order to validate the performance and usefulness of the proposed recommender system, we conducted empirical validation. In total, 30 undergraduate students participated in the experiment. We used 100 trailers of Korean movies that had been released from 2009 to 2012 as the items for recommendation. For the experiment, we manually constructed Korean movie trailer DB which contains the fields such as release date, genre, director, writer, and actors. In order to check if the recommendation using customers’ responses outperforms the recommendation using their demographic information, we compared them. The performance of the recommendation was measured using two metrics-satisfaction and arousal levels. Experimental results showed that the recommendation using customers’ responses (i.e. our proposed system) outperformed the recommendation using their demographic information with statistical significance.
인버터 기반 신재생 에너지 발전 시스템의 계통 지원 운전을 위한 계통 전압 검출 방법
안현철(Ahn, Hyun-Chul),송승호(Song, Seung-Ho) 한국신재생에너지학회 2013 신재생에너지 Vol.9 No.2
The Grid code is being strengthen as increase of renewable energy ratio. Especially, the grid connection regulations are continuously being updated for stable operation of power grids. Static grid support and Dynamic grid support must make an accurate measure at Grid connected point because they needs control algorithm individually. It has to exactly measure voltage including switching ripple at the output of the inverter generating system. In addition, it is necessary to have an accurate voltage measurement when the situation rapidly changing the grid impedance is caused by the input of serial impedance of transformer and line impedance as well as Grid Fault Device. In this paper, We propose a new detection method of grid voltage to calculate accurately the r.m.s voltage of the grid connection point along the standard required by the low voltage regulation. We verified performance through simulation grid fault device.
안현철(Hyun chul Ahn),이형용(Hyoung Yong Lee) 한국IT서비스학회 2015 한국IT서비스학회지 Vol.14 No.1
Currently, Social Commerces have increasingly gained popularity with the growth of Social Network Services (SNS). As the applications of smartphones are being applied in widespread areas, social commerces in the smartphone environment have entered a new chapter. The applications of social commerces on smartphones are widely used, which has increased the market share of social commerces exponentially. Thus, we tried to find out factors which may affect the user acceptance of social commerces in the smartphone environment. We develop a research model to examine how social commerces in the smartphone environment are accepted by users based on the academic factors-switch costs, trend-seeking tendency, richness in media. The theoretical model is validated through an survey of social commerce users in the smartphone environment from the undergraduates and the graduates in Seoul, Korea. The structural equation analysis is conducted based on the partial least square (PLS) approach. The results reveal that the switch cost will have positive mediating influences to the intention to use social commerce in the smartphone environment. We also find that the perceived usefulness of the smartphone is affected by the media richness. The results also suggest that the trend-seeking tendency has no influences to the users of social commerces in the smartphone environment. Also, theoretical and practical implications are discussed. The findings are believed to increase our understanding an interesting mobile phenomenon, as well as making contributions.
KIVA 코드를 이용한 HCNG 엔진의 연소 특성 및 NOx 분석
안현철(Hyun C. Ahn),유희식(Hee S. Yoo),이재서(Jae S. Lee),허강열(Kang Y. Huh) 한국자동차공학회 2010 한국자동차공학회 학술대회 및 전시회 Vol.2010 No.11
This study was to analyze the performance and emissions of an HCNG(Hydrogen Compressed Natural Gas) engine by the simulation tool, KIVA-3V. The engine performance was evaluated by efficiency and NOx with the expected advantage of a wider range of the flammability limit with hydrogen addition. The input parameters under investigation were the ratio of hydrogen to natural gas and the global air/fuel ratio. The mesh for the combustion chamber was generated by the KIVA-3V preprocessor and the laminar flame speed was calculated by CHEMKIN according to the fuel composition and the equivalence ratio. Validity of the results was checked against experimental results from KIMM(Korea Institute of Machinery & Materials) to identify the performance enhancement of the HCNG engine.