• 한국의류학회지
• /
• 제25권6호
• /
• pp.1179-1190
• /
• 2001

The purpose of this study was to segment adolescents according to shopping orientation and to clarify the different clothing behaviors among the segmented groups. The results may be useful for the marketer whose target is adolescents to make proper marketing strategies. The subjects for the final analysis were 436 adolescents who were living in Seoul and Pusan. The statistics used for analysis included factor analysis, cluster analysis, Cronbach $\alpha$, one-way ANOVA, Dancan multiple range test and chi-square using the SPSS program. The results were as follows. Adolescents were segmented to 4 groups(Shop Loyalty/Convenience Pursuit Group, Pleasure/Brand Loyalty Group, Low Shopping Involvement Group and Economic Group). And the four segmented groups were significantly different in clothing purchasing motives, clothing evaluation standards, shop evaluation standards, information preference and demographic variables such as sex, and monthly spending money.

• 기술혁신학회지
• /
• 제7권3호
• /
• pp.681-709
• /
• 2004

The purpose of this study is to classify customers by e-mail responsiveness on time-series analysis and testify the effectiveness of grouping by ROI analysis. Response recency, response frequency and Activity(RFA) of e-mailing systems are adapted for Customer segmentations. ROI analysis are consisted of open, click-through, duration time, personalization, conversion rate and email loyalty index of email systems. Major findings are as follows: RFA analysis is used for customer segmentations that is fundamental process of e-CRM applications. Customers can be grouped into loyal customers, odds customers, dormant customers, secession customers, and observation customers by RFA grouping. Loyal customer group has high point in all ROI index compared to other groups. These results indicated that customer responsiveness of e-mail systems were appropriate methods to group the customer with demographic variables. Therefore, effective e-mail marketing strategy of e-Biz should have suitable active DB and Behavior targeting is best approach to enforce the target e-mail marketing.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2009년도 춘계 종합학술대회 논문집
• /
• pp.776-783
• /
• 2009

본 논문은 스키니 스머지 툴을 이용한 2D 가상 컬러 헤어스타일러에 관한 것이다. 스머지 툴(smudge tool)은 어도비 포토샵에 내장된 대중적인 그래픽 툴로서 물감을 화폭 상에 문질러서 흐려지게 할 시에 이용된다. 그 효과는 지두화법과 매우 유사하다. 스머지 툴은 스머지 아이콘을 클릭한 다음에 화폭 위를 클릭한 후, 마우스 버튼을 누른 상태에서 번짐 효과를 주고 싶은 방향으로 끌어당김으로써 그 기능을 이용할 수 있다. 그러나 기존의 스머지 툴은 마스터 직경 내의 모든 화소값을 블렌딩시켜 목표 영상을 생성함에 따라 원하지 않는 부위의 화소마저도 변형시키는 단점이 있다. 이러한 단점을 해결하고자 본 논문에서는 마스터 형상 분할에 기반한 스키니 스머지 툴(skinny smudge tool)을 제안하고자 한다. 제안된 스키니 스머지 툴은 컬러 영상 분할에 통해 윤곽 형상에 밀착된 마스터 형상을 추출함에 따라 배경에 관계없이 변형하고 싶은 부분에만 번짐 효과를 적용시킬 수 있는 장점이 있다.

• 한국의류학회지
• /
• 제25권2호
• /
• pp.303-314
• /
• 2001

The purposes of this study were 1) to identify different sub-segments of tourism market in Cheju island based on fashion image of clothing souvenir and 2) to provide manufactures with useful information for developing cultural fashion goods related to Cheju island. The data were collected via a self-administered questionnaire from 192 female tourist(20-59 years old) in Cheju and analyzed by factor analysis, cluster analysis, one-way ANOVA and $\chi$$^2$-test. Six factors of fashion image were found image were found and labeled as: Sexy/feminine, wild/mannish, easy/simple, Cheju, ecology, natural image. Four factors of benefit sought were also identified: Practicality/economic-value, fashionability/preference of design, reputation and souvenir-value. Three groups were identified based on fashion image sought: Image of primitive nature(G1: 37.7%), image of nature in the city(G2: 20.1%), sexy/feminine image(G3: 42.2%). There were significant differences among sub-groups in age, fashion innovation, benefit sought and intention of buying Gal-ot. Younger females(20-30 ages) were included more in group 1 than group 2 while older females(40-50 ages) were included more in group 2. Group 1 had a higher score of fashion innovation comparing group 3. Group 1 had the highest scores on practicality/economic-value and souvenir-value. However, group 2 placed the highest importance on reputation as well as practicality/economic-value and group 3 had the lowest scores on all types of benefit. Group 1 and group 2 had intention of buying Gal-ot more than group 1. Based on the results of this study, manufactures may implement target marketing strategies on group 1 which sought the image of primitive nature and group 2 which sought the image of nature in the city.

• 패션비즈니스
• /
• 제22권5호
• /
• pp.64-82
• /
• 2018

As sustainability of fashion brands is becoming more important in the prolonged depression, the fashion market is also seeking ways to create new value through convergence with various fields. In the fashion market, convergence marketing is engaged with diverse technologies combined with advanced technologies and strategies. This study established the conceptual characteristics of convergence and divergence from a market perspective. Convergence can be summarized as Borderless, Compounding, Diversification, Recombination and Affiliation. The conceptual characteristics of the divergence can be summarized as de-fusion, individualization, differentiation, specialization, and segmentation. The characteristics of convergence revealed through the case of fashion market include the expandability of the new category, the expandability of the consumer, the brand experience, and the expandability of time and space. Divergence is the differentiation of brand value, target customer, and product nature. Through this study, we could understand the differentiation of the fashion market and the direction of the marketing strategy by looking at the characteristic of the convergence marketing - oriented research that has the contrary conceptual characteristics from the extended viewpoint. Based on this, it is possible to see the changes and patterns of brand marketing strategies and techniques in recent fashion market. In the future, it is expected that the systematic study of the marketing strategy of the domestic fashion brand based on the convergence and change characteristics of the fashion market proposed in this study will continue.

• 한국산업정보학회논문지
• /
• 제24권4호
• /
• pp.1-8
• /
• 2019

식물 표현체(plant phenomics) 연구는 우수한 형질의 식물 품종과 유전적 특성을 선별하기 위해 여러 식물체의 형태적 특징을 관측하고, 획득한 영상 빅데이터를 분석하는 기술이다. 기존의 방법은 검출 대상에 따라 직접 색상 임계값을 변경해야 하기 때문에 빅데이터를 다루는 정밀검정시스템에 적용하기 어렵다. 본 논문에서는 정밀검정시스템을 위한 식물체와 배경의 자동 분할이 가능한 합성곱 신경망(Convolution neural network: CNN) 구조를 제안한다. LeafNet은 9개의 컨벌루션 계층과 식물의 유무를 판단하기 위한 시그모이드(Sigmoid) 활성화 함수로 구성된다. LeafNet을 이용한 학습 결과, 식물 모종 영상에 대하여 정밀도 98.0%, 재현율 90.3%의 결과가 도출되어 정밀검정시스템의 적용 가능성을 확인하였다.

• 한국의학물리학회지:의학물리
• /
• 제31권3호
• /
• pp.111-123
• /
• 2020

Deep learning (DL) is a subset of machine learning and artificial intelligence that has a deep neural network with a structure similar to the human neural system and has been trained using big data. DL narrows the gap between data acquisition and meaningful interpretation without explicit programming. It has so far outperformed most classification and regression methods and can automatically learn data representations for specific tasks. The application areas of DL in radiation oncology include classification, semantic segmentation, object detection, image translation and generation, and image captioning. This article tries to understand what is the potential role of DL and what can be more achieved by utilizing it in radiation oncology. With the advances in DL, various studies contributing to the development of radiation oncology were investigated comprehensively. In this article, the radiation treatment process was divided into six consecutive stages as follows: patient assessment, simulation, target and organs-at-risk segmentation, treatment planning, quality assurance, and beam delivery in terms of workflow. Studies using DL were classified and organized according to each radiation treatment process. State-of-the-art studies were identified, and the clinical utilities of those researches were examined. The DL model could provide faster and more accurate solutions to problems faced by oncologists. While the effect of a data-driven approach on improving the quality of care for cancer patients is evidently clear, implementing these methods will require cultural changes at both the professional and institutional levels. We believe this paper will serve as a guide for both clinicians and medical physicists on issues that need to be addressed in time.

• 복식문화연구
• /
• 제29권6호
• /
• pp.795-809
• /
• 2021

The purpose of this study was first, to clarify the clothing benefits that Uzbek female college students seek through clothing products; and second, to determine whether there is a difference in clothing involvement and clothing purchasing behavior according to the type of clothing benefits. Data were collected from 290 female university students from Tashkent, Uzbekistan, and analyzed using factor analysis, K-means group classification analysis, ANOVA, Duncan test, χ²-test, and frequency analysis. Respondents were classified into four types according to their clothing benefits: individuality/economy-pursuit, comfort-pursuit, fashion/brand-pursuit, and indifference. Significant differences were identified in terms of clothing involvement, information sources, clothing evaluation criteria, clothing store attributes, clothing wearing conditions (including monthly clothing expenses), number of purchases per year, clothing purchase location, clothing preference style, and clothing dissatisfaction. The fashion/brand-pursuit and personality/economy-pursuit types were influenced more by fashion and symbolism of clothing involvement, information sources, clothing evaluation criteria, and clothing store attributes. The individuality/economy-pursuit type purchased more frequently, spent more monthly clothing expenses, and used the internet. Clothing store attributes were considered more important by female students than the other attributes. In these results, clothing benefits were identified as consumer characteristics of female Uzbek college students and market segmentation was determined. In addition, it is meaningful in providing basic data for efficient marketing activities and minimizing trials and errors in establishing local-friendly strategies for target customers in different cultures.

• 지능정보연구
• /
• 제17권4호
• /
• pp.95-108
• /
• 2011

인터넷 비즈니스의 활성화에 따라서 기업은 고객의 인물정보 및 거래정보를 활용하여 보다 맞춤화된 개인화 서비스를 제공하고 있다. 기존의 고객군별 예측기법은 유사한 고객들을 군집화하여 고객군별로 예측모델을 수립하는 것으로, 구매가 많고 충성도가 높은 핵심고객에게 요구되는 일대일 서비스를 제공하는 데는 한계가 있다. 반면 일대일 고객별 예측기법은 각 고객에게 고도로 맞춤화된 서비스를 제공하지만, 과거 구매이력이 많지 않은 고객 이나 신규 고객에게는 정확한 개인화 서비스를 제공하지 못한다. 본 연구는 고객의 구매빈도에 따라서 유사 고객들과의 군집화 수준을 동적으로 조정하는 새로운 지능형 개인화 시스템을 제안한다. 제안된 시스템은 과거 구매가 많은 고객들에 대해서는 일대일 예측모델을 수립하지만, 구매 빈도가 낮은 고객의 경우 다른 고객들과의 최적화된 군집화를 통해 예측모델을 수립한다. 본 기법을 Neilsen의 음료수 구매 데이터셋에 적용하여 고객의 일회 구매금액 및 구매품목을 예측한 결과, 기존 두 예측기법들에 비하여 적정한 계산비용(computational cost)으로 더욱 정확한 개안화 서비스를 제공할 수 있음을 확인하였다.

• 마케팅과학연구
• /
• 제16권1호
• /
• pp.73-91
• /
• 2006

본 연구는 국내 관광유람선의 신규출항에 따른 시장세분화를 중심으로 연구하고자 진행되었다. 연구 결과 시장세분화의 절차면에서는 먼저 Chung 등(2004)의 혜택에 의한 세분화를 시도하였으며, 관광유람선의 서비스속성을 모두 도출하여 속성을 정제한 후 요인분석을 시도하였다. 요인분석결과 5개의 유의미한 요인은 시설 및 서비스, 유람선분위기, 일탈성, 선택성, 안전성 등이었다. 한편 군집분석결과 중립형, 관광유람선선호형, 무관심형의 집단으로 분류되었는데 평균값이 가장 높았던 관광유람선선호형 집단은 안전성, 시설 및 서비스, 유람선분위기, 선택성, 일탈성의 순으로 중요하게 여기고 있었다. 연구결과에 따른 시사점으로 표적시장전략은 1차 표적시장으로 각 요인의 점수가 가장 높았던 관광유람선선호형 잡단을 선정하는 것이 타당할 것이며, 2차 표적시장으로 중립형의 집단이 고려되어야 할 것이다. 경쟁대상으로는 부산지역(특히 해운대지역)유명레스토랑, 놀이공원, 영화관이 될 것이며, 주요 혜택으로서는 경쟁대상지역과는 차별화된 안전성을 고려한 시설 및 서비스가 강조되어야 할 것이다. 특히 유형적 단서로의 조작에서 청결한 이미지를 위해서는 선상의 색상을 그린색상과 흰색계열로 하여 청결한 이미지를 세워 나가야 할 것이다. 또한 여름철의 계절성을 만끽하고 있는 모델이 담긴 브로셔의 제작, 환상적인 이벤트를 연출하고 있는 선상의 모습 등이 담긴 브로셔의 개발이 필요할 것이다. 획일성의 유지로서 시설 및 서비스, 유람선의 분위기, 일탈성의 요인들이 반영된 연출믹스, 제품믹스, 가격믹스, 촉진믹스, 분배믹스등의 전략이 구사되어야 할 것이다. 마지막으로 본 연구의 한계점은 부산지역에 국한되었으며, 관련 속성의 연구가 부족하였고, 기존고객과 신규고객의 차이분석이 시도되지 못하였다는 점이다. 따라서 향후 연구에서는 관련 속성의 보다 심도있는 정제작업과 기존고객, 신규고객, 충성도의 변수(집중도, 애정도, 재방문의도)등을 고려하여 연구에 임해야 할 것으로 본다.