• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1994년도 추계학술대회 논문집
• /
• pp.658-663
• /
• 1994

The classification and coding of part for group technology applications continus to be labour intensive and time-consuming process, and therefore much effort is dedicated to the structure and creation of automatic coding systems. IN this paper, Neural networks is used to generate processes-related digit as well as part geometry-related digit of the TS code where part name is provided as input.since part name, which is appropriately designated, provides much information about part geometry and manufacturing processes. THe developed GT recommendation system is integrated with interactive TS coding system and database in order to handle the changes of production environment, such as the change of production part of plant. It is found to recommend codes accurately and promises to be a useful tool for consistent, reliable and convenient coding processes.

• Journal of Information Science Theory and Practice
• /
• 제12권2호
• /
• pp.64-78
• /
• 2024

Sentiment analysis is one of the promising approaches for developing a point of interest (POI) recommendation system. It uses natural language processing techniques that deploy expert insights from user-generated content such as reviews and feedback. By applying sentiment polarities (positive, negative, or neutral) associated with each POI, the recommendation system can suggest the most suitable POIs for specific users. The proposed study combines two models for POI recommendation. The first model uses bidirectional long short-term memory (BiLSTM) to predict sentiments and is trained on an election dataset. It is observed that the proposed model outperforms existing models in terms of accuracy (99.52%), precision (99.53%), recall (99.51%), and F1-score (99.52%). Then, this model is used on the Foursquare dataset to predict the class labels. Following this, user and POI embeddings are generated. The next model recommends the top POIs and corresponding coordinates to the user using the LSTM model. Filtered user interest and locations are used to recommend POIs from the Foursquare dataset. The results of our proposed model for the POI recommendation system using sentiment analysis are compared to several state-of-the-art approaches and are found quite affirmative regarding recall (48.5%) and precision (85%). The proposed system can be used for trip advice, group recommendations, and interesting place recommendations to specific users.

• 한국임상약학회지
• /
• 제27권2호
• /
• pp.113-118
• /
• 2017

Objective: International institutes such as Global institute for Asthma(GINA), KAAACI(Republic of Korea), NHLBI(USA), BTS(UK) and JSA(Japan) have published guidelines for asthma treatment. The aim of this study was to compare the representatives' international guidelines of pharmacotherapy for pediatric asthma. Methods: The recommendations related to pharmacotherapy for pediatric asthma were extracted from the latest representatives' international guidelines, and comprehensive comparisons were conducted. Results: Major comparison outcomes between international guidelines were evaluated as follows: classification system on severity and pediatric age group, recommendation for inhaled corticosteroid dose, recommendation for pediatric age group of theophylline in mild asthma, and recommendation for pediatric age group of tiotropium in severe asthma. Clinical trials emphasized the adverse effects of theophylline, whereas tiotropium demonstrated beneficial actions for pediatric asthma. Therefore, theophylline was recommended for older patients with persistent asthma, and tiotropium was considered to be suitable for younger patients with severe asthma according to GINA guidelines. Conclusion: These findings address the requirement to harmonize international guidelines of pharmacotherapy in pediatric asthma. In addition, the findings suggest that KAAACI needs to update its pharmacotherapy guidelines of theophylline, tiotropium and other medicines recently approved.

• 동아시아식생활학회지
• /
• 제8권1호
• /
• pp.1-8
• /
• 1998

This study was designed to investigate the optimum recommendation level on Gatrodia rhizoma and the effects on the improvement of the lipids in the dietary hypercholesterterolemic rats. Experimental diets mixed with 5% Dioscorea batatas(Group 2), 10% Dioscorea batatas(Group 3), 15% Dioscorea batatas (Group 4) 5% Gastrodia rhizoma (Group 5), 10% Gastrodia rhizoma (Group 6), and 15% Gastrodia rhizoma (Group 7), were administered to the male rats of the Sprague Dawley for 3 weeks. Concentration of total cholesterol in serum was lower in the Gastrodia rhizoma groups than in the other groups, especially total cholesterol concentration of 10% Gastrodia rhizoma(Group 6) was the lowest in the Gastrodia rhizoma groups. Concentration of HDL-cholesterol in serum was higher in the 10% Gastrodia rhizoma and 15% Gastrodia rhizoma than in the other groups. Concentrations of cholesteryl ester, LDL, LDL-cholesterol in serum were the lowest in the 10% Gastrodia rhizoma. Concentration of glucose and activity of GPT in serum were the lowest in the 10% Gastrodia rhizoma group. The activity of GOT in serum was lower in the 10% Gastrodia rhizoma group and 15% Gastrodia rhizoma group than in the other groups. Therefore, we consider that there are effects on the improvement of the lipids in the Gastrodia rhizoma and the optimum recommendation quantity of Gastrodia rhizoma is 10% to quantity of food composition.

• 한국의류학회지
• /
• 제40권6호
• /
• pp.1010-1024
• /
• 2016

This study identifies the influence of on/off-line acquaintances' recommendation messages on fashion product attitude and purchase intention on the online purchase of fashion products in two-sided word of mouth situations as well as compares the difference in influence according to bond-base with equidistance. This study was conducted for one month on university students in their 20s who were believed to be active in smartphone use. Out of the collected 174 copies of the questionnaire, 162 copies were used for analysis. The questionnaire was classified into online and offline recommendation messages of an acquaintance. We present two-sided fashion product reviews made similar to the type found in an actual shopping mall web-site. As for analysis, confirmatory factory analysis, structural equation modeling, and multi-group analysis were conducted using AMOS 19.0. The analysis results are as follows. First, on/off-line acquaintances' recommendation messages had significant influences on product attitude in the situation where two-sided reviews on fashion products were presented; however, those messages did not influence purchase intention. Recommendation messages positively increased product attitude and enhanced purchase intention if acquaintances' recommendation messages were mediated between on/off-line acquaintances' recommendation messages and purchase intention. Consequently, a mediating effect on product attitude was revealed. Second, there was no difference between online acquaintances and offline acquaintances in terms of the influence of acquaintances' recommendation messages on product attitude and purchase intention, in the situation where two-sided reviews were presented on online fashion products. Therefore, no control effect according to the type of acquaintance was confirmed.

• 지능정보연구
• /
• 제7권2호
• /
• pp.153-177
• /
• 2001

데이터베이스 마케팅을 필두로 최근 마케팅 분야에서는 보다 고객에 적합한 제품이나 서비스를 제공하고 또한 이로 인해 그 마케팅 비용을 최소화하고 또한 그 매출효과를 극대화하고자 하는 움직임이 가속화되고 있으며, 극단적으로는 일대일 마케팅이라고까지 표현하고 있다. 더욱이 전자쇼핑몰에 있어서는 실제 판매원이 존재하지 않는 이상 보다 더 고객의 관심을 유도하고 궁극적으로 매출을 발생시키기가 더욱 어려운 실정이며 따라서 고객을 파악하기 또한 그 고객에 적합한 제품이나 서비스에 대한 정보를 즉각적 또는 사전적으로 추측 제시하여야 하는 역량이 매우 중요하다 하겠다. 그러나 이와 같은 즉시성의 추정이나 판단의 유효성을 제고하기 위해서는 전자쇼핑몰 입장에서 일단의 단편적 정보에 의존하는 방식보다는 이용가능한 모든 정보에 대한 통합적 고찰과 또한 고객에 대한 제안 여부와 추천 의사 결정을 개별적이고 순차적인 절차로 보는 관점보다는 하나의 통일된 관점에서 최대의 효과를 발생시킬 수 있도록 하는 상품 추천 방법론이 필요하다 하겠다. 본 연구는 이를 위해 전자쇼핑몰에서의 오프라인/온라인의 통합 정보를 바탕으로 추천 대상 고객 선정 및 추천 효과의 최적화를 목적으로 추천 상품 및 서비스 결정의 의사결정들에 대한 단일 의사결정 방법론 즉 상품 추천 방법론을 제안하며 이를 에이전트 기법을 바탕으로 설계하였다. 또한 이상의 방법론과 설계기법을 국내 유수의 전자쇼핑몰에 적용하여 그 실험적 성과를 제시하고 있다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.2-5
• /
• 2022

딥러닝의 등장과 ICT(Information and Communication Technology)의 급속한 발전으로 정치, 경제, 문화 등 사회의 다양한 분야에서 인공지능을 활용한 연구가 활발히 진행되고 있다. 딥러닝 기반 인공지능 기술은 자연어 처리, 영상 처리, 음성 처리, 추천 시스템 등 다양한 영역으로 세분화된다. 특히, 산업이 고도화됨에 따라 시장 동향 및 개인의 특성을 분석하여 소비자에게 추천하는 추천 시스템의 필요성이 점점 더 요구되고 있다. 이러한 기술 발전에 발맞추어, 본 논문에서는 딥러닝 기반 '언어처리지능' 과 '영상처리지능'의 기술개발을 통해 정형 또는 비정형 텍스트 및 이미지 빅데이터로부터 속성 정보를 추출 추출하고, 분류하여 패션시장의 트랜드나 신규소재 등을 분석하고 소비자의 취향 분석을 통하여 '시장-소비자' 인사이트를 발굴하여, 스타일 추천, 가상 피팅, 및 디자인지원 등이 가능한 인공지능 기반 '맞춤형 패션 어드바이저' 서비스 통합 시스템을 제안한다.

• 한국콘텐츠학회논문지
• /
• 제16권7호
• /
• pp.587-597
• /
• 2016

본 연구는 스키리조트를 바탕으로 체험형태를 스키형과 비스키형으로 구분하고, 자기 자신에 대한 신념과 기대감의 반영인 자기효능감을 독립변인으로 적용하고 체험형태와의 조절효과 규명과 두 변인들 사이의 상호작용효과를 고찰하고자 하였다. 또한 체험을 통해 형성된 주관적 안녕감이 서비스에 대한 고객만족의 표현인 추천의도에 미치는 영향을 규명하고자 하였다. 연구결과, 자기효능감은 주관적 안녕감(여가의 만족, 긍정적 정서)에 긍정적인 영향을 미치는 것으로 나타났다. 스키형 체험의 경우 자기효능감이 높은 사람들은 상대적으로 자기효능감이 낮은 사람들보다 주관적 안녕감(여가의 만족, 긍정적 정서)을 높게 느끼는 것으로 나타났다. 반면, 비스키형 체험의 경우 자기효능감이 낮은 사람들이 상대적으로 자기효능감이 높은 사람들보다 주관적 안녕감(여가의 만족, 긍정적 정서)을 높게 느끼는 것으로 나타났다. 이러한 주관적 안녕감(여가의 만족, 긍정적 정서)은 자기효능감과 추천의도 사이에 매개역할로 작용하였다.

• 한국컴퓨터정보학회논문지
• /
• 제15권2호
• /
• pp.135-146
• /
• 2010

본 논문에서는 이러닝 마켓플레이스에서 자기주도학습지원을 위한 추천시스템을 제안한다. 이 시스템은 마켓플레이스를 지원하기위한 개선된 협업필터링을 이용한 추천시스템이다. 기존의 협업필터링 기법은 입력데이터구성, 최근접 이웃선정을 통한 유사고객 그룹을 형성하고, 추천목록 생성하는 3단계로 구성되었다. 본 연구는 이를 개선하여 산업 수준을 고려한 최근접 이웃 교육과정 선정 단계를 추가한 협업필터링에 사용하여, 자기주도학습을 지원할 수 있는 추천시스템을 설계하였다. 이 서비스는 산업체 학습자에게 보다 정확한 교육과정을 선택할 수 있도록 도와준다. 추천시스템은 다양한 기법을 통해 구축되며, 협업필터링 방식을 사용하여 명시적인 속성이 부여 되어진 콘텐츠를 추천하는 것은, 기존 콘텐츠 추천의 한계를 해결하고자 하였다.

• 한국의상디자인학회지
• /
• 제24권2호
• /
• pp.59-72
• /
• 2022

The online fashion market in the 21st century has shown rapid growth. Against this backdrop, using consumer activity data to provide customized customer services has emerged as a viable business model that draws attention. Algorithm-based personalized recommendation services are a good example. But their application in fashion products has clear limitations. It is not easy to identify consumers' perceptions of the attributes of fashion, which are various, hard to define, and very sensitive to trends. So there is a need to compile data on consumers' underlying awareness and to carry out defined research to increase the utilization of such services in the fashion industry and further engage consumers. This research aims to classify the attributes and types of fashion products and to identify consumers' perceptions of a given situation where a recommendation service is offered. To find out consumers' perceptions of and satisfaction with recommendation services, an online and mobile survey was conducted on women in their 20s and 30s, a group that uses recommendation services frequently. A total of 455 responses were used for analysis. SPSS 28.0 was used, combined with Conjoint Analysis and multiple regression, to analyze data. The study results could provide insights into a better understanding of recommendation services and be used as basic data for companies to identify consumers' preferences and draw up a detailed strategy for market segmentation.