• Journal of Information Technology Applications and Management
• /
• 제16권4호
• /
• pp.93-107
• /
• 2009

This study investigated consumer preferences for Internet medical information service in China using the multi-attribute utility theory. The multi-attribute utility theory is a compositional approach for modeling consumer preferences wherein researchers calculate the overall service utility by summing up the evaluation results for each attribute. We found that Chinese Internet medical information users consider the availability of information and quick response to be the most important attributes. Further, they think that the comment feature is less important as compared to other attributes such as costs and updates. In addition, we found that the Internet users having more Internet experience consider these attributes to be more important as compared to the people who are just beginning to surf the Internet. For any successful Internet business, Internet marketers should assess individual-level preference and accordingly organize a fresh campaign. As of now, Internet marketers need estimation methods to predict the market performance of new services in many different business environments. We believe that the multi-attribute utility theory is a useful approach in this regard.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.369-373
• /
• 2022

In the decision-making domain, a document warehouse is designed to meet the analysis needs of users who may have a wide variety of analysis purposes. In this paper, we propose to integrate the preferences and interactions of users based on profiles to the concept of document warehouses. These profiles guarantee the integration of personalized documents and the collaborative recommendation of documents between different users sharing common interests.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• International Journal of Contents
• /
• 제12권2호
• /
• pp.37-41
• /
• 2016

In this paper, we propose a friend recommendation scheme that takes into consideration the attribute information of a POI and a user's movement patterns. The proposed scheme broadly consists of a part that filters out other users who have different preferences by calculating preferences using the attribute information of users and a part that finds a moving trajectory close to that of a user with a pattern-matching scheme. To verify the superiority of the proposed scheme, we compare it with existing schemes through various performance evaluations.

• 디지털산업정보학회논문지
• /
• 제8권4호
• /
• pp.83-90
• /
• 2012

With the rapid growth of internet infrastructure, World Wide Web is evolving recently into various services such as cloud computing, social network services. It simply go beyond the sharing of information. It started to provide new services such as E-business, remote control or management, providing virtual services, and recently it is evolving into new services such as cloud computing and social network services. These kinds of communications through World Wide Web have been interested in and have developed user-centric customized services rather than providing provider-centric informations. In these environments, it is very important to check and analyze the user requests to a website. Especially, estimating user preferences is most important. For these reasons, analyzing web logs is being done, however, it has limitations that the most of data to analyze are based on page unit statistics. Therefore, it is not enough to evaluate user preferences only by statistics of specific page. Because recent main contents of web page design are being made of media files such as image files, and of dynamic pages utilizing the techniques of CSS, Div, iFrame etc. In this paper, large log analyzer was designed and executed to analyze web server log to estimate web contents preferences of users. With mapreduce which is based on Hadoop, large logs were analyzed and web contents preferences of media files such as image files, sounds and videos were estimated.

• 한국게임학회 논문지
• /
• 제7권4호
• /
• pp.23-31
• /
• 2007

본 연구는 게임 이용자의 성향에 대한 분석을 통해 게임 이용자를 유형화하고, 게임 캐릭터 의 선호도를 중심으로 조형요소를 도출하여 이용자의 유형과 캐릭터 선호도 관계를 분석함으로서, 게임 이용자의 성향에 따른 게임 캐릭터 개발을 제안하는 것에 목적이 있다. 이를 위해 게임 이용자의 몰입도와 관련된 이용자 분류 방법을 조사하였으며, 이를 기초로 설문조사를 하였다. 설문조사 결과를 바탕으로 이용자 유형을 재정의 하였고, 게임 캐릭터 디자인 요소를 추출하여 이용자의 성향에 따른 캐릭터 선호도차이를 규명하였다.

• 한국농촌건축학회논문집
• /
• 제21권1호
• /
• pp.25-36
• /
• 2019

This study is a basic study for the planning of rural community center space, which introduced the concept of healthcare. As the rural community center is a place where the elderly in rural areas live mainly during the day, this place is very important place for the healthy life of the rural elderly. We conducted an interview survey for 207 users over 65. The survey was organized with three regions to consider the regional characteristics of the community center users and geographical characteristics. As a result of the analysis of planning elements, the main preferences for indoor and outdoor space elements are planning elements such as safety, air quality, light, and the thermal environment and safety handle, night lights, safety walkway. These preferences should be considered for the more healthy friendly rural community center.

• 한국도서관정보학회지
• /
• 제51권2호
• /
• pp.245-272
• /
• 2020

본 연구의 목적은 대학도서관 공간 활용 현황 분석을 통해 공간 활용도를 향상시키기 위한 고려 사항들을 도출하는 것이다. 이를 위해 첫째, 대학도서관의 이용자 공간을 범주화하고 그에 따른 이용률을 분석하였으며, 둘째, 이용자 공간의 특성에 따른 주요 이용자 그룹의 선호도를 분석하였다. 셋째. 구체적인 이용자 그룹별 공간 선호 요인을 판별하고, 넷째, 분석 결과를 바탕으로 효율적인 도서관 공간을 설계하기 위한 시사점과 개선 방안을 제안하였다. 실증적인 분석을 위해 국립 J대학의 중앙도서관을 대상으로 1년간 누적된 이용자 공간 이용 데이터(98,282명, 433,769건)를 수집·정제하여 공간별, 기간별(월별, 시간별)로 이용 패턴을 파악하였다. 또한 동 기간 내 도서관 방문자 전체 데이터(2,426,553건)를 통해 도서관의 주요 이용자 그룹(학부생, 대학원생, 졸업생)을 도출, 이용자 그룹별 공간 특성에 따른 선호도를 분석하였다. 본 연구의 결과는 향후 대학도서관의 이용자 공간의 구성 및 배치를 위한 기초 자료로 활용될 수 있을 것이다.

• 정보관리학회지
• /
• 제38권2호
• /
• pp.113-127
• /
• 2021

본 연구는 대학 도서관 사용 증진을 위하여 개인별 맞춤 도서 추천시스템을 구축하는 것을 목적으로 한다. 특히 사용자의 아이템에 대한 선호도가 존재하는 다수의 추천시스템과는 달리, 선호도가 존재하지 않을 때에 도서 추천이 가능하도록 하는 방안인 도서관 이용자의 도서 대출 목록과 성향을 활용하여 평가지표를 생성하는 방법을 제안하고자 한다. 이용자가 아직 읽지 않은 책에 대한 예상 선호도를 산출하는 방식으로 도서를 추천하는 행렬 분해 방법인 Singular Value Decomposition(SVD)과 Stochastic Gradient Descent(SGD) 알고리즘을 활용한 모델을 구축했다. 더불어 유사도가 높은 이용자 그룹 내의 도서 대출 목록을 참조하여 추천하는 사용자 기반 협업 필터링 알고리즘을 활용해 모델을 구현했다. 최종적으로 평가지표를 활용한 세 가지 모델에 대하여 사용자 평가를 진행했다. 각각의 모델이 제시한 개인별 맞춤 도서 다섯 권의 목록을 해당 대출자에게 제공하고, 추천 도서에 대한 만족/불만족 여부를 이진화 점수화하여 모델에 대한 평가를 진행했다.

• 한국환경복원기술학회지
• /
• 제10권6호
• /
• pp.33-43
• /
• 2007

The revised Urban Park regulations newly adopt Theme Parks in order to enhance richness and diversities of urban services to communities. However, the regulations ambiguously define the main facilities and service programs of the theme parks. And there have been increasing concerns about confusions in terms of the main facilities and service programs of the theme parks among landscape designers/planners, local governments and relevant field of areas. Misunderstanding on the facilities and service programs of the theme parks may lead to ruin the purposes of the new urban park regulations. In the lights of these, this paper tries to reach a consensus for main facilities and service programs of two theme parks including athletic park and waterfront park, based on measured potential users' preferences with a conjoint choice model. For waterfront parks, potential users show low preferences or negative responses to facilities which are perceived as un-environment friendly. They also show high preferences on ecological areas sitting near to streams. For athletic parks, potential users show demand to introduce something different facilities and atmosphere from existing athletic parks. The demands are particularly high for children's play ground facilities and service facilities. This study also show some methodological examples to compute the carrying capacity with two hypothetical alternatives. This approach might be beneficial for local governments which are wish to alternate the park size on the basis of local conditions such as their financial conditions and land availability.