• Journal of the Korean Data and Information Science Society
• /
• 제20권3호
• /
• pp.505-514
• /
• 2009

본 연구는 협력적 필터링 기법을 이용한 선호도 예측 과정에서 이웃의 수와 선호도 예측 정확도와의 관계를 분석하였다. 선호도 예측 과정에 선정된 이웃의 수를 4분위수로 4집단으로 구분하여 구분한 집단 간 선호도 예측 정확도에 차이가 나타남을 알 수 있었으며 각 집단의 예측 오차들의 평균들을 이용하여 선형의 보정함수를 제안하였다. 본 연구의 결과를 바탕으로 추천시스템에서 이웃 수를 이용한 보정함수를 이용하면 예측 정확도를 높일 수 있다.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.40-50
• /
• 2021

Science museum are dealing with exhibits on field of changing science and technology, and previous research suggested that exhibits replacement should carried out at least every 5 years. In order to efficiently replace exhibits within a limited budget, various studies analyzed visitors' preferences to exhibits. Recently, studies use various technologies to collect the data on visitors' preferences automatically, but almost of studies had a high dependency on their visitors such as visitors needed to carry specific sub-devices in the museums for gathering data. As complementing the limitations of previous research, this study introduces the improved method which is able to automatically collect and quantify visitors' preferences to exhibits using TensorFlow, a deep learning technology. By the proposed analysis method, it was possible to collect 2,520 data of visitors' experience on exhibits in totality. Based on collected data, attraction power and holding power indicating the preference of visitors on exhibits were able to be calculated. The result also confirmed antecedent research conclusion that the attraction power and holding power of the exhibit which consists of 3 dimensional structures work are higher than other exhibits. As a conclusion, the proposed method will provide more convenient data collection method for detecting visitors' preference.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.717-726
• /
• 2006

This study is to investigate the MAE of prediction value by collaborative filtering algorithm originated by GroupLens and improved algorithm. To decrease the MAE on the collaborative recommender system on user based, this research proposes the improved algorithm, which reduces the possibility of over estimation of active user's preference mean collaboratively using other user’s preference mean. The result shows the MAE of prediction by improved algorithm is better than original algorithm, so the active user's preference mean used in prediction formula is possibly over estimated.

• 대한가정학회지
• /
• 제31권1호
• /
• pp.193-210
• /
• 1993

The purpose of this study was to investigate the effect of age, physical type and job on preference for color and fabric motifs in men's clothing design. Color preference measures consisted of clothing styles painted in CAD. Preference for fabric motifs was assesed by stripe fabrics in size, width and strength. All of the preference measures were devised specifically for this study. Furthermore, items on Hight and Weight for physical type, age and job of subjects were included I the questionnaire. Data were obtained by self-administered questionnaires form 243 men (25-54 years old) in Seoul. Analysis was by chi-square (X2), frequency, and percentage. The results obtained in this study were as follows : 1. Color preference was not affected by age and physical type, Job was related to coordinate color of men's clothing. 2. Preference for width of striped motifs was affected by age and job. 3. Preference for strength of fabric motifs in men's jacket was affected by physical type.

• 데이타베이스연구회지:데이타베이스연구
• /
• 제34권3호
• /
• pp.86-98
• /
• 2018

장소추천시스템은 시간과 장소가 주어졌을 때, 사용자에게 가장 흥미로운 장소를 추천해주는 시스템을 말한다. 스마트폰과 사물인터넷(IoT), 장소기반 소셜네트워크(LBSN)의 발달에 힘입어 사용자들의 방대한 양의 장소 방문 데이터를 축적하게 되었고, 이를 통해 특정한 시점에 사용자들이 원하는 장소를 적절히 추천해줄 수 있는 장소추천시스템의 중요성이 부각되었다. 장소추천시스템은 사용자의 방문(Check-in) 횟수라는 암시적 피드백(Implicit feedback) 데이터에서 사용자의 시퀀스 선호(Sequential preference)를 이끌어내어 높은 성능을 내기 위한 연구들이 제안되었다. 하지만 시퀀스 선호 정보를 활용하여 모델을 구성하는 경우, 데이터의 밀도가 더욱 희박해지고 이에 따라 적은 수의 데이터에 기반하여 구축되는 모델의 성능이 왜곡될 가능성이 존재한다. 본 연구에서는 신뢰도(Confidence)에 기반하여 방문 주기를 보정하는 방법론을 제안한다. 사용자의 시퀀스 선호 정보로부터 도출된 장소 간 방문 시간전이간격(temporal transition interval)을 활용하여 추천시스템을 구성할 때, 해당 방법론을 통하여 데이터의 왜곡을 보정함으로써 추천시스템의 성능을 향상하였다. 제안하는 방법의 효과를 검증하기 위하여, Foursquare와 Gowalla의 데이터셋을 이용한 비교실험을 통해 제안하는 방법론의 우수성을 보였다.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2011년도 춘계학술발표대회 논문집
• /
• pp.279-284
• /
• 2011

This research was focused on collecting and analyzing the data about the preference and awareness about elderly housing among middle aged women. A questionnaire survey was adopted in this study. The data were collected from 120 people between 30~60years old middle aged women living in the city of Seoul from October, 1, 2010 to October, 19, 2010 and 105 cases were used for data analysis. To observe the preference differentiation of elderly housing, by the SPSS Win 18.0 program, $x^2$-test, t-test and ANOVA were utilized. The results of the research were as followings. First, respondents preferred middle scale and single-detached dwelling in suburban areas. Second, for the reason of considering elderly housing, respondents said that they consider the elderly housing as a safe and comfortable place. Third, they preferred that elderly housing should be supplied by local authority or the government. In conclusion, the government and local authorities need to provide elderly housing which can improve the older people's residential welfare in the future aged society and develop a model of the elderly housing which reflects the preference of the middle aged women.

• KIEAE Journal
• /
• 제8권2호
• /
• pp.65-70
• /
• 2008

Recently, there has been growing interest in barrier-free design which makes safe and convenient space for every pedestrian, not only the non-disabled but also the disabled. The purpose of this study is to suggest the data on the pavement materials of barrier-free pedestrian environment in view of universal design. In order to this, the research is focused on evaluating the visual preference and preference factors for pavement scenery, which can be changed by pavement materials. And this research is also comparing the visual preference and preference factors of the disabled with that of the non-disabled. A multi-regression analysis method is adopted to analyse the correlation between the visual preference for pavement scenery and preference factors in this study. The result of this analysis is as follows. Firstly, there are some differences of visual preference for the pavement material between the disabled and the non-disabled. Secondly, independent variables influencing on preference are similar between two groups. Thirdly, there are some differences in the priority of preference between the disabled and the non-disabled. This study will contribute to the field of barrier-free design and sustainable development projects in order to maximize the human being's satisfaction.

• 한국치위생학회지
• /
• 제15권6호
• /
• pp.973-981
• /
• 2015

Objectives: The purpose of the study is to investigate the correlation with subjective oral health status and food preference in elderly people. Methods: Data were extracted from the fifth Korea National Health and Nutrition Survey 2010-2012. The survey data included general characteristics of the subjects, food preference, and subjective oral health status. Food preference was analyzed by assigning score to 63 food categories. The subjective oral health status consisted of toothache within a month, self-perception of oral health, chewing difficulty, mastication difficulty, and speaking difficulty. Data were analyzed by frequency analysis, descriptive statistics, ${\chi}^2$ test, t-test, and ANOVA using SPSS 22.0 program. Results: Elderly men had a tendency to have a liking for all food categories except for fruit. Difficulty in chewing and mastication was shown in those who had older age, lower education, lower monthly income, and national basic livelihood security. Difficulty in speaking was found in those who had older age, lower education, and national basic livelihood security. Self perception of oral health status was closely related to food preference for pulses and potatoes, fish, vegetables and others(p<0.05). Difficulties in chewing and mastication had relation to all food categories excepting cereals, lipids and sugars(p<0.05). Speaking difficulty were significantly different in pulses, potatoes, meat, eggs, vegetables, fruits, milk, dairy products, and others(p<0.05). Conclusions: Poor subjective oral health status was closely related to food preference. It is necessary to educate that maintenance of good oral health is to ingest the balanced nutrition in the elderly people.

• 창의정보문화연구
• /
• 제7권4호
• /
• pp.279-288
• /
• 2021

본 연구의 목적은 국가 수준의 종단 연구 자료인 한국아동패널 자료를 활용하여 유아가 선호하는 놀이영역을 예측하는 변인들의 관계를 탐색하여 유아의 놀이행동에 대한 이해를 증진시키고자 하는 것이다. 이를 위해 유아의 성을 통제변인으로 설정하고 창의성과 또래놀이행동이 유아의 놀이영역 선호에 어떠한 영향을 미치는지를 알아보았다. 본 연구에서 밝힌 연구 결과는 다음과 같다. 첫째 유아의 성에 따라 창의성, 또래놀이행동, 놀이영역 선호의 차이가 나타났다. 둘째, 유아의 창의성과 또래놀이행동이 놀이영역 선호에 미치는 영향을 알아본 결과, 쌓기놀이영역 선호집단을 기준으로 할 때 언어영역, 미술영역, 수조작놀이영역, 역할놀이영역 선호에 영향을 미치는 요인은 다르게 나타났다. 본 연구는 유아의 놀이영역 선호에 영향을 미치는 변인들을 탐색하여 유아의 놀이행동을 위한 기초자료를 제공하고 있다는 점에서 시사하는 바가 크다.

• 정보관리학회지
• /
• 제39권3호
• /
• pp.311-336
• /
• 2022

본 연구는 도서관 정보서비스 환경에서 도서 이용자의 도서추천에 영향을 미치는 선호요인을 파악하기 위해 전 세계 도서 이용자의 참여로 이루어지는 사회적 목록 서비스인 Goodreads 리뷰 데이터를 대상으로 내용분석하였다. 이용자 선호의 내용을 보다 세부적인 관점에서 파악하기 위해 샘플 선정 과정에서 평점 그룹별, 도서별, 이용자별 하위 데이터 집합을 구성하였으며, 다양한 토픽을 고루 반영하기 위해 리뷰 텍스트의 토픽모델링 결과에 기반하여 층화 샘플링을 수행하였다. 그 결과, '내용', '캐릭터', '글쓰기', '읽기', '작가', '스토리', '형식'의 7개 범주에 속하는 총 90개 선호요인 관련 개념을 식별하는 한편, 평점에 따라 드러나는 일반적인 선호요인은 물론 호불호가 분명한 도서와 이용자에서 드러나는 선호요인의 양상을 파악하였다. 본 연구의 결과는 이용자 선호요인의 구체적 양상을 파악하여 향후 추천시스템 등에서 보다 정교한 추천에 기여할 수 있을 것으로 보인다.