• 감성과학
• /
• 제16권2호
• /
• pp.157-166
• /
• 2013

자동차 인테리어에 사용된 여러 가지 재질에 대하여 현재까지 촉감을 측정하고 평가하여 소재의 적용과 표면질감의 기준을 결정하고자 했던 연구는 자동차의 조작 장치에 대한 인간공학적 평가, 시각적 디자인요소에 대한 연구에 비해서는 많지 않다. 본 연구에서는 자동차 인테리어의 여러 소재에 대한 촉감 관련 감성을 측정하고 평가하는데 사용될 수 있는 촉감 관련 대표감성을 추출하고자 하였다. 기존의 감성어휘 연구에서 추출되어 있는 대표감성어휘를 이용하여, 자동차에 탑승하여 여러 재질을 보고 만지면서 촉각으로 느껴지는 촉감에 대해 느껴지는 감성어휘와 자동차 사용기의 분석 및 자동차 전문가에 대한 인터뷰 등을 종합하여 최종적으로 52개의 촉감 관련 감성어휘를 추출하였다. 이를 요인분석한 결과 거칠기, 단단함, 마찰감, 안락감, 뻣뻣함, 부드러움, 온도감, 매끈함, 친숙함, 유연함 등 10개의 대표감성으로 분류되었다. 이러한 대표감성 어휘는 자동차 인테리어의 촉감에 대한 소비자의 감성을 측정하고 평가하는데 활용될 수 있을 것이며 금속, 플라스틱, 가죽 등 다양한 소재들의 고급감을 향상시킬 수 있는 질감을 결정할 수 있는 감성평가의 기본 자료로 활용될 수 있을 것이다.

• 한국주거학회논문집
• /
• 제24권1호
• /
• pp.41-49
• /
• 2013

In this research, a representative type of the housing plan was extracted on the basis of elements that exert the influence on the discrimination of the plan type, in other words, plan composition. Firstly, 'connection type of the room' and 'composition type of LDK (living room, dining room and kitchen)' were selected as elements of the plan type. Secondly, three forms of 'connection type of the room' became clear namely 'middle corridor type', 'living room centered type' and 'entrance hall type', as the factors that discriminate plan composition specifically. Thirdly, 'LD/K type' and 'L/D/K type' were confirmed as the factors in 'composition type of LDK'. Finally, four combinations of plan type, such as 'living room centered type-LD/K type', 'middle corridor type-LD/K type', 'living room centered type-L/D/K type' and 'entrance hall type-LD/K type' were confirmed as the representative types. These four combinations are the representative plan types of the urban LDK houses in Japan.

• 대한산업공학회지
• /
• 제38권1호
• /
• pp.67-73
• /
• 2012

Identification of meaningful patterns and trends in large volumes of text data is an important task in various research areas. In the present study we crawled the keywords from the abstracts in IIE Transactions, one of the representative journals in the field of Industrial Engineering from 1969 to 2011. We applied low-dimensional embedding method, clustering analysis, association rule, and social network analysis to find meaningful associative patterns of key words frequently appeared in the paper.

• 정보관리학회지
• /
• 제16권1호
• /
• pp.89-117
• /
• 1999

지역정보 쓰기에서 이용자들을 돕기 위해 (1) 글 구조, (2) 단락 구성, (3) 문장 작성, (4) 어휘 구사에 대한지식을 글 분석을 통해 연구하였다. 글 구상과 단락 구성을 각각 도와주는 글틀과 단락틀 지식베이스가 고안되었고 단어, 절, 문장의 구현에 필요한 단어와 절 및 문장의 예들을 모은 사전 데이터베이스도 만들었다. 서비스의 질을 높이기 위해 전문가 지향적인 시스템을 추구하였다. PC통신과 웹에서 실용적인 시스템이 되려면 앞으로 (1) 글틀과 단락틀의 주제 추출, (2) 문장의 대표어 작성, (3) 각종 규칙의 정제, (4) 정밀한 지식베이스 구축이 필수적이라고 사려된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권2호
• /
• pp.722-733
• /
• 2012

Recently various studies on various applications using images taken by mobile phone cameras have been actively conducted. This study proposes a correction method for misrecognition of Korean Texts in signboard images using improved Levenshtein metric. The proposed method calculates distances of five recognized candidates and detects the best match texts from signboard text database. For verifying the efficiency of the proposed method, a database dictionary is built using 1.3 million words of nationwide signboard through removing duplicated words. We compared the proposed method to Levenshtein Metric which is one of representative text string comparison algorithms. As a result, the proposed method based on improved Levenshtein metric represents an improvement in recognition rates 31.5% on average compared to that of conventional methods.

• 대한가정학회지
• /
• 제30권4호
• /
• pp.167-182
• /
• 1992

The purpose of the study was to determine if an abstract color palette was representative of a color scheme of interior environment by which the meaning of colcor could be determined. An abstract color palette was developed by the researchers to show contrast, overlapping, and adjacencies as they might actually appear in an interior environment. Six pictures and six color palettes were used to test the meaning of color. The questionnaire consisted of 21 words to describe the color of interior environment. The sample consisted of 73 undergraduate students of varied majors. A factor analysis was used to identify the structure of color meaning. Five factors; emotional factor, factor of unity, spatial quality factor, factor of complexity, and social evaluation factor were identified. A t-test was used to analyze the difference in responses to the descriptor words for the pictures and palettes. It was found that in 14 of 21 descriptor, there was no significant difference between evaluation of color meaning for the pictures and palettes in 50% or more of the cases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2154-2168
• /
• 2022

Our work addresses the issues associated with usage of the semantic features by Bag of Words model, which requires construction of the dictionary. Extracting the relevant features and clustering them into code book or dictionary is computationally intensive and requires large storage area. Hence we propose to use a simple distribution of multiple shape based features, which is a mixture of gradients, radius and slope angles requiring very less computational cost and storage requirements but can serve as an equivalent image representative. The experimental work conducted on PASCAL VOC 2007 dataset exhibits marginally closer performance in terms of accuracy with the Bag of Word model using Self Organizing Map for clustering and very significant computational gain.

• 한국멀티미디어학회논문지
• /
• 제17권9호
• /
• pp.1125-1133
• /
• 2014

Recently, there are many researches have been studying for analyzing user interests and emotions based on users profiles and diverse information from Social Network Services (SNSs) due to their popularities. However, most of traditional researches are focusing on their researches based on single resource such as text, image, hash tag, and more, in order to obtain what user emotions are. Hence, this paper propose a method for obtaining user emotional information by analyzing texts and images both from Instagram which is one of the well-known image based SNSs. In order to extract emotional information from given images, we firstly apply GRAB-CUT algorithm to retrieve objects from given images. These retrieved objects will be regenerated by their representative colors, and compared with emotional vocabulary table for extracting which vocabularies are the most appropriate for the given images. Afterward, we will extract emotional vocabularies from text information in the comments for the given images, based on frequencies of adjective words. Finally, we will measure WUP similarities between adjective words and emotional words which extracted from the previous step. We believe that it is possible to obtain more precise user emotional information if we analyzed images and texts both time.

• 디지털콘텐츠학회 논문지
• /
• 제12권4호
• /
• pp.541-550
• /
• 2011

모션타이포그래피는 디지털사회가 요구하는 감성적인 커뮤니케이션에 효과적인 수단으로 활용될 수 있는 요체가 된다. 이에 따라 본 연구에서는 모션타이포그래피로 감성을 표현하기 위하여 움직임의 특성을 연구하는 것을 목적으로 사용자 감성평가를 통해 모션타이포그래피의 감성척도를 구성하고 움직임에 대한 이미지 분포를 파악하였다. 본 연구는 문헌연구와 실험조사를 통하여 감성어휘를 수집하였고 KJ법과 클러스터 분석법으로 대표어휘를 추출하였다. 연구 결과, '차분한-활동적인', '부드러운-딱딱한' 축으로 구성된 모션타이포그래피 감성척도 공간을 구성하였으며, 모션타이포그래피의 움직임은 사용자에게 특정한 감성반응을 유발한다는 것을 알 수 있었다. 향후에 본 논문의 결과와 함께 감성어휘별 시각 요소의 특성을 도출한다면 일반인도 비교적 손쉽게 모션타이포그래피를 제작할 수 있는 가이드라인이 제시될 수 있을 것이다.

• 지식경영연구
• /
• 제21권1호
• /
• pp.99-116
• /
• 2020

Text is the most widely used means of exchanging or expressing knowledge and information in the real world. Recently, researches on structuring unstructured text data for text analysis have been actively performed. One of the most representative document embedding method (i.e. doc2Vec) generates a single vector for each document using the whole corpus included in the document. This causes a limitation that the document vector is affected by not only core words but also other miscellaneous words. Additionally, the traditional document embedding algorithms map each document into only one vector. Therefore, it is not easy to represent a complex document with interdisciplinary subjects into a single vector properly by the traditional approach. In this paper, we introduce a multi-vector document embedding method to overcome these limitations of the traditional document embedding methods. After introducing the previous study on multi-vector document embedding, we visually analyze the effects of the multi-vector document embedding method. Firstly, the new method vectorizes the document using only predefined keywords instead of the entire words. Secondly, the new method decomposes various subjects included in the document and generates multiple vectors for each document. The experiments for about three thousands of academic papers revealed that the single vector-based traditional approach cannot properly map complex documents because of interference among subjects in each vector. With the multi-vector based method, we ascertained that the information and knowledge in complex documents can be represented more accurately by eliminating the interference among subjects.