• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.621-623
• /
• 2022

최근 코로나19로 인해 비대면으로 소통할 수 있는 플랫폼에 대한 관심이 증가하고 있으며, 가상 세계의 개념을 도입한 메타버스 플랫폼이 MZ세대의 새로운 SNS로 떠오르고 있다. 아바타를 통해 상호 교류가 가능한 메타버스는 텍스트 기반의 소통뿐만 아니라 음성과 동작 시선 등을 활용하여 변화된 의사소통 방식을 사용한다. 음성을 활용한 소통이 증가함에 따라 다른 이용자에게 불쾌감을 주는 혐오 발언에 대한 신고가 증가하고 있다. 그러나 기존 혐오 발언 탐지 시스템은 텍스트를 기반으로 하여 사전에 정의된 혐오 키워드만 특수문자로 대체하는 방식을 사용하기 때문에 음성 혐오 발언에 대해서는 탐지하지 못한다. 이에 본 논문에서는 인공지능을 활용한 음성 혐오 표현 탐지 시스템을 제안한다. 제안하는 시스템은 음성 데이터의 파형을 통해 은유적 혐오 표현과 혐오 발언에 대한 감정적 특징을 추출하고 음성 데이터를 텍스트 데이터로 변환하여 혐오 문장을 탐지한 결과와 결합한다. 향후, 제안하는 시스템의 현실적인 검증을 위해 시스템 구축을 통한 성능평가가 필요하다.

• Journal of Software Assessment and Valuation
• /
• v.14 no.2
• /
• pp.1-9
• /
• 2018

The proportion of users and companies using open source continues to grow. The size of open source software market is growing rapidly not only in foreign countries but also in Korea. However, compared to the continuous development of open source software, there is little research on open source software subject classification, and the classification system of software is not specified either. At present, the user uses a method of directly inputting or tagging the subject, and there is a misclassification and hassle as a result. Research on open source software classification can also be used as a basis for open source software evaluation, recommendation, and filtering. Therefore, in this study, we propose a method to classify open source software by using machine learning model and propose performance comparison by machine learning model.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.614-625
• /
• 2013

The nostalgia marketing is active in various industrial areas. The nostalgic theme is emerging as a new trend in the film industry. This thesis attempts to investigate empirically the effect of nostalgia, the expectation and the evaluation on the intention to watch a movie. Nostalgia is a sentimental yearning for a former place or time. Expectation is classified into the utilitarian and the hedonic one; the evaluation into the subjective and the objective one. This thesis analyzed the effects of these five factors on the intention to watch a movie. The result shows that the older group felt more nostalgic than the younger; women more than men. Regarding the age, 10-20s are affected by the hedonic expectation, the subjective evaluation, and nostalgia, and over 30s are affected in order of the hedonic expectation and nostalgia. In terms of sex, men are affected most in order of the hedonic expectation, nostalgia and the subjective evaluation. Women are affected most in order of the hedonic expectation and the subjective evaluation. These results indicate that the marketing strategy needs to vary according to age and sex.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.45-52
• /
• 2020

Traditional methods of detecting security vulnerabilities in source-code require a lot of time and effort. If there is good data, the issue could be solved by using the data with machine learning. Thus, this paper proposes a source-code vulnerability detection method based on machine learning. Our method employs the code2vec model that has been used to propose the names of methods, and uses as a data set, Juliet Test Suite that is a collection of common security vulnerabilities. The evaluation shows that our method has high precision of 97.3% and recall rates of 98.6%. And the result of detecting vulnerabilities in open source project shows hopeful potential. In addition, it is expected that further progress can be made through studies covering with vulnerabilities and languages not addressed here.

• Korean Journal of Child Studies
• /
• v.24 no.5
• /
• pp.105-118
• /
• 2003

Construction of the Prosocial Behavior Scale for young children(PBSYC) was based on document research and interviews with kindergarten teachers and child development specialists. After 200 kindergarten teachers evaluated the 42 items of the PBSYC, factor analysis was conducted; items were categorized into seven factors: leadership, helping, communication, concern, proximity, sharing and empathy. As factors showed high correlation. The prosocial behavior of 306 4 to 5 year old children was measured with the PBSYC and compared with the Babock, Hartle & Lamme(l995) scale. The resulting correlation between the 2 scales was .764. Further tests indicate that the PBSYC is a valid and reliable scale for the measurement of prosocial behavior in young children.

• Korean Journal of Biological Psychiatry
• /
• v.2 no.2
• /
• pp.177-185
• /
• 1995

외상후 뇌손상은 대표적이며, 가장 중요한 신경정신계 질환의 하나이다. 더욱이 외상후 뇌손상 환자들은 각종의 사고 및 산업재해 등으로 인해 그 수가 급증하고 있으며, 특히 인지기능의 장애로 인한 다양한 기질성 정신장애로 고통을 겪게 된다. 따라서 외상후 뇌손상은 손상의 시점에서부터 정확하고 올바른 평가는 물론 손상후의 경과 및 치료대책의 수립에 있어서 체계적이며 종합적인 신경인지기능의 평가는 필수적이다. 왜냐하면 신경인지기능평가는 뇌의 손상부위와 이와 관련된 기능장애 및 행동의 변화에 대한 객관적인 자료를 제시해 주기 때문이다. 신경인지기능 평가의 영역은 지각, 운동기능은 물론 주요인지기능인 기억, 언어, 실행 및 감정조절능력에 이르기까지 다양하며, 외상후 뇌손상환자들은 손상부위 및 정도에 따라 신경인지기능의 장애를 초래하게 된다. 대표적인 신경인지기능평가 도구로는 KWIS, Halstead-Reitan, Luria-Nebraska batteries, 특히 전두엽기능검사인 Wisconsin Card Sorting Test (WCST)를 비롯하여, 현재는 PC/S Vienna Test System 및 Stim등의 각종 전산화 인지기능검사가 개발되어 임상에서 활발히 사용되고 있다. 즉 외상후 뇌손상환자를 위한 신경인지기능평가의 목적은 뇌손상과 관련된 신경인지기능장애를 정확히 평가하여, 환자 개개인에 적합한 인지재활치료 계획을 수립하는데 있다. 물론 여기에는 신경정신상태검사(neuropsychiatric mental status examination)를 통하여 외상 후 뇌손상의 경과 및 예후에 결정적인 영향을 미칠 수 있는 나이, 의식소실 및 외상후 기억 손상 시간의 정확한 측정은 물론 심리 사회 문화적인 상태와 두부외상전 환자의 지적수준 및 사회 적용기능이 함께 평가되어야 할 것이다.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.23 no.8
• /
• pp.1075-1085
• /
• 1999

Brand equity is the added value endowed by the brand to the product. This concept born in the 1980's has aroused intense interest among market managers and business strategists from a wide variety of industries. Brand equity can be approached in different perspectives according to the motivations and the objectives of the studies. Consumer-based brand equity is examined internally by consumers' cognition and feeling and externally by consume behavior in the market By analyzing the relationship between them we can understand how brand value is made in the mind of consumers and how it is converted into the consumer behavior,. The brand is an especially important extrinsic cue in clothing products and the apparel industry has higher brand equity when it is actually compared with the brand equity of many other industries measured as a financial asset. Therefore the purpose of this study was to find out brand value of clothing products through clothing brand equity and to understand consumer behavior of the brand. And so we focused in consumer-based brand equity. For the empirical study three brands that are predicted to have different level of brand equity were selected based on prices and market shares of the brands. As the result the consumer-based brand equity is composed of emotional and cognitive dimensions and each dimension has several sub-dimensions. These diverse dimensions of brand equity bring about differences in consumers' purchase behavior market share and price premium of brands.

• Culinary science and hospitality research
• /
• v.13 no.4
• /
• pp.45-56
• /
• 2007

The purpose of this study was to measure the causal relationships among affective belief, ambivalence, subjective norm, attitude, intention to consume and meat consumption. A total of 318 questionnaires were completed. The structural equation model was used to measure the causal effects among constructs. The results demonstrated that the confirmatory factor analysis model provided excellent model fit. The proposed model yielded a significantly better fit to the data than the baseline model. The effects of affective belief, ambivalence and subjective norm on attitude were statistically significant. The effect of subjective norm on intention was statistically significant. As expected, subjective norm and attitude had significant effects on meat consumption. Moreover, affective belief, ambivalence and subjective norm had indirect influences on meat consumption. Subjective norm also had an indirect influence on intention. The overall findings offered strong empirical support for the intuitive notion that improving the level of attitude toward eating meat can increase favorable intentions and decrease unfavorable intentions to reduce future meat consumption.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.276-288
• /
• 2020

This study analyzed the intervention program of smartphone addiction. The literature used for this research analysis was published from Jan. 2010 to Jul. 2019. The foreign literature was searched for in 'Pubmed and Science Direct', and the domestic literature was found in 'RISS, Keris, and KISS'. A total of 310 studies were found and analyzed on the basis of our inclusion and exclusion criteria. Finally, 16 theses were analyzed. Thirteen theses (81%) meet the required evidence level, and three theses (19%) had level III. As a result of analysis on the intervention methods of smartphone addiction, art therapy was found in 6 theses (37.5%), exercise therapy in four theses (25.0%), and cognitive behavior therapy in three theses (18.6%). After the intervention of most of the programs, there were reduced withdrawal symptoms of smartphone addiction, reduced negative feelings like depression, anxiety, and impulsiveness, and increased positive feelings like self-esteem. A smartphone addiction evaluation scale was mostly applied in terms of the evaluated items, along with psychological evaluation. These studies are expected to be effectively used as intervention tools for treating smartphone addiction.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.83-92
• /
• 2021

There are continuous and tremendous attempts to apply various sensor systems and ICTs into the dairy science for data accumulation and improvement of dairy productivity. However, these only concerns the fields which directly affect to the dairy productivity such as the number of individuals and the milk production amount, while researches on the physiology aspects of dairy cows are not enough which are fundamentally involved in the dairy productivity. This paper proposes the basic approach for extraction of daily behavior pattern from hourly behavioral data of dairy cows to identify the health status and stress. Total four clusters were grouped by k-means clustering and the reasonability was proved by visualization of the data in each groups and the representatives of each groups. We hope that provided results should lead to the further researches on catching abnormalities and disease signs of dairy cows.