• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.465-467
• /
• 2022

Mobile phones have become an essential item nowadays since it provides access to online platform and service fast and easy. Coming to these platforms such as Social Network Service (SNS) for shopping have been a go-to option for many people. However, searching for a specific fashion item in the picture is challenging, where users need to try multiple searches by combining appropriate search keywords. To tackle this problem, we propose a system that could provide immediate access to websites related to fashion items. In the framework, we also propose a deep learning model for an automatic analysis of image contexts using instance segmentation. We use transfer learning by utilizing Deep fashion 2 to maximize our model accuracy. After segmenting all the fashion item objects in the image, the related search information is retrieved when the object is clicked. Furthermore, we successfully deploy our system so that it could be assessable using any web browser. We prove that deep learning could be a promising tool not only for scientific purpose but also applicable to commercial shopping.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.209-209
• /
• 2022

Reservoirs play a key role in the carbon cycle between terrestrial and marine systems and are pathways that release greenhouse gases(GHGs), CO₂, CH₄, and N₂O, into the atmosphere by decomposing organic matters. Developed countries have been actively conducting research on carbon emission assessment of dam reservoirs for over 10 years under the leadership of UNESCO/IHA, but associated research is very rare in Korea. In particular, the GHGs footprint evaluation, which calculates the change in net carbon emission considering the watershed environment between pre- and post- impoundment, is very important in evaluating the carbon emission of hydroelectric dams. The objective of this study was to estimate the GHG emissions and footprints in Daecheong Reservoir using the G-res Tool, an online platform developed by UNESCO/IHA. The G-res Tool estimates CO₂ and CH₄ emissions in consideration of diverse pathway fluxes of GHGs from the reservoir and characterizes changes in GHG fluxes over 100 years based on the expected lifetime of the dam. The input required to use the G-res Tool include data related to watersheds, reservoirs, and dams, and most were collected through the government's public portal. As a result of the study, the GHG footprint of Daecheong Reservoir was estimated to be 93 gCO₂eq/m²/yr, which is similar to that of other reservoirs around the world in the same climate zone. After impoundment, the CH₄ diffusion emission from the reservoir was 73 gCO₂eq/m²/yr, also similar to those of the overseas reservoirs, but the CH₄ bubbling emission, degassing emission, and CO₂ diffusion emissions were 44, 34, 252 gCO₂eq/m²/yr, respectively, showing a rather high tendency. Since the dam reservoir carbon footprint evaluation is essential for the Clean Development Mechanism evaluation of hydroelectric power generation, continuous research is needed in the future. In particular, experimental studies that can replace the emission factors obtained from the overseas dam reservoirs currently used in the G-res Tool should be promoted.

• 한국의류산업학회지
• /
• 제25권6호
• /
• pp.704-714
• /
• 2023

This study explores how avatar customization influences the continuous intention to use the metaverse, mediated by self-expansion. The moderating effects of self-efficacy between avatar customization and self-expansion are also explored. Data were collected through an online survey using consumer panels. Participants were Zepeto users aged 18 or older who had used the platform within the previous six months. They were asked to recall a recent shopping experience of exploring the virtual fashion store via Zepeto. A total of 196 valid responses from participants were analyzed using SPSS 26.0 for descriptive statistics, reliability analysis, and PROCESS procedure, and AMOS 23.0 for confirmatory factor analysis. Results demonstrate that avatar customization increases continuous intention to use the metaverse; this effect is mediated by self-expansion. The moderated mediation effect of self-efficacy in the indirect path was significant and mediated by self-expansion. Specifically, the interplay effect of avatar customization and self-efficacy on self-expansion was statistically significant. For participants with high self-efficacy, avatar customization increases self-expansion, and it mediates the relationship between avatar customization and the continuous intention to use the metaverse. Findings contribute to expanding the literature on metaverse usage by testing the impact of avatar customization on self-expansion.

• 정보화정책
• /
• 제30권4호
• /
• pp.89-112
• /
• 2023

교통안전정책은 교통안전법을 기반으로 5년마다 수립되어 진행되고 있다. 장기적으로 계획이 수립되어 진행되는 정책 외에도 사회적으로 이슈가 되는 각종 사건, 사고의 재발을 방지하기 위해 수립되는 정책들도 있다. 시민의 행정참여는 최근 들어 관심이 매우 집중되고 있으며, 행정의 민주성을 실현할 수 있는 효율적인 수단이 되고 있다. 본 연구에서는 최근 어린이보호구역에 대한 법령강화라는 사회적 이슈를 몰고 온 '김민식 사건'이 '국민청원'이라는 '온라인 플랫폼'의 등장으로 인해 어떻게 행정의 민주성이 구현되고 있으며, 법제정에 기여하게 되었는지 빅데이터 분석을 기반으로 제시하고자 한다. 이슈의 주기에 따른 정책변동을 시계열적인 구분에 따라 나누고 각 구간에 어떠한 내용으로 구성되고 있는지 텍스트마이닝 분석을 통해 살펴보고자 한다. 본 연구의 결과는 정책문제 해결에 있어 실질적이고 현실적인 대안의 마련이 중요하다는 정책적 함의를 제시함으로써 연구자 및 정책입안자에게 유용한 이론적, 실무적 시사점을 제공할 것으로 기대한다.

• 무역학회지
• /
• 제46권2호
• /
• pp.193-212
• /
• 2021

This study investigates the structural relationship among 11 latent factors that potentially influence the intention of Chinese consumers to purchase electrical vehicles (EV) by applying the MGB and TAM models, both based on well-established socio-psychological theories. For this research, we conducted an online survey using a Chinese platform collecting 287 valid responses to our questionnaire. The analysis reveals that 10 out of the 12 hypotheses were adopted while 2 were rejected. Specifically, it was found that EC (environment concern) and PEV (perceived environment value) had a positive effect on the PEU (perceived environmental usefulness) of electric vehicles. In addition, ATT (attitude), PAE (positive anticipated emotion), and PBC (perceived behavior control) were confirmed to have a significant positive relationship with DES (desire) for EV purchase. At the same time, the results of the analysis show a statistically significant relationship between PEU, ATT as well as PI (purchase intention). This study further analyzed and presented the results of the moderating effects of gender, based on the adopted relationship hypotheses. This study is novel in that it is the first attempt in the literature to apply both the MGB model and the TAM simultaneously to predict EV purchasing behavior.

• 한국기록관리학회지
• /
• 제23권4호
• /
• pp.159-178
• /
• 2023

디지털 아카이브는 지속적으로 보존할 가치가 있는 디지털 기록을 보존하고 활용하기 위한 온라인 플랫폼이다. 그러나 국내에서 운영되고 있는 디지털 아카이브는 기능 메타데이터, 데이터의 기술원칙과 관련된 공통 원칙이 존재하지 않는다. 이는 분산적으로 존재하는 디지털 기록을 연계하기 힘들게 만드는 요인이 된다. 본 연구는 디지털 기록의 상호운용을 개선하기 위한 방안으로 디지털 아카이브를 위한 공통 어휘를 제안하고, 공통 어휘로 구축된 디지털 아카이브의 상호운용성을 평가한다. 1997 외환위기 아카이브의 데이터를 수집·분석하여 지식그래프를 구축하고, RiC-O로 구축된 지식그래프와 상호운용성을 비교한다, FAIR 데이터 원칙의 평가 프레임워크는 1997 외환위기 아카이브와 지식그래프를 평가하는 데 활용된다. 구축된 지식그래프는 기록의 다양한 개체가 서로 연계되고, 기록의 이해에 도움이 되는 맥락 정보를 제공한다. 검증 결과는 공통 어휘로 구축된 지식그래프가 기존 아카이브에 비해 디지털 기록의 연계와 검색, 상호운용 관점에서 향상된 결과를 보인다.

• International Journal of Computer Science & Network Security
• /
• 제23권10호
• /
• pp.97-106
• /
• 2023

Sentiment analysis using social network platforms such as Twitter has achieved tremendous results. Twitter is an online social networking site that contains a rich amount of data. The platform is known as an information channel corresponding to different sites and categories. Tweets are most often publicly accessible with very few limitations and security options available. Twitter also has powerful tools to enhance the utility of Twitter and a powerful search system to make publicly accessible the recently posted tweets by keyword. As popular social media, Twitter has the potential for interconnectivity of information, reviews, updates, and all of which is important to engage the targeted population. In this work, numerous methods that perform a classification of tweet sentiment in Twitter is discussed. There has been a lot of work in the field of sentiment analysis of Twitter data. This study provides a comprehensive analysis of the most standard and widely applicable techniques for opinion mining that are based on machine learning and lexicon-based along with their metrics. The proposed work is helpful to analyze the information in the tweets where opinions are highly unstructured, heterogeneous, and polarized positive, negative or neutral. In order to validate the performance of the proposed framework, an extensive series of experiments has been performed on the real world twitter dataset that alter to show the effectiveness of the proposed framework. This research effort also highlighted the recent challenges in the field of sentiment analysis along with the future scope of the proposed work.

• 아태비즈니스연구
• /
• 제14권3호
• /
• pp.67-88
• /
• 2023

Purpose - This study examined the effect of empowering leadership on adaptive performance and verified the mediating effect of job challenge in the relationship between empowering leadership and adaptive performance. Additionally, this study investigated the moderating effect of agentic and communal traits in the relationship between supervisor's empowering leadership and adaptive performance of subordinates. Design/methodology/approach - This study used data collected from 279 participants via an online platform. Multiple regression analysis, bootstrapping, hierarchical regression analysis, and simple slope test were used to analyze the data. Findings - First, supervisor's empowering leadership had a positive effect on adaptive performance. Second, job challenge was found to mediate the relationship between supervisor's empowering leadership and adaptive performance. Third, the agentic trait showed a moderating effect on strengthening the relationship between supervisor's empowering leadership and adaptive performance. However, communal trait did not show a moderating effect. Research implications or Originality - This study examined the moderating effect of agentic traits in the relationship between empowering leadership and adaptive performance, which has not been investigated before.

• 한국의류학회지
• /
• 제48권1호
• /
• pp.50-65
• /
• 2024

By analyzing the style of creator avatars in the world of Metaverse, which is emerging as a fourth-generation social media platform, this study aims to identify the meta-fashion tastes of Generation Z (Gen Z) creators (born in the late 2010s and early 2020s) and to analyze the extent to which current trends in the fashion market are influencing meta-fashion. The research method uses a case study to compare meta-fashion and current fashion trends. First, five Gen Z fashion creators on ZEPETO were selected to analyze the meta-fashion styles presented by this group. In the end, a total of 100 fashion styles were analyzed by combining 50 items each from the current meta-fashion and real fashion trends. The fashion styles were found to be hip-hop, easy-casual, punk, lovely feminine, and sexy, and the main fashion items were analyzed as jeans, hip-hop style pants, sneakers, tight crop tops, dresses, tattoos, chain accessories, and dyeing. Meta-fashion is the emergence of items similar in shape to those popular in the current fashion market, but are more exaggerated or show off the human body than actual fashion items.

• 한국컴퓨터정보학회논문지
• /
• 제29권4호
• /
• pp.9-21
• /
• 2024

최근 딥러닝 분야가 빠르게 발전하는 가운데, 다양한 영역에서 거대 언어 모델을 활용하기 위한 많은 연구들이 진행되고 있다. 하지만 언어 모델의 개발 및 활용을 위해서는 방대한 데이터와 고성능 자원이 필요하다는 현실적인 어려움이 존재한다. 이에 따라 프롬프트를 활용하여 언어 모델을 효율적으로 학습할 수 있는 문맥 내 학습이 등장하였지만, 학습에 효과적인 프롬프트가 무엇인지에 대한 명확한 기준은 구체적으로 제시되지 않았다. 이에 본 연구에서는 문맥 내 학습 방법 중 하나인 PET 기법을 활용하여 기존 데이터의 문맥과 유사한 PVP를 선정하고, 이를 통해 생성한 프롬프트를 학습하여 모델의 성능을 향상시킬 수 있는 프롬프트 기반 학습 성능 향상 방법론을 제안한다. 제안 방법론의 성능 평가를 위해 온라인 비즈니스 리뷰 플랫폼인 Yelp에서 수집된 레스토랑 리뷰 데이터 30,100개로 실험을 수행한 결과, 제안 방법론이 기존의 PET 방법론에 비해 정확도와 안정성, 그리고 학습 효율성의 모든 측면에서 우수한 성능을 보임을 확인하였다.