• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1738-1764
• /
• 2019

With the advent of big data, deep learning technology has become an important research direction in the field of machine learning, which has been widely applied in the image processing, natural language processing, speech recognition and online advertising and so on. This paper introduces deep learning techniques from various aspects, including common models of deep learning and their optimization methods, commonly used open source frameworks, existing problems and future research directions. Firstly, we introduce the applications of deep learning; Secondly, we introduce several common models of deep learning and optimization methods; Thirdly, we describe several common frameworks and platforms of deep learning; Finally, we introduce the latest acceleration technology of deep learning and highlight the future work of deep learning.

• 전자통신동향분석
• /
• 제37권5호
• /
• pp.54-61
• /
• 2022

Data are an essential resource for artificial intelligence-based services. It is considered a vital resource in the 4th industrial revolution era based on artificial intelligence. However, it is well-known that only a few giant platforms that provide most of the current online services tend to monopolize personal data. Therefore, some governments have started enforcing personal data protection and mobility regulations to address this problem. Additionally, there are some notable activities from a technical perspective, and Web 3.0 is one of these. Web 3.0 focuses on distributed architecture to protect people's data sovereignty. An important technical challenge of Web 3.0 is how to facilitate the personal data storage technology to provide valuable data for new data-based services while providing data for producers' sovereignty. This study reviews some currently proposed personal data storage technologies. Furthermore, we discuss the domestic countermeasures from MyData perspective, which is a typical project for data-based businesses in Korea.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권4호
• /
• pp.52-57
• /
• 2022

In this study, keywords from representative online portal sites such as Naver, Google, and Youtube were collected based on text mining analysis technique using Textom to check the changes in metqaverse after COVID-19. before Corona, it was confirmed that social media platforms such as Kakao Talk, Facebook, and Twitter were mentioned, and among the four metaverse, consumer awareness was still concentrated in the field of life logging. However, after Corona, keywords from Roblox, Fortnite, and Geppetto appeared, and keywords such as Universe, Space, Meta, and the world appeared, so Metaverse was recognized as a virtual world. As a result, it was confirmed that consumer perception changed from the life logging of Metaverse to the mirror world. Third, keywords such as cryptocurrency, cryptocurrency, coin, and exchange appeared before Corona, and the word frequency ranking for blockchain, which is an underlying technology, was high, but after Corona, the word frequency ranking fell significantly as mentioned above.

• 웰빙융합연구
• /
• 제6권1호
• /
• pp.33-36
• /
• 2023

Purpose: This study analyzed the perfume buying behavior of 561 men in their 20s and 30s. Research design, data and methodology: The demographic characteristics of the study subjects were analyzed frequently, the use of perfumes and chi-square tests were performed to identify differences in purchasing behavior, and the Likert 5-point scale was used to measure the importance of the reasons for choosing perfumes. Results: The most commonly used perfume product was Eau de Toilette, which had statistically significant differences with age and education (p<.05). Perfumes were most commonly purchased at health and beauty stores, with statistically significant differences by age, marital status, and education (p<.05). Conclusions: The study subjects have a high purchasing power for perfume products and are proficient in using smart devices, so they have a high level of information through beauty platforms, so they need to promote online products by introducing live commerce, etc.

• Journal of Information Science Theory and Practice
• /
• 제11권1호
• /
• pp.49-60
• /
• 2023

This study endeavors to answer four research questions: (a) Who are the celebrities? (b) How popular are they? (c) What do they post on social media platforms? (d) How do their followers react to them? Following quantitative methods, this study analyzes the top 195 Facebook celebrities of Bangladesh and their 9,441 Facebook posts' interactions. The result suggests that actors, music-related celebrities, and sports stars are the most popular celebrities. While male celebrities have a higher frequency, female celebrities have higher average followers than their male counterparts. Celebrities mostly share photos on Facebook, perhaps to recreate their public images and provide regular updates to their followers. The followers also engage the most in photos with affection and surprise reactions. Their reactions to celebrities' Facebook content are highly positive. Some strengths and limitations of this study are also discussed.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.101-109
• /
• 2023

This paper discusses the use of sentiment analysis and text summarization techniques to extract valuable information from the large volume of user-generated content such as reviews, comments, and feedback on online platforms and social media. The paper highlights the effectiveness of sentiment analysis in identifying positive and negative reviews and the importance of summarizing such text to facilitate comprehension and convey essential findings to readers. The proposed work focuses on summarizing all positive and negative reviews to enhance product quality, and the performance of the generated summaries is measured using ROUGE scores. The results show promising outcomes for the developed methods in summarizing user-generated content.

• International Journal of Advanced Culture Technology
• /
• 제11권2호
• /
• pp.109-117
• /
• 2023

Menstrual cycle irregularity reflects the reproductive health of women of childbearing age, but studies are scant on women in communities. In this study, we identified factors associated with menstrual cycle irregularity among 884 community women of childbearing age (19-40 years) and confirmed the relationship between menstrual cycle irregularity and depressive symptoms. Data were collected through online or mobile platforms. We noted that 25% of participants had menstrual cycle irregularity. Multivariable ordinal logistic regression analysis revealed that age, irregular eating, and depressive symptoms were associated with menstrual cycle irregularity. After adjusting for confounding variables, participants with depressive symptoms were at a slightly higher risk of menstrual cycle irregularity (odds ratio = 1.078, confidence interval = 1.021-1.139). Additional support be provided for community-living women of childbearing age with depressive symptoms, to improve their reproductive health

• 한국인공지능학회지
• /
• 제11권2호
• /
• pp.29-38
• /
• 2023

The purpose of this study is to explore how citizens perceive application of the metaverse platforms for city marketing and investigate factors that affect overall attitude for citizen relationship management in the public sector. In particular, this study investigates the following: i) how factors including perceived city brand value, public service, emotional value, experience, personalization, economic value, social value, and cultural value on overall attitude and ii) how overall attitude affects intention to use of metaverse for the public sector and citizen satisfaction. This study conducted an online survey with the assistance of a well-known research firm. This study applied factor, ANOVA, and regression analysis to test hypotheses. The results found that effects of perceived city brand value, emotional value, information, economic value, social value, and cultural value on overall attitude toward metaverse application for the public sector showed significance. The results provide managerial and policy implications for the public sector on how to apply metaverse to provide public services and enhance engagement with citizens. The results also provide implications which aspects should be considered to enhance citizen relationship management and to build the better city brand value by applying metaverse.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.458-460
• /
• 2023

가공식품이라는 특정 도메인에서는 기존 검색엔진에서 많이 활용되는 BM25 만을 가지고 최저가 검색하는 데는 어려움이 있다. 본 논문에서는 BM25 외에도 검색의 정확성을 높이기 위해 HuggingFace 에 공개되어 있는 KoELECTRA 를 활용하여 개체명 인식(Named Entity Recognition 과 이진 분류모델(Binary Classification)을 Fine-tuning 하고 BM25 와 연계하여 구축한 검색시스템을 제안한다. 기존의 BM25 대비 성능 평가를 통해 효과를 검증하였다.

• Asia pacific journal of information systems
• /
• 제34권1호
• /
• pp.114-149
• /
• 2024

Internet-only banks (IOB) refer to financial institutions which provide services entirely through online digital platforms without physical branches. Although IOBs have been around for over 26 years, there is still room for investigating what factors motivate customers to use them continuously and extensively. Therefore, this study aims to examine what factors lead to customers' intention of continued use and cross-buying on IOBs by extending the Post-Acceptance Model of IS Continuance (PAMISC). The result shows that perceived economic benefit and ongoing trust have significant relationships with the intention of continued use and that ongoing trust has significant direct and mediating (via intention of continued use) relationships with the intention of cross-buying. Also, personal innovativeness positively moderates the relationship between ongoing trust and the intention of cross-buying. This study sheds light on the literature on branchless financial services and PAMISC. IOB practitioners should revisit the effectiveness of customers' economic benefits to establish ongoing trust with customers.