• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.301-302
• /
• 2021

After the Korona 19, "social distancing" was implemented, existing "pop culture" or entertainment programs were unable to communicate in both directions and declined. Since then, "Untact content" has shown its potential to grow due to untouch performances such as BTS' "Bangbangcon" and the rapid growth of Netflix, a global OTT (online video service). In addition, most of the global and Untact content is online and digital, which means a huge amount of big data will be poured out. Therefore, analyzing the big data poured out during the distribution of untact content will help us identify consumers' needs, and the growth expectations will also be high. Therefore, we would like to explore the research cases that have been conducted in existing studies regarding the subject of the study and analyze how big data can affect the distribution of content in the Untact era.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.66.2-66.2
• /
• 2019

구술채록은 특정 주제의 연구사 기록화 작업에 있어 후대에 생생한 역사체험을 전승할 수 있는 최적의 연구사업이다. 특히 국내 천문우주과학 분야의 원로들이 대부분 연로하다는 점에서 한국천문학 발전사에 대한 구술채록은 시급성이 더욱 요구되고 있다. 이에 한국천문연구원 고천문연구센터는 그간 기관에서 자체적으로 수행해 온 사료분류체계 수립작업과 단발적인 구술채록 경험을 기반으로 본격적인 구술채록 연구사업을 수행할 계획이다. 이 연구는 한국천문학 발전사 구술채록 사업의 절차적 방법에 대한 기획론이다. 크게 (1)구술채록 로드맵 수립, (2) 구술기록 생산 프로세스, (3) 산출물 관리 및 활용으로 제시하고자 한다. 먼저 구술채록 로드맵 수립에 있어서는 현대 한국천문학 발전의 태동기 1950년대 중반을 기점으로 역사연구 및 주제분류를 중심으로 천문학 구술기록 특성화를 기한다. 이를 기반으로 구술대상자를 선정하고 큰 맥락의 역사와 개인 생애사를 교차하는 분석 틀을 중심으로 인터뷰 질문지를 추출한다. 이 과정에서 구술대상자의 소장 사료를 도출하여 미리 잠재적 사료 수집을 도모하도록 한다. 둘째, 본격적 구술기록 생산 프로세스에서는 전 단계에서 이행한 수집정보를 바탕으로 구술 산출물을 제작한다. 면담일지, 상세녹취록, 요약본, 이용동의서 등 기타 필요한 구술 제반 서식을 바탕으로 구술 동영상을 산출하고 라벨링한다. 이 산출물에 대한 사실관계 검증 후 최종 산출물 완성 및 기타 행정 처리로 제작은 종료된다. 마지막으로 산출물 관리 및 활용에 있어서는 사료 수집 전략의 기반 자료와 다양한 지식정보콘텐츠의 활용체계를 수립한다. 더 나아가 향후 이 연구사업은 구술DB화와 서비스 체계화를 위하여 구술아카이브 시스템을 설계하는 데 성과물을 활용한다. 이 연구기획론은 한국천문학이라는 특정 주제에 대한 것이므로 큰 틀에서의 방법은 기록학적 전개방식을 차용하지만, 역사연구와 기록의 특성화에 있어서는 한국천문학 연구사에 대한 깊은 이해가 동반되어야 한다. 따라서 광범위한 한국천문학 네트워크에 해당하는 다양한 학회, 교육기관, 연구기관 및 각종 사단법인 등의 역사와도 긴밀히 연결되어야 성과물은 비로소 가치 있고 풍부할 것이다. 이 연구를 시발점으로 향후 한국천문학 발전사 구술채록 사업에 대한 다양한 관학연구의 인식 공감대가 마련되기를 기대한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.383-383
• /
• 2020

한반도를 비롯한 전 세계를 대상으로 가뭄과 홍수 등 물관련 재해정보를 체계적으로 수집·분석하고 이를 정부부처 및 민간에서도 제공 가능한 국가 차원의 과학적이고 효율적인 수재해 대응 및 관리 위하여 현재 수재해 정보플랫폼 융합기술 연구단이 2014년 7월 1일 출범하여 수행중에 있다. 정보플랫폼 융합기술 연구단은 국토관측센서(위성, 레이더, 지상관측자료) 기반 광역 및 지역 수재해 정보 허브 구축 및 운영기술 개발로 행복한 안심국토 및 물산업 강국 실현이라는 연구비전 아래, 고정밀 수문레이더 기반 도시홍수 관리기술, 가뭄/하천건천화 평가 및 예측 기술 개발, 홍수재해 평가 및 예측 기술 개발, 빅데이터기반 광역 및 지역 수자원정보 서비스 플랫폼 기술 개발이라는 4대 연구성과 목표로 X-Net 실증 테스트베드 구축을 통해 획득된 자료를 기반으로 수재해 감시·평가·예측 등에 필요한 관련 수문정보를 생성하고 있으며, 생성된 위성영상 및 수문레이더 등의 수문정보를 활용하여 미계측 유역에 대한 수자원 변동 감시 및 가뭄과 하천 건천화를 효율적으로 평가·예측함으로써 물안보 대응체계를 강화하기 위한 기술을 확보하고 있다. 또한 광역 및 국지 홍수 피해 범위와 규모 등을 평가·산정하고 정확히 예측함으로써 홍수재해를 저감할 수 있는 기술 개발을 추진하고 있으며, 최종적으로는 광역 및 지역 수문자료와 수재해 관련 분석정보를 체계적으로 관리하고 맞춤형 수재해 정보를 제공할 수 있는 수재해정보플랫폼 및 포털시스템을 개발 글로벌 물 정보 허브로써 기반을 조성해 나가고 있다. 이에 수재해 정보플랫폼 융합기술 연구단에서 개발하여 운영중에 있는 수재해 정보플랫폼의 고정밀 수문레이더 기반 도시홍수 관리시스템, 위성기반 가뭄 모니터링 시스템, 미계측 지역 수문정보 및 수자원 모니터링 시스템, 한국형 지표 수문정보 생성 시스템 개발현황 등 그간의 노력에 대해 소개하고자 한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.83-88
• /
• 2023

In this paper, we developed a workout and diet assistance application to meet the growing demand for workout and dietary support services due to the increase in the home training population. The application analyzes the user's workout posture in real-time through the camera and guides the correct posture using guiding lines and voice feedback. It also classifies the foods included in the captured photos, estimates the amount of each food, and calculates and provides nutritional information such as calories. Nutritional information calculations are executed on the server, which then transmits the results back to the application. Once received, this data is presented visually to the user. Additionally, workout results and nutritional information are saved and organized by date for users to review.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.159-170
• /
• 2023

It takes a lot of time and manpower to search for the missing. As part of the solution, a missing person search AI system was implemented using a YOLO-based model. In order to train object detection models, the model was learned by collecting recognition images (road fixation) of drone mobile objects from AI-Hub. Additional mountainous terrain datasets were also collected to evaluate performance in training datasets and other environments. In order to optimize the missing person search AI system, performance evaluation based on model size and hyperparameters and additional performance evaluation for concerns about overfitting were conducted. As a result of performance evaluation, it was confirmed that the YOLOv5-L model showed excellent performance, and the performance of the model was further improved by applying data augmentation techniques. Since then, the web service has been applied with the YOLOv5-L model that applies data augmentation techniques to increase the efficiency of searching for missing people.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.515-525
• /
• 2024

Dark patterns refer to intentionally deceptive design techniques used by online service providers to hide necessary information, preventing users from taking desired actions or luring them into unintended behaviors. In this study, we analyzed the prevalence of dark patterns such as banners, advertorials, pop-ups, and video ads, and their impact on users across the top 200 news websites worldwide. The research revealed that there is a minimal correlation between banner ads and user bounce rates or unique visitors. Consequently, the main screen moving banner and headline news screen moving banner were most frequently observed in South America, while the headline news screen fixed banner was most commonly observed in Asia. All other categories were predominantly observed in Europe, making European websites the most diverse and abundant in various dark patterns.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.141-147
• /
• 2024

Recently, there has been growing interest in personalized services tailored to an individual's preferences. This has led to ongoing research aimed at recognizing and leveraging an individual's personality traits. Among various methods for personality assessment, the OCEAN model stands out as a prominent approach. In utilizing OCEAN for personality recognition, a multi modal artificial intelligence model that incorporates linguistic, paralinguistic, and non-linguistic information is often employed. This paper examines the impact of the margin value set for extracting facial areas from video data on the accuracy of a personality recognition model that uses facial expressions to determine OCEAN traits. The study employed personality recognition models based on 2D Patch Partition, R2plus1D, 3D Patch Partition, and Video Swin Transformer technologies. It was observed that setting the facial area extraction margin to 60 resulted in the highest 1-MAE performance, scoring at 0.9118. These findings indicate the importance of selecting an optimal margin value to maximize the efficiency of personality recognition models.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.67-74
• /
• 2024

As the number of coffee shops increases, many people are studying or working at coffee shops. Coffee shop operators have been required to analyze customer visits due to customer turnover and profit problems. Methods such as image analysis, QR code authentication, and Bluetooth beacon have been proposed for these statistics and analysis. However, it is difficult to use due to problems such as invasion of privacy and low accuracy. Therefore, in this study, to solve these problem and provide more accurate in-store congestion information, we propose a crowding measurement method of coffee shop using high frequency signal. There is an advantage in that a high frequency signal replaces the Bluetooth signal, and the transmission range of the signal is limited to the store, thereby increasing the accuracy of the method. To verify the performance of the proposed system, we conducted a comparative experiment with a Bluetooth based system, and as a result, the proposed method showed lower misrecognition rate. Thus, the proposed method will be an effective useful service for providing information on crowding at coffee shops and processing statistics.

• Industry Promotion Research
• /
• v.9 no.3
• /
• pp.155-161
• /
• 2024

This study investigates user experiences of reward-based mini-games, gamified elements within the domestic mobile commerce sector. Recently, gamification marketing strategies have been actively employed in mobile commerce services to attract customers, increase dwell time, and enhance revisit rates. Conducting research on user experiences of gamified elements, we quantified evaluations of how users perceive these elements within mobile commerce. Using enjoyment, immersion, rewards, value, and utility as criteria, we designed a questionnaire and conducted surveys, followed by 1:1 in-depth interviews with users aged 20 to 40. The experimental results highlight the need for strategies to increase user satisfaction in terms of enjoyment and immersion, as well as the necessity to enhance user experiences related to predictable reward systems and product exploration to facilitate product purchases. It is hoped that this study will provide insights for companies seeking to incorporate gamified elements into their marketing strategies and improve user experiences.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.25-34
• /
• 2024

This paper presents the development of a mobile application that detects and identifies canine skin diseases by training a deep learning-based U-Net model to infer the presence and location of skin lesions from images. U-Net, primarily used in medical imaging for image segmentation, is effective in distinguishing specific regions of an image in a polygonal form, making it suitable for identifying lesion areas in dogs. In this study, six major canine skin diseases were defined as classes, and the U-Net model was trained to differentiate among them. The model was then implemented in a mobile app, allowing users to perform lesion analysis and prediction through simple camera shots, with the results provided directly to the user. This enables pet owners to monitor the health of their pets and obtain information that aids in early diagnosis. By providing a quick and accurate diagnostic tool for pet health management through deep learning, this study emphasizes the significance of developing an easily accessible service for home use.