• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• 패션비즈니스
• /
• 제27권4호
• /
• pp.141-162
• /
• 2023

With the prospect that integrating creative AI in the fashion design field will become more visible, this study considered the case of creative fashion design development through Human-AI Co-creation (HAIC). Methodologically, this research encompasses a literature review and empirical investigations. In the literature review, the fashion design and creative HAIC processes, and the possibilities of integrating AI in fashion design were considered. In the empirical study, based on the case analysis of generating fashion design through HAIC, the HAIC type according to the role and interaction method, and characteristics of humans and AI was considered, and the HAIC process for fashion design was derived. The results of this study are summarized as follows. First, HAIC types in fashion design are divided into four types: AI-driven passive HAIC, human-driven passive HAIC, flexible interaction-based HAIC, and integrated interaction-based value creation HAIC. Second, the stages of the HAIC process for creative fashion design can be broadly divided into semantic data integration, visual ideation, design creation and expansion, design presentation, and design/manufacturing solution and UX platform creation. Third, in fashion design, HAIC contributes to human ability, enhancement of creativity, achievement of efficient workflow, and creation of new values. This research suggests that HAIC has the potential to revolutionize the fashion design industry by facilitating collaboration between humans and AI; consequently, enhancing creativity, and improving the efficiency of the design process. It also offers a framework for understanding the different types of HAIC and the stages involved in the creative fashion design process.

• 한국지구과학회지
• /
• 제44권4호
• /
• pp.331-341
• /
• 2023

The goal of this study was to examine the PCK required for science teachers and PCK required for university teacher educators in terms of school science knowledge, science teaching and learning, and the role of science educators, which are the main axes of science education in future schools, and to explore the relationship between them. This study is a follow-up to a previous stage of research that explored the prospects for changes in schools in the future (2040-2050) in terms of school knowledge, educational methods, and teacher roles. Based on in-depth interviews, qualitative and semantic network analyses were conducted to derive and compare the characteristics of PCK and PCK. As for the main research results, science teacher PCK in future schools should include expertise in organizing science classes centered on convergence topics, expertise in digital platforms and ICT use, and expertise in building a network of learning communities and resources, as part of the expertise of human teachers differentiated from AI. Teacher educators' PCK includes expertise in the research and development of T-L methods using AI, expertise in the knowledge construction process and practice, and expertise in developing preservice teachers' research competencies. Discussed in the conclusion is the change in teacher PCK and teacher educator PCK with changes in science knowledge, such as convergence-type knowledge and cognition-value integrated knowledge; and the need to emphasize values, attitudes, and ethical judgments for the coexistence of humans and non-humans as school science knowledge in the post-humanism future society.

• 문화기술의 융합
• /
• 제9권1호
• /
• pp.463-469
• /
• 2023

본 연구의 목적은 신규간호사가 경험하는 현실충격 관련 연구를 텍스트 네트워크 분석을 통해 분석함으로써 신규간호사의 성공적인 임상적응과 이직률 감소에 기여할 수 있는 기초자료를 제공하기 위함이다. 2002년 1월부터 2021년 12월까지 국내외 학술지에 게재된 115편의 논문에서 신규간호사가 경험한 현실충격에 관한 토픽을 추출하였다. 6개의 데이터베이스(국내: DBpia, KISS, RISS / 해외: Web of science, Springer, Scopus)에서 문헌을 검색하였다. 키워드는 문헌의 초록에서 추출되었고 의미론적 형태소를 사용하여 정리되었다. 네트워크분석 및 토픽모델링은 NetMiner 4.5 프로그램을 사용하여 수행되었다. 핵심 키워드는 '신규간호사', '현실충격', '전환', '학생간호사', '경험', '실습', '근무환경', '역할', '돌봄', '교육' 등으로 확인되었다. 최근 신규간호사의 현실충격에 관한 연구에서 잠재적 디리클레 할당(LDA) 기법으로 '이직', '근무환경', '전환 경험'의 세 가지 주요 주제를 추출하였다. 본 연구결과를 바탕으로 신규호사가 경험하는 현실충격을 효과적으로 감소시키고 성공적으로 임상적응을 도울 수 있는 중재 연구의 필요성을 제언한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• 한국간호교육학회지
• /
• 제30권2호
• /
• pp.149-159
• /
• 2024

Purpose: The aim of this study was to identify core keywords and topic groups in the "adolescent pregnancy" field of research for a better understanding of research trends in the past 10 years. Methods: Topics related to adolescent pregnancy were extracted from 3,819 articles that were published in journals between January 2013 and July 2023. Abstracts were retrieved from five databases (MEDLINE, CINAHL, Embase, RISS, and KISS). Keywords were extracted from the abstracts and cleaned using semantic morphemes. Text network analysis and topic modeling were performed using NetMiner 4.3.3. Results: The most important keywords were "health," "woman," "risk," "group," "girl," "school," "service," "family," "program," and "contraception." Five topic groups were identified through topic modeling. Through the topic modeling analysis, five themes were derived: "health service," "community program for school girls," "risks for adult women," "relationship risks," and "sexual contraceptive knowledge." Conclusion: This study utilized text network analysis and topic modeling to analyze keywords from abstracts of research conducted over the past decade on adolescent pregnancy. Given that adolescent pregnancy leads to physical, mental, social, and economic issues, it is imperative to provide integrated intervention programs, including prenatal/postnatal care, psychological services, proper contraception methods, and sex education, through school and community partnerships, as well as related research studies. Nurses can play a vital role by actively engaging in prevention efforts and directly supporting and educating socially disadvantaged adolescent mothers, which could significantly contribute to improving their quality of life.

• 한국도서관정보학회지
• /
• 제55권2호
• /
• pp.109-132
• /
• 2024

서지환경이 링크드 데이터, 시맨틱웹 기반으로 전환됨에 따라 국내에서도 RDA를 기반으로 한 KCR5 개정 작업을 진행 중에 있다. 변화하는 서지환경에서도 전거형 접근점은 자원의 식별 및 자원 간의 연계에 중요한 역할을 하고 있으나, KCR5가 준용하는 원본 RDA는 모든 개체에 대한 전거형 접근점이 마련되지 않은 상황이다. 이에 본 연구에서는 RDA 2020의 구현형의 전거형 접근점 분석을 토대로 국내 서지환경 및 원본 RDA에 적용 가능한 구현형의 전거형 접근점의 속성을 선정하고 연계 구조를 제안하였다. 구현형의 전거형 접근점은 지적 측면과 물리적 측면을 모두 고려한 접근점으로, 실제 자원의 연계와 식별이 더욱 원활해지는 토대를 마련할 수 있다. 또한 국내 서지환경에 적합한 구현형의 전거레코드 연계 구조 구성은 향후 구현형의 전거형 접근점의 실제적인 적용에 도움이 될 것으로 기대된다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제30권3호
• /
• pp.109-123
• /
• 2024

딥러닝과 강화학습을 활용한 비전 기반 엔드투엔드 자율주행 시스템 관련 연구가 지속적으로 증가하고 있다. 일반적으로 이러한 시스템은 위치, 속도, 방향, 센서 데이터 등 연속적이고 고차원적인 차량의 상태를 잠재 특징 벡터로 인코딩하고, 이를 차량의 주행 정책으로 디코딩하는 두 단계로 구성된다. 도심 주행과 같이 다양하고 복잡한 환경에서는 Variational Autoencoder(VAE)나 Convolutional Neural Network(CNN)과 같은 네트워크를 이용한 효율적인 상태 표현 방법의 필요성이 더욱 부각된다. 본 논문은 차량의 이미지 상태 표현이 강화학습 성능에 미치는 영향을 분석하였다. CARLA 시뮬레이터 환경에서 실험을 수행하였고, 차량의 전방 카메라 센서로부터 취득한 RGB 이미지 및 Semantic Segmented 이미지를 각각 VAE와 Vision Transformer(ViT) 네트워크로 특징 추출하여 상태 표현 학습에 활용하였다. 이러한 방법론이 강화학습에 미치는 영향을 실험하여, 데이터 유형과 상태 표현 기법이 자율주행의 학습 효율성과 결정 능력 향상에 어떤 역할을 하는지를 실험하였다.

• 모자간호학회지
• /
• 제2권1호
• /
• pp.5-20
• /
• 1992

This study was undertaken to identify the levels and affecting factors of the maternal role attainment(MRA) in the primipara during the postpartum period. The healthy ninety primiparous from the one university hospital and two local clinics in KwangJu city were selected and two Semantic Differential Scales (SD-Myself as Mothers, SD-My Baby) and the Pharis Self Confidence Scale were used in this study. Questionnaires were distributed at the 3rd days and the 4-6 weeks of the primiparous not showing any complication after normal delivery. The data collected were analysed statistically using t-test, Pearson's Product Moment Correlation Coefficient and ANOVA. The results obtained were summarized as follows; 1) On the 3rd day after the delivery, the scores of SD-myself as mother, SD-baby and Pharis Self Confidence were 70.6 points, 73.6 points and 78.6 points, respectively, showing the low level of MRA. 2) On the 4-6 weeks after delivery, the score of SD-myself as mother, SD-baby and Pharis Self Confidence were 72.8 points, 77.9 points, and 86.9 points, respectively, indicating the moderate level of MRA. 3) The mean scores of the SD scale and the Pharis Self Confidence during the postpartum periods were higher than those of the 3rd days, showing the SD-myself as mother (t=-2.09, P<.05), SD-baby(t=-4.12, P<.001), Pharis Self Confidence(t=-6.59, P<.001), respectively. 4) Positive correlations (r=.24$\sim$.69) were shown in the concepts related to the MRA and the cognitive-motor skill components and cognitive-affective skill components of the MRA became harmonious over time. 5) The relationships between the score of the MRA and the demographic and obstetric variables were as follows ; a) the score of the MRA in the twenties was higher than those of the thirties. b) the group with higher educational background showed higher MRA socres than the group with lower one. c) those who wanted pregnancy sustenance had higher MRA scores than those who did not. d) the group that did think of festus-feature represented higher MRA scores than those who did not. e) the group of mothers who have the daughters showed higher MRA scores than those who have boys. It can be concluded from the results that the MRA in the primiparous increased gradually, and that the cognitive-motor skills and cognitive-affective skills became harmonious over time. The level of the MRA was affected partly by the mothers general, obstetrical variables. Following suggestion were made oil the basis of the present study ; a) The longitudinal study on the MRA is needed. b) Multivariate analyses should be done for the identification of the factors influcening on the MRA. c) Education program for primiparous mother should be designed and developed to improve the MRA.

• Spatial Information Research
• /
• 제22권6호
• /
• pp.55-65
• /
• 2014

본 논문은 조경설계를 위한 창의적 개념화를 지향하는 공간 의사 결정 시스템 모델에 대한 연구이다. (1)정보의 폭발 및 무시 (2)원칙성과 융통성의 딜레마 (3)비구조화된 성격의 계획 및 설계라는 세가지 특징 때문에, 현재 정보중심의 GIS는 큰 역할을 못하고 있다. 이에 현재의 정보중심의 GIS에 대한 대안으로 공간 개념화를 지향하는 SDSS(공간의 사결정지원시스템)모델을 제시하고자 한다. 미래의 공간 개념화 지향의 SDSS는 인지적 관점을 기반으로 한 공간개념화를 현재의 GIS기술과 연계시킴으로써 조경설계의 비구조적인 문제를 효율적이고, 창조적으로 해결할 수 있다. 공간개념화 지향의 SDSS 모델은 (1)인간정보처리 (2)도구 및 이론의 상호작용 (3)인지과학 및 실천인식론 (4)의사결정지원 시스템 (5)인간과 컴퓨터의 상호작용 (6)창조적인 사고라는 핵심이론 및 기술을 반영한다. 향후 구현될 공간 개념화 지향의 SDSS는 설계자가 공간계획 및 설계상에서 "숨겨진 조직"을 파악할 수 있게 하고, 생성 및 개념화 능력을 통해 새로운 아이디어를 개발하고 이를 다른 설계자와 공유할 수 있게 한다. 공간개념화는 (1)버블다이어그램 지향의 설계지원 시스템 (2)어의적 기억의 확장으로서의 프로토타입 (3)삽화적 기억의 확장으로서 스크립트라는 세 가지 핵심 아이디어를 통해 공간 설계의 개념화를 보다 용이하게 할 수 있다. 앞으로 이 세 가지 아이디어는 계획 및 설계를 위한 GIS기술의 미래 방향을 제시할 수 있을 것이다.