• 패션비즈니스
• /
• 제26권4호
• /
• pp.64-82
• /
• 2022

This study aimed to explore fashion technologies for small-scale designer brands and reveal the priorities of the derived fashion technologies. Interviews were conducted with owners of 15 designer brands to explore fashion technologies needed in the field based on the business operation stage (study 1), and an online survey of owners of 61 designer brands was conducted to verify their priorities (study 2). A total of 12 fashion technologies were derived from study 1, including 2 market analysis stages, 6 season planning stages, and 4 product operation stages. In study 2, importance and satisfaction were measured with 12 fashion techniques derived from study 1, and importance-performance analysis (IPA) was performed. The technologies of product management with image tagging and sales channel matching were considered to be the fashion technologies that should be developed first. Second, in the case of maintenance, demand prediction and price determination were applicable. Third, over-effort avoidance was revealed through market analysis and design generation. Finally, in automatic product detail page creation and digital marketing, development was the lowest priority. The results of this study are expected to provide insight into priority areas for fashion technology developers and policy departments providing emerging brand support.

• 인터넷정보학회논문지
• /
• 제24권1호
• /
• pp.49-59
• /
• 2023

COVID-19로 대표되는 팬데믹 상황에서 의료 인력 부족으로 인한 문제가 대두되고 있다. 본 논문에서는 진단 업무를 지원하기 위한 컴퓨터 비전 솔루션으로 PA 흉부 X-선 영상에 대한 병변 유무 진단 방법에 대해 제시한다. 디지털 영상에 대한 특징 비교 방식의 이상 탐지 기법을 X-선 영상에 적용하여 비정상적인 영역을 예측할 수 있다. 정렬된 PA 흉부 X-선 영상으로부터 특징 벡터를 추출하고 패치 단위로 분할하여 지역적으로 등장하는 비정상을 포착한다. 사전 실험으로 다중 객체를 포함하는 시뮬레이션 데이터 세트를 생성하고 이에 대한 비교 실험 결과를 제시한다. 정렬된 영상에 대해 적용 가능한 패치 특징 하드마스킹을 통해 프로세스의 효율성 및 성능을 향상하는 방법을 제시한다. 지역 특수성 및 전역 이상 탐지 결과를 합산하여 기존 연구 대비 6.9%p AUROC 향상된 성능을 보인다.

• 한국간호교육학회지
• /
• 제28권4호
• /
• pp.444-455
• /
• 2022

Purpose: This study explored the meaning of the social perceptions of nurses in online news articles during the coronavirus disease 2019 (COVID-19) pandemic. Methods: A total of 339 nurse-related articles published in Korean online newspapers from January 1 to December 31, 2020, were extracted by entering various combinations of OR and AND with the four words "Corona," "COVID," "Nursing," and "Nurse" as search keywords using BIGKinds, a news database provided by the Korea Press Foundation. The collected data were analyzed with a keyword network analysis and topic modeling using NetMiner 4. Results: The top keywords extracted from the nurse-related news articles were, in the following order, "metropolitan area," "protective clothing," "government," "task," and "admission." Four topics representing keywords were identified: "encouragement for dedicated nurses," "poor work environment," "front-line nurses working with obligation during the COVID-19 pandemic," and "nurses' efforts to prevent the spread of COVID-19." Conclusion: The media's attention to the dedication of nurses, the shortage of nursing resources, and the need for government support is encouraging in that it forms the public opinion necessary to lead to substantial improvements in treating nurses. The nursing community should actively promote policy proposals to improve treatment toward nurses by utilizing the net function of the media and proactively seek and apply strategies to improve the image of nurses working in various fields.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.249-251
• /
• 2022

본 연구에서는 뇌파를 이용하여 드론을 제어하기 위한 기계학습을 논의한다. 드론의 이륙과 전진, 후진, 좌측 이동 그리고 우측 이동을 제어대상으로 정의하였고 이를 제어하기 위한 뇌파의 신호를 전두엽을 대상으로 하는 Fp1·Fp2 2채널 건식 전극(NeuroNicle FX2) 뇌파 측정장비를 통하여 5.19초동안 각 제어대상과 연관된 행동의 운동 심상을 눈을 뜬 상태에서 측정(Sampling Rate 250Hz, Cutoff Frequency 6~20Hz) 하였다. 측정된 뇌파신호에 대해 매틀랩의 분류학습기를 이용해서 삼중 계층 신경망, 로지스틱 회귀커널, 비선형 3차 SVM 학습을 실시하였으며 학습결과 로지스틱 회귀 커널 학습에서 드론의 이륙과 전진, 후진, 좌측 이동 그리고 우측 이동을 위한 가장 높은 정확도를 가지고 있음을 클래스 참양성률로 확인할 수 있었다.

• 여성건강간호학회지
• /
• 제28권1호
• /
• pp.8-17
• /
• 2022

Purpose: Although the term "transition to motherhood" is commonly used in research, the concept is not clear. This study, hence, was conducted to clarify the concept of "transition to motherhood." Methods: The concept analysis framework developed by Walker and Avant is used to analyze the concept of transition to motherhood. Results: Transition to motherhood is defined as the physical, psychological, social, and relational (mother-baby relationship/interpersonal relationship) changes that happen to a woman after pregnancy and delivery of a baby. The attributes of the transition to motherhood include: 1) adapting to physical changes after pregnancy and childbirth; 2) experiencing various psychological changes; 3) changing of her social perception from being a woman to someone's mother; and 4) forming and developing a relationship with the newborn, adjusting priorities, and redefining the relationship between family and others. Meeting the newborn is regarded as an antecedent of the transition to motherhood. Redefining identity and physical image, ensuring mother's well-being, maternal attachment, and confidence in the maternal role are regarded as consequences of the transition to motherhood. The concept was clarified by the presentation of model, borderline, and contrary cases. Conclusion: The significance of this study lies in the clarification of the concept of transition to motherhood and defining its attributes. It is recommended that tools be developed to measure transition to motherhood based on the results of this study. Furthermore, nurses and midwives can use study findings to better understand the concept of transition to motherhood in providing care and support to mothers who experience it.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권12호
• /
• pp.947-954
• /
• 2017

초고층 빌딩, 복합상가, 대형 지하시설물 등과 같은 도시 대형 구조물에서 화재가 발생한 경우에는 거주자들에 대하여 신속한 긴급피난유도를 제공해야 인명피해를 최소화할 수 있다. 따라서 대형 화재가 발생한 경우에 긴급피난유도를 제공하는 것이 필수적이다. 이러한 긴급피난유도를 효과적으로 지원하기 위해서는 화재발생 위치, 거주자 위치, 탈출경로 등과 같은 주요 항목들을 파악하는 것도 중요하지만, 거주자들이 화재로부터 안전하게 대피할 수 있는 피난구역을 신속하게 파악하는 것이 무엇보다도 중요하다. 본 논문에서는 안전한 피난대피구역 파악을 위하여 CCTV 영상을 분석하여 화재 발생에 따른 연기로부터 피난구역의 가시도를 측정하는 방법을 제안한다. 이를 위하여 먼저 연기로 인한 특정 구역의 가시도 측정을 위하여, 연기가 발생하고 있는 영상으로부터 배경 영상을 추출한다. 그리고 추출된 배경 영상에 대하여 에지를 추출한 영상을 생성한 후에, 연기로 인한 에지 강도의 변화를 계산하여 가시도를 측정한다.

• Journal of Animal Science and Technology
• /
• 제65권3호
• /
• pp.519-534
• /
• 2023

Rumination in cattle is closely related to their health, which makes the automatic monitoring of rumination an important part of smart pasture operations. However, manual monitoring of cattle rumination is laborious and wearable sensors are often harmful to animals. Thus, we propose a computer vision-based method to automatically identify multi-object cattle rumination, and to calculate the rumination time and number of chews for each cow. The heads of the cattle in the video were initially tracked with a multi-object tracking algorithm, which combined the You Only Look Once (YOLO) algorithm with the kernelized correlation filter (KCF). Images of the head of each cow were saved at a fixed size, and numbered. Then, a rumination recognition algorithm was constructed with parameters obtained using the frame difference method, and rumination time and number of chews were calculated. The rumination recognition algorithm was used to analyze the head image of each cow to automatically detect multi-object cattle rumination. To verify the feasibility of this method, the algorithm was tested on multi-object cattle rumination videos, and the results were compared with the results produced by human observation. The experimental results showed that the average error in rumination time was 5.902% and the average error in the number of chews was 8.126%. The rumination identification and calculation of rumination information only need to be performed by computers automatically with no manual intervention. It could provide a new contactless rumination identification method for multi-cattle, which provided technical support for smart pasture.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.434-436
• /
• 2021

의료산업은 진단 및 치료 위주의 기술개발이 진행되어왔다. 최근 의료 빅데이터를 기반으로 진단, 치료 및 재활뿐만 아니라 예방과 예후관리까지 지원하는 의료서비스에 대한 패러다임이 변화되고 있다. 특히, 여러 의료 중심의 플랫폼 기술 가운데 객관적인 진단지표를 가지고 있는 의료영상을 기반으로 인공지능 학습에 적용하여 진단 및 예측을 중심으로 한 플랫폼 개발이 진행되고 있다. 하지만, 인공지능 연구에는 많은 학습 데이터가 요구될 뿐만 아니라 학습에 적용하기 위해서는 데이터 특성에 따른 전처리 기술과 분류 작업에 많은 시간 소요되어 이와 같은 문제점을 해결할 수 있는 방법들이 요구되고 있다. 따라서, 본 논문은 인공지능 학습까지 적용하기 위한 의료영상 데이터에 대한 확장 모델을 개발하여 공통적인 조건에 따라 의료영상 데이터가 표준화되어 변환하며, 자동화 시스템 구조에 따라 데이터가 분류·저장되어 인공지능 학습까지 지원할 수 있는 플랫폼을 제안하고자 한다. 그리고 근감소증 학습데이터 관리 및 적용 결과를 통해 플랫폼의 수행성을 검증하였다. 향후 제안한 플랫폼을 통해 의료데이터에 대한 전처리, 분류, 관리까지 지원함으로써 CDM 확장 표준 의료데이터 플랫폼으로 활용 가능성을 보였다.

• 분석과 대안
• /
• 제1권2호
• /
• pp.13-30
• /
• 2017

Referred to as a 'media war,' there is a fierce competition for media discourse between different countries. Twenty four hour global news channels like Al Jazeera, France 24, RT, NHK World, China's CCTV and teleSUR emerged to offer their own perspectives and stance in the global society, and to face the monopolization and distorted information created by the hegemony of English news channels which have swayed international public opinions for a long time. As a tool of public diplomacy, the media's role in determining the image of the nation and winning the 'Hearts and Minds' of the international community is decisive, but it cannot be said that they all have a similar influence or play a positive role in media diplomacy. A global news channel, which is both a media diplomatic subject and a journalism organization, can be in the position of acting as a public relations organization or a propaganda agency for the government depending on the regime's attitude because most of global news channels receive support from the government. Sometimes it is difficult for these media to implement quality journalism because of financial difficulties. Media discourse also has limitations in that it is dependent upon changes in foreign policy of its own government. This study examines the current status of global news channels, the dilemma these channels are facing, and suggests some potential directions that can be taken by global news channels in order to become more effective. It is becoming increasingly important for all nations to respond to distorted information about their own countries, to appropriately identify various issues and changes in the international community and to convey their views and positions to the international community. For now, there is a lack of awareness about the importance of media diplomacy in Korea: There are many English-language media, but as yet no global news channel which could have an influence on the international stage. However, there seems to be some understanding about the need for the media to present the Korean alternative discourse to the senseless dependency on Western media. We hope that this study will be an opportunity to think in depth about the attitude of the Korean global media, whether existing global media or new global news channels, in order to help them become more effective in media diplomacy.

• 대한원격탐사학회지
• /
• 제39권5_1호
• /
• pp.507-519
• /
• 2023

Multi-temporal optical images have been utilized for time-series monitoring of croplands. However, the presence of clouds imposes limitations on image availability, often requiring a cloud removal procedure. This study assesses the applicability of various machine learning algorithms for effective cloud removal in optical imagery. We conducted comparative experiments by focusing on two key variables that significantly influence the predictive performance of machine learning algorithms: (1) land-cover types of training data and (2) temporal variability of land-cover types. Three machine learning algorithms, including Gaussian process regression (GPR), support vector machine (SVM), and random forest (RF), were employed for the experiments using simulated cloudy images in paddy fields of Gunsan. GPR and SVM exhibited superior prediction accuracy when the training data had the same land-cover types as the cloud region, and GPR showed the best stability with respect to sampling fluctuations. In addition, RF was the least affected by the land-cover types and temporal variations of training data. These results indicate that GPR is recommended when the land-cover type and spectral characteristics of the training data are the same as those of the cloud region. On the other hand, RF should be applied when it is difficult to obtain training data with the same land-cover types as the cloud region. Therefore, the land-cover types in cloud areas should be taken into account for extracting informative training data along with selecting the optimal machine learning algorithm.