• Journal of Platform Technology
• /
• v.10 no.1
• /
• pp.20-28
• /
• 2022

Artificial intelligence-based health data verification has become an essential element not only to help clinical research, but also to develop new treatments. Since the US Food and Drug Administration (FDA) approved the marketing of medical devices that detect mild abnormal diabetic retinopathy in adult diabetic patients using artificial intelligence in the field of medical diagnosis, tests using artificial intelligence have been increasing. In this study, an artificial intelligence model based on image classification was created using a Teachable Machine supported by Google, and a predictive model was completed through learning. This not only facilitates the early detection of cataracts among eye diseases occurring among patients with chronic diseases, but also serves as basic research for developing a digital personal health healthcare app for eye disease prevention as a healthcare program for eye health.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.591-592
• /
• 2013

현재 사회는 건강에 대한 관심이 크게 증가하고 있으며, 전문적인 건강관리 서비스를 받기 위해서 사용자의 상태 및 상황을 정확히 알 수 있도록 사용자 행위인지 관련 연구가 활발히 진행되고 있다. 기존의 행위인지 연구에서 사용하는 각종 웨어러블 센서는 일상생활의 불편 및 비용 문제를 야기하여, 본 연구에서는 센서 디바이스로 스마트폰을 사용한다. 기존의 행위인지 연구는 특정 실험군 이외의 제3자에 의한 실험에서는 정확도에 큰 차이를 보이며, 인지 오류에 대한 실시간 수정이 불가능하였다. 본 논문에서는 프롬프트 방식을 통해 실시간으로 사용자의 인지 오류를 피드백하고, 클라우드 시스템에서 실시간으로 재트레이닝을 통한 수정된 행위 모델을 생성하여 지속적으로 행위의 오류를 줄이며, 각각의 사용자에 맞는 건강관련 서비스를 추천하는 방안을 제안하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.505-507
• /
• 2020

본 연구에서는 헬스장에서 지속적인 운동 관리를 할 수 있도록 동기를 부여하는 가상화폐 기반 스마트 건강관리 시스템을 제안하였다. 인공지능 및 블록체인 기술을 적용하여, 운동기구로부터 측정된 운동량 데이터와 얼굴인식을 통해 인식된 사용자 정보가 자동으로 클라우드 서버에 전송되고, 운동량에 기반하여 가상화폐를 생성하고 거래할 수 있다. 미니어처 모델을 통한 실험 결과는 가상화폐를 이용한 건강관리 시스템이 실제 헬스장에 성공적으로 적용될 수 있는 가능성을 보여준다.

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2003.11a
• /
• pp.394-395
• /
• 2003

대기 중의 황산염 입자는 인체 건강에 좋지 않은 영향을 미칠 뿐 아니라, 지구에 유입되는 빛을 산란시키고 구름을 생성하는 핵으로 작용함으로서 직ㆍ간접적으로 햇빛을 차단하여 전지구적 기후 변화에 상당한 역할을 하는 것으로 알려져 있다. 황산염 입자는 대기 중 SO$_2$의 산화에 의해 주로 생성되는데, 지금까지의 대기 모델을 활용한 연구에 의하면 대기 중의 SO$_2$의 양에 비해 황산염의 양은 과소 평가되고 있다. 이는 대기 중 황산염의 생성에 대한 대기 화학 반응기전이 제대로 파악되지 않아서 global scale의 예측이 불확실하기 때문이다. (중략)

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.277-286
• /
• 2020

This study aimed to examine bone health awareness and knowledge and the bone mass-improving behaviors of female nursing college students. The subjects were 172 nursing students attending nursing colleges. The data were collected from March 16 to April 4, 2020, by using bone health awareness, bone health knowledge, and bone mass-promoting behavior assessment tools. Descriptive statistics are presented, and t-tests, ANOVA, Pearson's correlation, and multi-regressions were used for data analysis. Students' bone health awareness was 1.79, bone health knowledge was 8.86, and bone mass-promoting behavior level was 2.78. There were significant negative correlations between bone mass-promoting behavior level and age of menarche (r = 0.21, p = .004) and sun exposure (r = 0.44, p < .000). Also, bone mass-promoting behavior level and knowledge of bone health were negatively correlated (r = 0.21, p = .005). Regression analysis showed that knowledge of bone health (β = 0.21, p = .005), age of menarche (β = 0.20, p = .005), and sun exposure (β = 0.38, p < .000) were significant predictors of bone mass-promoting behaviors and their variance explanation power was 20.6%. Based on these results, education to improve knowledge of bone health will help to improve bone health and increase bone mass-promoting behaviors among young women.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.590-591
• /
• 2023

최근 사람들의 건강에 대한 관심이 많아지고 다양한 운동 컨텐츠가 확산되면서 실내에서 운동을 할 수 있는 기회가 많아졌다. 하지만, 전문가의 도움없이 정확하지 않은 동작을 수행하다 큰 부상을 입을 위험성이 높다. 본 연구는 CNN 기반 요가 자세 분류 모델을 생성하고 설명가능 인공지능 기술을 적용하여 예측 결과에 대한 해석을 제시한다. 사용자에게 설명성과 신뢰성 있는 모델을 제공하여 자신에게 맞게 올바른 자세를 결정할 수 있고, 무리한 동작으로 부상을 입을 확률 또한 낮출 수 있을 것으로 보인다.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.139-159
• /
• 2022

As interest in health functional foods has increased since COVID-19, the importance of imported food safety inspections is growing. However, in contrast to the annual increase in imports of health functional foods, the budget and manpower required for inspections for import and export are reaching their limit. Hence, the purpose of this study is to propose a machine learning model that efficiently detects unsuitable food suitable for the characteristics of data possessed by government offices on imported food. First, the components of food import/export inspections data that affect the judgment of nonconformity were examined and derived variables were newly created. Second, in order to select features for the machine learning, class imbalance and nonlinearity were considered when performing exploratory analysis on imported food-related data. Third, we try to compare the performance and interpretability of each model by applying various machine learning techniques. In particular, the ensemble model was the best, and it was confirmed that the derived variables and models proposed in this study can be helpful to the system used in import/export inspections.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.5
• /
• pp.61-72
• /
• 2019

The purpose of this study is to propose the clue of planning guideline for the elderly welfare center supporting the healthy life of the elderly through deriving the planning element of the elderly welfare center based on the Salutogenic Model(SM). The research method was proceeded with literature review. The meaning of Sense of Coherence(SOC) and Generalised Resistance Resources(GRR) which constitute Salutogenic Model is established. The correlation between SOC and GRR is analyzed. The conclusions of this study are as follows. First, EBD, BD, HD, UD, and BFD were studied as planning theories that could enhance the SOC of space. Second, based on the five planning theories, 43 planning elements needed for the elderly welfare center plan were derived. Third, as a result of classifying the plan elements based on the SOC, 'Manageability' is divided into 22 elements, 'Meaningfulness' is 11 and 'Comprehensibility' is 10 elements. Fourth, the details of the SOC items for each theory are as follows: BFD focuses on 'Manageability' with 'Manageability'(74%) and 'Comprehensibility'(26%), but 'Meaningfulness' does not exist. And UD regards 'Comprehensibility'(66%) as important, and 'Manageability' and 'Meaningfulness' as 17%. BD, on the other hand, has a high percentage of 'Meaningfulness'(70%), 'Comprehensibility'(21%) and 'Manageability'(9%). Next, the 'Manageability' of HD and EBD is 46%. And HD was 'Meaningfulness'(34%), 'Comprehensibility'(20%), and EBD was 'Meaningfulness'(30%) and 'Comprehensibility'(24%). The three items of SOC showed different distribution according to the spatial planning theory. As a result of the analysis, the spatial planning theory with the 'Comprehensibility' was related to Universal Design(UD), and the spatial planning theory with the 'Manageability' was related to Barrier-Free Design(BFD). In addition, the spatial planning theory of 'Meaningfulness' was related to Bio-philic Design(BD). Therefore, the plan of the elderly welfare center needs to approach the multidimensional design methodology to enhance the SOC(Sense of Coherence).

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.21-22
• /
• 2021

사람들이 체중을 조절하고 건강을 관리하기 위한 방법 중 하루 영양소 섭취량을 조절이 있다. 현대 사회에선 가공식품의 섭취량이 증가함에 따라 자연스레 가공식품들의 영양소를 파악하고 기록하는 것도 중요한 문제가 되었다. 본 논문에서는 실제 가공 식품의 포장지에 인쇄되어있는 영양성분 표 이미지를 인식할 수 있는 OCR을 FOTS 기반으로 구현 및 실험을 진행하였다. 실제로 시중에서 파는 영양성분 표는 한글과 영어가 섞여 있기 때문에 한글을 인식하는 모델과 영어와 숫자를 인식하는 모델을 따로 학습한 뒤 생성하여 각 언어에 대한 인식률을 향상시켰다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.185-188
• /
• 2017

Health promotion is essential for overcoming the low health longevity of senior citizens preparing for aging population. Therefore, the lower body strengthening exercise to prevent falls is crucial to prevent a fall in the number of deaths of senior citizens. In this game model, the elderly are aiming at home training contents that can be found to feel that the elderly are going out of walk and exercising in the natural environment. To achieve this, Kinect extracts a specific bone model provided by the Kinect Sensor to generate the feature vectors and recognizes the movements and motion of the user.