딥러닝을 위한 마스크 착용 유형별 데이터셋 구축 및 검출 모델에 관한 연구

황호성,김동현,김호철 대한의용생체공학회 2022 의공학회지 Vol.43 No.3

Due to COVID-19, Correct method of wearing mask is important to prevent COVID-19 and the other respiratory tract infections. And the deep learning technology in the image processing has been developed. The pur- pose of this study is to create the type of mask wearing dataset for deep learning models and select the deep learning model to detect the wearing mask correctly. The Image dataset is the 2,296 images acquired using a web crawler. Deep learning classification models provided by tensorflow are used to validate the dataset. And Object detection deep learning model YOLOs are used to select the detection deep learning model to detect the wearing mask cor- rectly. In this process, this paper proposes to validate the type of mask wearing datasets and YOLOv5 is the effective model to detect the type of mask wearing. The experimental results show that reliable dataset is acquired and the YOLOv5 model effectively recognize type of mask wearing.

계절예측시스템(GloSea5) 가변적 과거재현자료를 활용한 예측 특성 분석

황호성,김중락,김강하,이희서 한국기상학회 2018 한국기상학회 학술대회 논문집 Vol.2018 No.4

CT 정도관리를 위한 인공지능 모델 적용에 관한 연구

황호성,김동현,김호철 대한의용생체공학회 2023 의공학회지 Vol.44 No.3

CT is a medical device that acquires medical images based on Attenuation coefficient of human organs related to X-rays. In addition, using this theory, it can acquire sagittal and coronal planes and 3D images of the human body. Then, CT is essential device for universal diagnostic test. But Exposure of CT scan is so high that it is regulated and managed with special medical equipment. As the special medical equipment, CT must implement quality control. In detail of quality control, Spatial resolution of existing phantom imaging tests, Contrast resolution and clinical image evaluation are qualitative tests. These tests are not objective, so the reliability of the CT undermine trust. Therefore, by applying an artificial intelligence classification model, we wanted to confirm the possibility of quantitative eval- uation of the qualitative evaluation part of the phantom test. We used intelligence classification models (VGG19, DenseNet201, EfficientNet B2, inception_resnet_v2, ResNet50V2, and Xception). And the fine-tuning process used for learning was additionally performed. As a result, in all classification models, the accuracy of spatial resolution was 0.9562 or higher, the precision was 0.9535, the recall was 1, the loss value was 0.1774, and the learning time was from a maximum of 14 minutes to a minimum of 8 minutes and 10 seconds. Through the experimental results, it was concluded that the artificial intelligence model can be applied to CT implements quality control in spatial res- olution and contrast resolution.

인공지능 기반 흉부 후전방향 검사에서 자세 평가 방법에 관한 연구

황호성,최용석,이대원,김동현 3,김호철 대한의용생체공학회 2023 의공학회지 Vol.44 No.3

Chest PA is the basic examination of radiographic imaging. Moreover, Chest PA's demands are constantly increasing because of the Increase in respiratory diseases. However, it is not meeting the demand due to problems such as a shortage of radiological technologist, sexual shame caused by patient contact, and the spread of infectious diseases. There have been many cases of using artificial intelligence to solve this problem. Therefore, the purpose of this research is to build an artificial intelligence dataset of Chest PA and to find a posture evaluation method. To construct the posture dataset, the posture image is acquired during actual and simulated examination and classified correct and incorrect posture of the patient. And to evaluate the artificial intelligence posture method, a posture esti- mation algorithm is used to preprocess the dataset and an artificial intelligence classification algorithm is applied. As a result, Chest PA posture dataset is validated with in over 95% accuracy in all artificial intelligence classification and the accuracy is improved through the Top-Down posture estimation algorithm AlphaPose and the classification InceptionV3 algorithm. Based on this, it will be possible to build a non-face-to-face automatic Chest PA examination system using artificial intelligence.

만성질환 노인의 활동 제한에 영향을 미치는 요인 : 국민건강영양조사 제 8기 자료를 활용하여

황호성,최지현,김수경 한국융합학회 2021 한국융합학회논문지 Vol.12 No.11

본 연구는 국민건강영양조사 제 8기 원시 자료를 활용하여 65세 이상 2,701명의 정상 노인과 만성질환 노인의 활동 제한에 영향을 주는 요인을 파악하기 위해서 복합표본 로지스틱 회귀분석을 실시하였다. 만성질환 노인이 정상 노인보다 활동 제한을 느낀다고 조사되었다. 뇌졸중, 고혈압 환자의 활동 제한 요인으로는 주관적 건강 상태, 경제 수준, 스트레스 인지 정도, 중강도의 일과 여가이다. 심장질환 환자의 활동 제한 요인으로는 주관적 건강 상태, 경제 수준이었 으며, 관절질환 환자의 활동 제한의 요인으로는 주관적 건강 상태, 고강도의 일과 여가이다. 폐 질환 환자의 활동 제한 요인으로는 교육 수준, 고강도의 일과 여가이며, 내분비계 환자의 활동 제한의 요인으로는 주관적 건강 상태, 스트레스 인지 정도, 고강도의 일과 여가이며, 암 환자의 활동 제한의 요인으로는 주관적 건강 상태, 스트레스 인지 정도, 중강도 의 일과 고강도의 여가이다. 만성질환 노인의 지속적인 활동 참여를 위한 재활프로그램과 정책적 지원이 필요하다. In this study, a complex sample logistic regression analysis was performed to identify the factors affecting the activity restriction of 2,701 normal elderly and chronically ill elderly aged 65 and over using raw data from the 8th period of the National Health and Nutrition Examination Survey. It was found that the elderly with chronic disease felt more restricted in their activities than the normal elderly. Activity limiting factors in stroke and hypertension patients are subjective health status, economic level, stress perception, and moderate-intensity work and leisure. The factors limiting activity in patients with heart disease were subjective health status and economic level, and factors limiting activity in patients with joint disease were subjective health status and high-intensity work and leisure. Activity limiting factors for lung disease patients are education level, high intensity work and leisure, and endocrine system activity limiting factors include subjective health status, stress perception, high intensity work and leisure, and activity limiting factors for cancer patients. is subjective health status, stress perception, moderate-intensity work and high-intensity leisure. Rehabilitation programs and policy support are needed for the continuous participation of the elderly with chronic diseases.

염기로 처리한 소나무 목질의 Cu(2) 이온 흡착 특성

황호성,김하나,양경민,박세근,김영관 대한환경공학회 2006 대한환경공학회 학술발표논문집 Vol.2006 No.12

Invertebrates fauna in the intertidal regions of Yubudo Island, South Korea

황호성,한정호,이상보,류연미,백인환,민홍기,백운기 국립중앙과학관 2015 Journal of Asia-Pacific Biodiversity Vol.8 No.1

Yubudo Island, which is located at the estuary of the Geumgang River, is known to have high biodiversity level. This study investigated the invertebrates fauna in the intertidal regions of Yubudo Island during May 2014 to December 2014. A total of 49 species from 32 families were observed. Among them, arthropods were the most abundant, accounting for 48% of the total with 24 species. A large number of Uca (Austruca) lactea, Endangered Wild Species Class II of Korea, were found on the mud flats in December 2014.

가상현실 기반 상지재활훈련이 뇌졸중 환자의 상지기능, 근 활성도, 일상생활활동, 삶의 질에 미치는 효과

황호성,유두한,김희,김수경 대한작업치료학회 2020 대한작업치료학회지 Vol.28 No.2

Objective: The purpose of this study is to analyze the effects of virtual reality-based upper limb rehabilitation usingsmart gloves on the upper extremity function, muscle activation, daily activities, and quality of life in strokepatients. Methods: A total of 31 patients after a stroke were randomly assigned to a study group of 16 patients and a controlgroup of 15 patients. For the experimental group, virtual reality-based upper limb rehabilitation using smartgloves was applied, and for the control group, occupational therapy was given. The experiment was conducted for25 sessions, 5 times a week for 30 min. A Manual Function Test, surface electromyography, Korean version ofthe Modified Barthel Index, and Stroke Impact Scale 3.0 were applied as pre- and post-assessments. Results: Virtual reality-based upper limb rehabilitation using smart gloves showed significant differences in upperextremity function, muscle activation, daily activities, and quality of life. Conclusion: Virtual reality-based upper limb rehabilitation using smart gloves is an effective occupational therapymethod for improving the upper limb function, muscle activation, activities of daily living, and quality of life instroke patients. 목적 : 본 연구는 스마트 글러브를 이용한 가상현실 기반의 상지재활훈련이 뇌졸중 환자의 상지기능, 상지의근 활성도, 일상생활 활동과 삶의 질에 미치는 효과를 분석하고자 한다. 연구방법 : 선착순 무작위 대조 실험연구 방식으로 연구를 진행하였다. 의료연구협의회 지표(medicalresearch council scale), 한국판 간이정신상태검사(Korean version of Mini-Mental State Examination;MMSE-K)로 대상자를 선별하여 뇌졸중 환자 31명을 무작위로 스마트 글러브를 이용한 가상현실 기반의상지재활훈련군과 일반적 작업치료군으로 나눈 뒤, 주 5회 하루 30분씩 총 25회기 동안 실험을 진행하였다. 중재 전ᆞ후 비교 분석을 하기 위해서 뇌졸중 상지 기능평가(Manual Function Test; MFT), 표면 근전도검사(Surface Electromyography; EMG), 한국판 수정된 바델지수(Korean version of Modified BarthelIndex; K-MBI), 뇌졸중 영향 척도 3.0(Stroke Impact Scale 3.0; SIS)을 사용하였다. 결과 : 첫째, 실험군과 대조군에서 상지의 기능향상(MFT)이 있었고, 실험군에서 위팔노근의 근 활성도에 유의한 향상이 있었다. 둘째, 일상생활활동에서는 실험군과 대조군에서 유의한 향상을 보였다. 셋째, 삶의 질에서는 실험군에서 유의한 향상이 있었다. 결론 : 스마트 글러브를 이용한 가상현실 기반 상지재활훈련은 뇌졸중 환자의 상지기능, 근 활성도, 일상생활활동과 삶의 질을 향상하는 효과적인 작업치료 방법이다.

태풍의 온대저기압화와 관련한 한반도 강수량의 분포

황호성,김도우,변희룡,최기선,오수빈,이상민 한국기상학회 2010 한국기상학회 학술대회 논문집 Vol.2010 No.4

GloSea5 한영통합앙상블 과거재현자료의 월별 예측특성 분석

황호성,박병권,박지선,전찬일,김동준 한국기상학회 2017 한국기상학회 학술대회 논문집 Vol.2017 No.10