• 한국시뮬레이션학회논문지
• /
• 제33권2호
• /
• pp.27-35
• /
• 2024

본고에서는 인공지능 모델 학습에 사용하는 데이터셋에 내재한 편향성이 인공지능 예측 결과에 미치는 영향을 분석함으로써, 위의 경우가 사회적 격차를 고착화시키는 문제를 조명하고자 하였다. 따라서 데이터 편향성이 인공지능 모델에 끼치는 영향을 분석하기 위해, 성별 임금 격차에 관한 편향이 포함된 원본 데이터셋을 제작하였으며 해당 데이터셋을 비식별 처리한 데이터셋을 만들었다. 또한 의사결정트리 알고리즘을 통해 원본 데이터셋과 비식별화 된 데이터셋을 학습한 각각의 인공지능 모델 간의 산출물을 비교함으로써, 데이터 비식별화가 인공지능 모델이 산출한 결과의 편향에 어떠한 영향을 미치는지 분석하였다. 이를 통해 데이터 비식별화가 개인정보 보호뿐만 아니라, 데이터의 편향에도 중요한 역할을 할 수 있음을 도출하고자 하였다.

• Clinical and Experimental Vaccine Research
• /
• 제12권2호
• /
• pp.127-133
• /
• 2023

Purpose: Around 70% of the Iranian population had received two doses of coronavirus disease 2019 (COVID-19) vaccines by the end of 2021. In this study, we evaluated the reasons for vaccination refusal among people in Ahvaz, Iran. Materials and Methods: In this cross-sectional study, 800 participants (400 vaccinated and 400 unvaccinated) were recruited. A demographic questionnaire was completed through interviews. The unvaccinated participants were asked about the reasons for their refusal. The Shapiro-Wilk test, independent t-test, chi-square test, and logistic regression were used for analyzing data. Results: Older people were 1.018 times more likely to refrain from vaccination (95% confidence interval [CI], 1.001-1.039; p=043). People who were manual workers as well as those who were unemployed/housewives were 0.288 and 0.423 times less likely to receive vaccination, respectively. Those with high school education and married women were 0.319 and 0.280 times less likely to receive vaccination, respectively (95% CI, 198-0.515; p<0.001; 95% CI, 0.186-0.422; p<0.001). Participants who had hypertension or suffered from neurological disorders were more likely to receive the vaccination. Finally, people affected with severe COVID-19 infection were 3.157 times more likely to get vaccinated (95% CI, 1.672-5.961; p<0.001). Conclusion: The results of this study showed that lower level of education and older age were contributed to reluctance for vaccination, while having chronic diseases or being already infected with severe COVID-19 infection were associated with more acceptance of vaccination.

• 한국의료질향상학회지
• /
• 제30권1호
• /
• pp.55-75
• /
• 2024

Purpose: This study aimed to elucidate the intention to use non-face-to-face treatment, which was temporarily allowed during the coronavirus disease 2019 pandemic. Based on the social cognitive theory, individual behavioral changes occur through the dynamic interaction of individual, environmental, and behavioral factors. Thus, we investigated the impact of personal, environmental, and behavioral factors on the acceptance of non-face-to-face treatment. Methods: A Web survey was conducted using Korea Research Panel between December 26 and 29, 2022, to examine the conceptual framework. The survey targeted adults aged 19 and older, regardless of whether they had used non-face-to-face treatment. A total of 502 responses were collected. Further, a three-step hierarchical regression analysis was conducted using SPSS Windows software version 25.0. Results: The study showed that 131 out of 502 respondents had experience using non-face-to-face treatment, while 371 did not. The factors that influenced the intention to accept non-face-to-face treatment included the general characteristics of the participants (women, underlying disease), personal factors (usefulness, cost savings, knowledge), and environmental factors (social norms, trust, perceived risk). The model demonstrated an explanatory power of 65%. Conclusion: The results of this study directly show that intention is linked to behavior through the interaction between personal and environmental factors. Further research is needed to explore additional factors influencing the intention to accept non-face-to-face treatment, enabling its effective use in preventing and treating various diseases, including infectious diseases.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.1-8
• /
• 2024

실시간 처리 및 프라이버시 강화를 위해 인공지능 모델을 엣지에서 동작시킬 수 있는 온디바이스 AI 기술이 각광받고 있다. 지능형 사물인터넷 기술이 다양한 산업에 적용되면서 온디바이스 AI 기술을 활용한 서비스가 크게 증가하고 있다. 그러나 일반적인 딥러닝 모델은 추론 및 학습을 위해 많은 연산 자원을 요구하고 있다. 따라서 엣지에 적용되는 경량 기기에서 딥러닝 모델을 동작시키기 위해 양자화나 가지치기와 같은 다양한 경량화 기법들이 적용되어야 한다. 본 논문에서는 다양한 경량화 기법 중 가지치기 기술을 중심으로 엣지 컴퓨팅 기기에서 딥러닝 모델을 경량화하여 적용할 수 있는 방안을 분석한다. 특히, 동적 및 정적 가지치기 기법을 적용하여 경량화된 비전 모델의 추론 속도, 정확도 그리고 메모리 사용량을 시험한다. 논문에서 분석된 내용은 실시간 특성이 중요한 지능형 영상 관제 시스템이나 자율 이동체의 영상 보안 시스템에 적용될 수 있다. 또한 사물인터넷 기술이 적용되는 다양한 서비스와 산업에 더욱 효과적으로 활용될 수 있을 것으로 기대된다.

• 한국의상디자인학회지
• /
• 제25권4호
• /
• pp.13-28
• /
• 2023

The purpose of this study is to analyze the characteristics of hippie style in emerging brands pursuing the hippie spirit, examine the changes in hippie style, and apply them to the design development process to propose a hippie style design that reflects contemporary characteristics. The research method of this study was used to grasp the characteristics and current status of hippie style based on a literature review and prior research. Through the analysis of Bode and Story mfg, a new brand that reflects the hippie spirit, the design expression methods and characteristics of modern hippie style were derived, and based on the analysis, the design of the 3D CLO virtual outfit was developed. The results of the study are as follows. First, in addition to the use of eco-friendly materials, the digital technology of the CLO 3D program was applied to the design development process, which made it possible to increase sustainability from the production process. Second, by creating a retro design centered on a striped pattern expressing freedom, revolution, and equality, and a handcrafted design based on a tie-dye pattern, the design was able to express the hippie spirit of loving nature, and through this, a new direction of eco-friendly and modern fashion design was presented.

• 대한영상의학회지
• /
• 제81권6호
• /
• pp.1486-1491
• /
• 2020

기쿠치병은 주로 아시아에 거주하는 젊은 여성에서 경부 림프절 비대와 열을 주소로 나타나는 조직구 괴사성 림프절염이며 자연적으로 치유되는 양성질환이다. 기쿠치병이 전형적으로 발현하는 위치가 아닌 림프절에서 발생하면 진단이 어려워지고 악성 질환으로 오인되기도 한다. 저자들은 2주간 지속되는 발열을 주소로 내원하여 시행한 초음파와 CT, 18F-fluorodeoxyglucose PET/CT에서 비장 종대와 경부, 액와부, 복강, 후복강, 서혜부 림프절 비대를 보여 림프종을 의심하였던 15세 여자 환아 증례를 보고한다. 복강 림프절 절제술로 기쿠치병을 진단하였다. 이후, 환자는 스테로이드로 보존적인 치료를 받고 발열 증상이 호전되어 퇴원하였다.

• 한국응용과학기술학회지
• /
• 제40권4호
• /
• pp.890-896
• /
• 2023

본 연구는 혈중 엽산농도와 대사증후군의 관련성을 살펴보고자 한다. 분석에 사용한 자료는 국민건강영양조사 2018년도 자료(제7기 3차)를 사용하였으며 본 연구는 만 19세 이상인 성인을 대상으로 혈중 엽산농도를 측정한 대상자 중 남자 495명, 여자 706명, 총 1,201명을 최종 분석하였다. 자료의 분석은 일반적 특성에 따른 혈중 엽산 차이는 Chi-square와 t- test로, 대사증후군 하부요인들간의 관계는 Pearson 상관관계, 혈중엽산농도와 대사증후군 지표는 로지스틱 회귀분석을 사용하였다. 본 연구 결과에 의하면 혈중 엽산농도와 대사증후군의 하부요인인 허리둘레(r=-0.113, p<0.05), 중성지방(r=-0.086, p<0.05)과 유의미한 음의 상관관계, HDL-cholesterol(r=0.086, p<0.05)은 유의미한 양의 상관관계를 보였으며 회귀분석결과 HDL-cholesterol의 경우 혈중엽산농도가 정상인 군이 낮은 군에 비하여 유의미하게 높았다(p<0.05). 따라서 본 연구를 통하여 대사증후군 예방을 위한 적절한 식습관 및 건강 교육프로그램 개발을 제안한다.

• Korean Journal of Radiology
• /
• 제24권7호
• /
• pp.626-639
• /
• 2023

Objective: To investigate the association of clinical, pathologic, and magnetic resonance imaging (MRI) variables with progressive disease (PD) during neoadjuvant chemotherapy (NAC) and distant metastasis-free survival (DMFS) in patients with triple-negative breast cancer (TNBC). Materials and Methods: This single-center retrospective study included 252 women with TNBC who underwent NAC between 2010 and 2019. Clinical, pathologic, and treatment data were collected. Two radiologists analyzed the pre-NAC MRI. After random allocation to the development and validation sets in a 2:1 ratio, we developed models to predict PD and DMFS using logistic regression and Cox proportional hazard regression, respectively, and validated them. Results: Among the 252 patients (age, 48.3 ± 10.7 years; 168 in the development set; 84 in the validation set), PD was occurred in 17 patients and 9 patients in the development and validation sets, respectively. In the clinical-pathologic-MRI model, the metaplastic histology (odds ratio [OR], 8.0; P = 0.032), Ki-67 index (OR, 1.02; P = 0.044), and subcutaneous edema (OR, 30.6; P = 0.004) were independently associated with PD in the development set. The clinical-pathologic-MRI model showed a higher area under the receiver-operating characteristic curve (AUC) than the clinical-pathologic model (AUC: 0.69 vs. 0.54; P = 0.017) for predicting PD in the validation set. Distant metastases occurred in 49 patients and 18 patients in the development and validation sets, respectively. Residual disease in both the breast and lymph nodes (hazard ratio [HR], 6.0; P = 0.005) and the presence of lymphovascular invasion (HR, 3.3; P < 0.001) were independently associated with DMFS. The model consisting of these pathologic variables showed a Harrell's C-index of 0.86 in the validation set. Conclusion: The clinical-pathologic-MRI model, which considered subcutaneous edema observed using MRI, performed better than the clinical-pathologic model for predicting PD. However, MRI did not independently contribute to the prediction of DMFS.

• 대한통합의학회지
• /
• 제12권2호
• /
• pp.177-186
• /
• 2024

Purpose : The purpose of this study was to use oral instruction and taping to induce abdominal draw-in in the previous study, but there is a lack of research on the comparison of effects. Therefore, in this study, we would like to study how the effect of oral instruction, taping, and no feedback can affect muscle activity when performing abdominal draw-in pier exercises. Methods : Before the experiment, group A trained piers and applied only draw-in piers, group B applied taping feedback, and group C were divided into three groups per week for six weeks, and three sets of contractions for five seconds per group were performed five times, and a minute break was provided between each exercise. As a measurement tool, a wireless surface electromyography (EMG) was used to measure surface electromyography (Telemyo-DTS, NORAXON, USA) that derives a synthetic unit of muscle using a surface electrode. For statistical processing of data, the analysis is performed using the SPSS/PC Version 25.0 statistical program for Windows, and the statistical significance level is a=.05 Results : First, the duration was somewhat shorter in order to more accurately compare the muscle activity of the core muscles. Therefore, future research needs to be research that can be exercises with precise biofeedback and taping applied over a longer period of time. Secondly, it is believed that there is no significant difference, since the subjects were studied in healthy young adult men and women, not patients. Thirdly, they could not control the daily life of the subjects. Through future research, it is necessary to analyze the correlation between muscle activity and abdominal muscle thickness by adding ultrasound in addition to muscle activity in various age groups. Conclusion : During draw-in bridge exercise according to feedback, the muscle activity of the back muscle increased, and there was no significant difference in the muscle activity of the back muscle according to each feedback. Therefore, both the feedback applied during the draw-in pier exercise and the control group are effective in changing the thickness of the abdominal muscles.

• 한국컴퓨터정보학회논문지
• /
• 제29권3호
• /
• pp.55-66
• /
• 2024

성별 분류 기술은 법의학, 감시 시스템, 인구 통계 연구 등 다양한 분야에서 활용될 수 있기 때문에, 연구자들로부터 많은 관심을 받고 있다. 남성과 여성의 보행 사이에는 서로 구별되는 특징이 있다는 것이 기존 연구들에서 밝혀지면서, 3차원 보행 데이터에서 성별을 분류하는 다양한 기술들이 제안됐다. 하지만, 기존 기술들을 사용해 3차원 보행 데이터로부터 추출한 보행 특징 중에는 서로 유사 또는 중복되거나 성별 분류에 도움이 되지 않는 특징들도 있다. 이에 본 연구에서는 상관관계 기반 특징 선별 기술을 활용해, 성별 분류에 도움이 되는 특징들을 선별하는 방법을 제안한다. 그리고 제안하는 특징 선별 기술의 효용성을 입증하기 위해서, 인터넷상에 공개된 3차원 보행 데이터 세트(Dataset)를 활용하여 제안하는 특징 선별 기술을 적용하기 전과 후에 대해 성별 분류 모델들의 성능을 비교 분석하였다. 실험에는 이진 분류 문제에 적용할 수 있는 여덟 가지의 머신러닝 알고리즘(Machine Learning Algorithms)을 활용하였다. 실험 결과, 제안하는 특징 선별 기술을 사용하면 성별 분류 성능은 유지하면서, 특징의 개수를 82개에서 60개까지, 22개를 줄일 수 있다는 것을 입증하였다.