프로세스 마이닝 기반 Felder-Silverman 학습패턴 데이터 분석 방법 개발

권나은,김종민,조민수,박규동 대한산업공학회 2022 대한산업공학회 춘계학술대회논문집 Vol.2022 No.6

프로세스 마이닝 기반 Felder-Silverman 학습패턴 데이터 분석 방법 개발

권나은,김종민,조민수,박규동 한국경영과학회 2022 한국경영과학회 학술대회논문집 Vol.2022 No.6

한식 기내식 선택요인에 관한 연구 : 방한 외국인을 대상으로

권나은,김해옥,현성협 한국호텔외식관광경영학회 2019 호텔경영학연구 Vol.28 No.7

The purpose of this study was to investigate factors that lead to foreigners’ meal satisfaction of Korean food on airlines. Also, this study aimed to empirically discover the positive impact from such customer satisfaction that can lead to an increase of purchase intentions of Korean cuisine and the improvement of the national image. First, a survey was conducted for empirical analysis of 201 foreigners visiting Korea who have tried Korean food in-flight meals at least once. Out of the five reasons for choosing a Korean food in-flight meal, deduced from similar experiments conducted in the past and field interviews, the highest incidence of responses was because of the nutritional value of the meal, followed by aesthetics, and ease of digestion. Based on these rankings, the latest Korean –food positioning was suggested. Moreover, the fact that foreigners’ desire to try Korean cuisine in the future and the improvement of national image corresponded with their satisfaction of the Korean food in-flight meals, proves the impact Korean food in-flight meals have and indicated the need for an improvement in its quality. If the tourism, aviation, and restaurant industries can work together toward providing high-quality Korean meals through concerted efforts, not only will it benefit the companies involved, but it will be a new model for national promotion and economic growth. 본 연구는 방한 외국인을 대상으로 한식 기내식 만족도를 발생시키는 선택요인을 밝혀내고 해당요인들로 인한 고객만족도가 한식 구매 의도 증가와 국가 이미지 상승효과 발생에 영향을 미치는 요인에 관해 연구하고자 한다. 실증분석을 위하여 한식 기내식을 먹은 경험이 있는 방한 외국인 201명을 대상으로 설문조사를 시행했다. 유사 주제의 선행연구와 현장 인터뷰를 바탕으로 도출한 한식 기내식 5가지 선택요인을 분석한 결과 건강식으로의 가치로 인한 선택요인이 가장 높게 나타났으며, 다음으로는 감각적 가치, 소화의 용이성 순서로 채택된 결과를 바탕으로 최신의 K-FOOD 포지셔닝을 제시했다. 더불어 외국인의 한식 기내식 만족도는 방한 이후 한식 구매 의도와 국가 이미지 상승에 유의한 영향을 미치는 것으로 연구결과가 나타나 한식 기내식의 파급력과 품질 향상의 필요성을입증했다. 분석결과, 건강식으로의 가치, 소화의 용이성, 감각적 가치가 고객만족도에 유의한 영향을미친다는 가설 H1-1, H1-2, H1-4은 채택되었다. 또한, 고객만족도가 한식 구매 의도와 국가 이미지에 유의한 영향을 미친다는 H2, H3은 채택되었다. 반면에 체중 조절과 친숙도가 고객만족도에 유의한 영향을 미친다는 가설 H1-3, H1-5는 기각되었다. 본 연구는 국내의 관광・항공・외식업계가 각분야의 전문성을 이용한 협업을 통해 더욱 수준 높은 한식 경험을 전달하기 위한 노력을 함께 한다면 자사의 이익 창출을 넘어 국가적 이미지 제고와 경제 활성화의 새로운 모델이 될 수 있음을 시사한다.

팬데믹 이후 항공기 기내식음료 서비스의 지각된 위험이 고객 만족도에 미치는 영향에 관한 연구

권나은,현성협 한국마이스관광학회 2022 MICE관광연구 Vol.22 No.1

The purpose of this study is to empirically examine the effect of perceived risk of in-flight food and beverage service on customer satisfaction after the pandemic. In addition we would like to examine the changes in customer perception and the direction of in-flight food and beverage services. First, this study found that customers who are well aware of the risk of infectious diseases were more than customers who are less aware of infectious disease risks. Therefore, as the risk of infectious diseases increases, related in-flight food and beverage services should be introduced more safely and thoroughly. Second, among the related airline food and beverage services provided, customers responded that services provided on board, such as wearing safety protective equipment and sanitary gloves, using disposable items, and stability of in-flight food and beverage, are more important than other service areas. Therefore, airlines need to improve the overall industry and procedures of in-flight food and beverage services directly connected to infectious diseases based on specific demands and changes in perceptions that differ from before the pandemic.

효과적인 상지 재활을 위한 운동 어플리케이션 개발 : 게이미피케이션 적용을 중심으로.

권나은,이규민,이지윤,채수지,박규동,이상민 한국정보처리학회 2022 한국정보처리학회 학술대회논문집 Vol.29 No.1

필라테스 운동이 임신성 요통을 가진 임산부의 골반 경사각 및 건강 체력에 미치는 영향

권나은,최승준 대한고유수용성신경근촉진법학회 2020 PNF and Movement Vol.18 No.3

Purpose: The purpose of this study was to investigate the effects of Pilates exercise on the back pain index, pelvic tilt angle, and physical fitness of pregnant women with low back pain. Methods: All study participants, all of whom had pregnancy-induced back pain, were randomly assigned to either a Pilates exercise group (PG, n = 8) or control group (CG, n = 7). The PG performed a Pilates exercise for 50 minutes three times a week for eight weeks. The back pain scale and pelvic tilt angle were measured using a visual analogue scale and angulometer, respectively. Cardiopulmonary endurance, flexibility, and grip strength were measured to examine the physical fitness. The variables were analyzed using two-way repeated-measures ANOVA with the Holm-Sidak post hoc procedure. Results: Back pain in the PG significantly decreased from 4.69 ± 1.28 to 1.06 ± 0.94, whereas the CG showed significantly increased back pain from 2.63 ± 2.20 to 4.71 ± 2.56. The left pelvic angle in the PG showed a significant decrease from 13.94 ± 3.70° to 12.29 ± 2.95°, while the CG showed a non-significant difference from 13.07 ± 4.42° to 17.37 ± 3.13°. The right pelvic angle in the PG showed a significant decrease from 13.50 ± 4.47° to 10.34 ± 3.66°, while a non-significant difference in the CG from 44 ± 4.98 ° to 15.30 ± 3.61° was found. These results showed that the regular participation in Pilates exercise was effective in reducing the pelvic tilt angle. In terms of physical fitness, the PG showed a significant increase in cardiopulmonary endurance, flexibility, and grip strength. However, the CG showed any significance increase in those variables. Conclusion: Eight weeks of Pilates exercise was associated with a decrease in lower back pain, a maintained or reduced pelvic tilt angle, and increased cardiopulmonary endurance, grip strength, and flexibility in pregnant woman with lumbar pain.

고정익 항공기 주익 구조물 하중 해석을 통한 균열 원인 분석 및 결함 개선

권나은(Na Eun Kwon),손혜경(Hye Gyeong Son),서의화(EuyHwa Seo),이진원(Jinwon Lee) 한국산학기술학회 2024 한국산학기술학회논문지 Vol.25 No.1

In this study, an improved design was proposed to address crack formation in a bracket used to secure the asymmetric brake of the flap in front of the main wing of a military aircraft and to prevent recurrence. A defect analysis tree was used to identify the cause, and items of interest were identified by fracture surface /structural analysis and subjected to further analysis. Fracture surface analysis confirmed that the cracks were caused by a lack of static strength and propagated due to fatigue induced by repeated tensile loading. We confirmed that loads beyond design specifications were responsible for the lack of static strength, and calculation showed static strength was insufficient under certain load conditions. The improved shape was reinforced to cope with the additional load, and it was confirmed that the modification improved structural health. In addition, a check of safety margins showed that static strength requirements were met.

전차 유압펌프용 EDV 케이블 단선방지를 위한 진동저감 연구

강승주,권나은,하상수 한국기계기술학회 2024 한국기계기술학회지 Vol.26 No.5

In order to prevent disconnection of the hydraulic pump EDV cable, this study judged the vibration generated by the pump as the greatest effect on disconnection, and confirmed the vibration effect. And it had a structure that was vulnerable to vibration because of the wire flow space inside the EDV cable connector. After applying the improved adapter, vibration analysis, excitation test, and bending strength test were performed to confirm the effectiveness of design change and improvement. As a result of vibration analysis, the amount of vibration was reduced by about 10 times compared to the existing product, and the strength increased by about 4 times in the bending strength test was confirmed to increase the effect of preventing disconnection due to vibration.

Sample Size Estimation for Developing Artificial Intelligence to Predict Orthodontic Treatment Outcomes

김종학,권나은,이신재 대한치의학회 2025 Journal of korean dental science Vol.18 No.1

Purpose: To estimate the sample size required for developing artificial intelligence (AI) that can predict soft-tissue and alveolar bone changes following orthodontic treatment. Materials and Methods: From the original data sets with N=887, consisting of 132 input and 88 output variables used to create AI models for predicting treatment changes following orthodontic treat ment, six subsets of the data (n=75, 150, 300, 450, 600, and 750) were generated through random resampling procedures. The process was repeated four times, resulting in 24 different data subsets. Each data subset was used to create a total of 24 AI mod els using the TabNet deep neural network algorithm. The clinically acceptable prediction accuracy was defined as a less than 1.5 mm prediction error on the lower lip. The prediction errors from each AI model were compared according to sample sizes and analyzed to estimate the optimal sample size. Results: The prediction error decreased with increasing sample sizes. A training sample size greater than approximately 1650 was estimated to develop an AI model with less than 1.5 mm of prediction errors at the lower lip area. Conclusion: From a statistical and research design perspective, a considerable amount of training data ap pears necessary to develop an AI prediction model with clinically acceptable accuracy. [J Korean Dent Sci. 2025;18(1):12-9]

AI 기반 항공기 광학 탐지 장치 성능 개선을 위한 합성 이미지 활용 연구

정상규,권나은,김형우 한국항행학회 2024 한국항행학회논문지 Vol.28 No.5

본 연구는 야간 환경에서 발생하는 조명과 노이즈에 의한 이미지 왜곡을 저감하고, 적외선 탐지 장치의 성능을 향상시키기 위해 AI 기반 이미지 복원 기술을 제안한다. 이를 위해 가시광선 이미지를 기반으로 다양한 조명 조건과 ISO 값을 반영한 합성 이미지 데이터셋을 구축하고, 딥러닝 모델(AutoEncoder 및 U-Net)을 활용하여 원본 이미지 복원 성능을 확인하였다. 실험 결과, Multi-ISO 모델(9채널)이 Single-ISO 모델(3채널)보다 전반적으로 우수한 성능을 보였으며, 특히 다양한 ISO 값을 활용한 입력 데이터가 이미지 복원 성능을 향상시킴을 입증하였다. 본 연구는 실제 데이터 수집이 어려운 상황에서도 합성 데이터를 통해 AI 모델을 효과적으로 학습시키고, 이미지 복원에 적용할 수 있음을 확인하였다. 이러한 연구 결과는 AI를 활용한 광학 탐지 장치의 성능을 향상시키는 데 기여할 수 있을 것으로 기대된다. This study proposes an AI-based image restoration technique to reduce image distortion caused by lighting and noise in nighttime environments and improve the performance of infrared detection systems. A synthetic image dataset was constructed using visible light images under various lighting conditions and ISO settings, and deep learning models (AutoEncoder and U-Net) were trained to assess image restoration performance. Experimental results show that the Multi-ISO model (9-channel) outperforms the Single-ISO model (3-channel), especially when utilizing input data with multiple ISO values. This study demonstrates that AI models can be effectively trained using synthetic data, even when real data collection is challenging, and can be applied to image restoration tasks. These findings are expected to contribute to enhancing the performance of optical detection systems through AI-based technology.