• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.35-37
• /
• 2021

Analyzing and predicting foreign tourists' demand is a crucial research topic in the tourism industry because it profoundly influences establishing and planning tourism policies. Since foreign tourist data is influenced by various external factors, it has a characteristic that there are many subtle changes over time. Therefore, in recent years, research is being conducted to design a prediction model by reflecting various external factors such as economic variables to predict the demand for tourists inbound. However, the regression analysis model and the recurrent neural network model, mainly used for time series prediction, did not show good performance in time series prediction reflecting various variables. Therefore, we design a foreign tourist demand prediction model that complements these limitations using a convolutional neural network. In this paper, we propose a model that predicts foreign tourists' demand by designing a one-dimensional convolutional neural network that reflects foreign tourist data for the past ten years provided by the Korea Tourism Organization and additionally collected external factors as input variables.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.74-74
• /
• 2021

우리나라의 농업용수 사용량은 152억톤으로 우리나라 전체 물 사용량의 약 42%이며, 농업용수의 관리는 전체 논 면적 865천ha 중 한국농어촌공사에서 487천ha(56%), 지방자치단체에서 221천 ha(26%), 수리 불안전답이 157천ha(18%)이다. 또한 우리나라에 설치된 저수지, 양수장 등과 용수로로 공급되는 농업용수 공급량 중 논에 유입되지 못하고 퇴수되는 물이 약 43%이다. 농업용수 급수 중 용수로의 수위가 낮아 급수관을 통해 논에 유입되지 못하고 배수로로 퇴수되고 있는 실정이다. 농업용수 급수가 원활하기 위해서는 용수로의 수위를 20cm이상 확보하여야 급수관을 통해 논에 급수가 가능하다. 하지만 현장에서는 이러한 물 공급의 문제점을 해결하기 위해 용수로를 비료포대 등으로 막아서 사용함으로써 용수로 시설물의 관리가 되지 않고 토사가 쌓여 급수 애로가 가중되는 상황으로 시설물 관리를 위한 용수로 준설 등 시설 유지관리비가 발생하고 있다. 특히 금강권역(금강, 만경강, 동진강, 삽교천, 충남 서북부)에서 상습적인 가뭄 발생으로 농업용수 사용에 관한 분쟁이 상시적으로 도사리고 있는 실정이다. 이러한 문제를 해결하기 위해 농업용수의 급수 손실을 최소화하며 원활하고 안정적인 용수를 공급하고자 하였으며, 농민을 대상으로 설문지를 작성하여 응답을 분석하고 농민들의 요구사항을 개선하기 위해 법·제도, 거버넌스, 재원 및 기술·시설로 구분하여 제시하였다. 또한 과거 관행에 의한 유말부 용수공급에 탈피해서 원활한 용수공급이 가능하고 유지관리가 쉬운 장치인 부력식 제수문을 선정하고 제시하였다. 따라서 본 연구에서는 금강권역 상습 가뭄지역의 안정적인 농업용수의 공급관리를 위한 기술 개발 및 적용을 실시하고, 농업용수 공급관련 정량화된 손실현황을 분석한 후 수위확보 장치 적용 전·후 모니터링으로 효과 분석을 실시하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.59-59
• /
• 2021

최근 기후변화에 따른 가뭄의 상습화와 농촌용수 수요증가에 대비할 수 있는 가뭄대책의 수립을 통한 용수부족 문제에 대한 근본적인 해소의 필요성 증가하고 있는 가운데 기존 수자원을 효율적으로 활용하기 위한 4차 산업기술을 적용한 순환형 농업용수 관리시스템의 개발이 요구되고 있다. 본 연구는 2017년 가뭄이 극심하였던 충청남도 대사저수지, 풍전저수지와 경기도 마둔저수지에 대하여 기상분석, 관개분석, 수리분석 등을 수행하여 이수관리, 관개만족도, 회귀수의 재이용 등을 예측 관리할 수 있는 순환형 농업용수 관리 시스템을 개발하여 적용하고자, 선제적으로 가뭄 발생 들녘의 용수공급을 위한 농업용 저수지 소유역 순환용수 가용수량을 추정하였다. 2010년부터 2019년까지의 강우유출 모형을 적용하기 위하여 수원, 천안, 이천관측소의 강우, 최고/최저기온, 상대습도, 풍속, 일사량자료를 일자료로 활용하였고, 10년 평균 유출량을 순별로 산정하여 기본자료로 구축하여 주요 취입보 유입수량을 산정하였다. 주요 취입보 유입수량 산정과 취입보의 용적을 산출하기 위하여 시설별 높이차와 하천의 길이 및 폭을 측정하였으며 물수지는 보유용수량과 유입량의 합에서 공급수량을 제외한 값으로 정의하였고, 내용적을 초과하는 경우에는 범람되는 것으로 구현하여 마둔, 대사, 풍전저수지의 임의 지점(하천)별로 순환용수 가용을 위한 모의를 실시하였다. 공간 범위는 평야부 말단부로 선정하였고, 가상으로 약 2m 높이의 임시보를 적용하여 관개기 강우유출수 및 퇴수에 의한 가용수량을 산정하였다. 이를 위하여 하천의 폭과 표고를 이용하여 길이를 산출하여, 내용적을 산출하였다. 소유역별로 TANK 모형적용 결과를 입력자료로 활용하여 일 공급 양수량을 내용적 최대로 하였을 때 회복 기간에 대한 모의를 수행하였다. 강우유출수에 의한 소유역별 가용수량을 4월부터 모의 분석한 결과 유역별로 차이는 발생하지만 만수위에 도달하는 기간은 특이 유역을 제외하고는 약 50일 이상 걸리는 것으로 분석되었고, 관개기가 계속되면서 회복되는 기간이 짧아지는 경향을 보였다. 이를 통해 소유역별 농업용수 부족분 투입을 위한 위치선정과 용수량 판단이 가능할 것으로 예상된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.268-268
• /
• 2021

Groundwater resource is mostly used in Abomey-calavi (southern region of Benin) as main source of water for domestic, industrial, and agricultural activities. Groundwater intake across the region is not perfectly controlled by a network due to the presence of many private boreholes and traditional wells used by the population. After some decades, this important resource is becoming more and more vulnerable and needs more attention. For a better groundwater management in the region of Abomey-calavi, the present study attempts to predict a future probable groundwater drought using Recurrent Neural Network (RNN) for future groundwater level prediction. The RNN model was created in python using jupyter library. Six years monthly groundwater level data was used for the model calibration, two years data for the model test and the model was finaly used to predict two years future groundwater level (years 2020 and 2021). GRI was calculated for 9 wells across the area from 2012 to 2021. The GRI value in dry season (by the end of March) showed groundwater drought for the first time during the study period in 2014 as severe and moderate; from 2015 to 2021 it shows only moderate drought. The rainy season in years 2020 and 2021 is relatively wet and near normal. GRI showed no drought in rainy season during the study period but an important diminution of groundwater level between 2012 and 2021. The Pearson's correlation coefficient calculated between GRI and rainfall from 2005 to 2020 (using only three wells with times series long period data) proved that the groundwater drought mostly observed in dry season is not mainly caused by rainfall scarcity (correlation values between -0.113 and -0.083), but this could be the consequence of an overexploitation of the resource which caused the important spatial and temporal diminution observed from 2012 to 2021.

• Journal of dental hygiene science
• /
• v.23 no.2
• /
• pp.88-92
• /
• 2023

Background: Aphthous stomatitis is a common disease of the oral mucosa and its pathogenesis is associated with several risk factors. Frequently, minor ulcers are idiopathic in nature and often resolve naturally. However, those ulcers are painful and sensibly compromise patients' eating. There are different treatment strategies for the clinical management of oral aphthae. Methods: The present study assessed the efficacy of a film-forming cream in accelerating the healing and diminishing the pain associated with minor aphthae in a randomized fashion design. The test product (AphtoFix^®) was compared with placebo cream in a cohort of patients with a diagnosis of minor recurrent stomatitis. Patients were randomly distributed into two groups and were followed for 10 days. The primary outcomes included the number of days until symptoms were relieved and the number of days to complete healing. Results: Thirty-six patients completed the follow-up, eighteen per group. All lesions eventually healed within day 10. However, patients in the test group experienced significantly less pain, already from day 1. Patients in the test group also showed a faster healing rate of the lesion with an average of 7 days against the 9 days required for patients in the control group. Conclusion: The present study supported the utility of a film-forming in cream in relieving the patient from symptoms associated with aphthous stomatitis already at day 1 of product use. Patients also displayed faster healing of the lesions when compared to the control group. Further studies with greater sample size and patient stratification according to age and risk factors are recommended to support the present findings.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.37.3-38
• /
• 2020

Ever since thick disk was proposed to explain the vertical distribution of the Milky Way disk stars, its origin has been a recurrent question. We aim to answer this question by inspecting 19 disk galaxies with stellar mass greater than 10^10 solar mass in recent cosmological high-resolution (>34 pc) zoom-in simulations: Galactica and New Horizon. The thin and thick disks are reproduced by the simulations with scale heights and luminosity ratios that are in reasonable agreement with observations. When we spatially classify the disk stars into thin and thick disks by their heights from the galactic plane, the "thick" disk stars are older, less metal-rich, kinematically hotter, and higher in accreted star fraction than the "thin" disk counterparts. However, we found that the the thick disk stars were spatially and kinematically thinner when they were born. Indeed, a large fraction of thick disk stars was born near the galactic plane at earlier times and get heated with time, eventually occupying high altitudes and exhibiting different population properties compared to the thin-disk stars. In conclusion, from our simulations, the thin and thick disk components are not entirely distinct at birth, but rather a result of the time evolution of the stars born in the main disk of the galaxy. (excerpted from the abstract of the upcoming paper submitted to Astrophysical Journal: Park, M.-J., Yi, S.K. et al. 2020)

• Korean Journal of Applied Biomechanics
• /
• v.33 no.2
• /
• pp.62-72
• /
• 2023

Objective: Although balance training has been used as an effective ankle injury rehabilitation program to restore neuromuscular deficits in patients with chronic ankle instability, it is not effectively used in terms of motor learning. Attentional focusing can be an effective method for improving ankle kinematics to prevent recurrent ankle injuries. This study aimed to 1) evaluate the effects of attentional focus, including internal and external focus, and 2) determine a more effective focusing method for patients with chronic ankle instability to learn balance tasks. Method: Twenty-four patients with chronic ankle instability were randomly assigned to three groups (external focus, internal focus, and no feedback) and underwent four weeks of progressive balance training. The three-dimensional ankle kinematics of each patient were measured before and after training as the main outcomes. Ensemble curve analysis, discrete point analysis, and post hoc pairwise comparisons were performed to identify interactions between groups and time. Results: The results showed that (1) the external focus group was more dorsiflexed and everted than the internal focus group; (2) the external focus group was more dorsiflexed than the no feedback group; and (3) the no feedback group was more dorsiflexed than the internal focus group. Conclusion: Because dorsiflexion and eversion are ankle motions that oppose the mechanism of lateral ankle sprain, using the external focus method during balance training may be more effective in modifying these motions, thereby reducing the risk of ankle sprain.

• Journal of Veterinary Science
• /
• v.24 no.4
• /
• pp.58.1-58.25
• /
• 2023

Porcine epidemic diarrhea virus (PEDV) has posed significant financial threats to the domestic pig industry over the last three decades in South Korea. PEDV infection will mostly result in endemic persistence in the affected farrow-to-finish (FTF) herds, leading to endemic porcine epidemic diarrhea (PED) followed by year-round recurrent outbreaks. This review aims to encourage collaboration among swine producers, veterinarians, and researchers to offer answers that strengthen our understanding of PEDV in efforts to prevent and control endemic PED and to prepare for the next epidemics or pandemics. We found that collaboratively implementing a PED risk assessment and customized four-pillar-based control measures is vital to interrupt the chain of endemic PED in affected herds: the former can identify on-farm risk factors while the latter aims to compensate for or improve weaknesses via herd immunity stabilization and virus elimination. Under endemic PED, long-term virus survival in slurry and asymptomatically infected gilts ("Trojan Pigs") that can transmit the virus to farrowing houses are key challenges for PEDV eradication in FTF farms and highlight the necessity for active monitoring and surveillance of the virus in herds and their environments. This paper underlines the current knowledge of molecular epidemiology and commercially available vaccines, as well as the risk assessment and customized strategies to control PEDV. The intervention measures for stabilizing herd immunity and eliminating virus circulation may be the cornerstone of establishing regional or national PED eradication programs.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.483-483
• /
• 2022

댐과 저수지의 운영 최적화를 위한 수문학적 예보는 현재 수동적인 댐 운영이 주를 이루면서 활용도가 높지 않다. 불확실한 기후변화나 기후재난 상황에서 우리 사회에 악영향을 최소화하기 위해 선제적으로 대응/대비할 수 있는 댐 운영 방안이 불가피하다. 강우량 예측 기술은 기후변화로 인해 제한적인 상황이다. 실례로, 2020년 8월에 섬진강의 댐이 극심한 집중 강우로 인해 무너지는 사태가 발생하였고 이로 인해 지역사회에 막대한 경제적 피해가 발생하였다. 선제적 댐 방류량 운영 기술은 또한 환경적인 변화로 인한 영향을 완화하기 위해 필요한 것이다. 제한적인 기상 예보 기술을 극복하고자 심화학습이나 강화학습 같은 인공지능 모델들의 활용성에 대한 연구가 시도되고 있다. 따라서 본 연구는 섬진강 댐의 시간당 수문 데이터를 이용하여 댐 운영을 위한 심화학습 모델을 개발하고 그 활용도를 평가하였다. 댐 운영을 위한 심화학습 모델로서 시계열 데이터 예측에 적합한 Long Sort Term Memory(LSTM)과 Gated Recurrent Unit(GRU) 알고리즘을 구축하고 댐 수위를 예측하였다. 분석 자료는 WAMIS에서 제공하는 2000년부터 2021년까지의 시간당 데이터를 사용하였다. 입력 데이터로서 시간당 유입량, 강우량과 방류량을, 출력 데이터로서 시간당 수위 자료를 각각 사용하였으며. 결정계수(R2 Score)를 통해 모델의 예측 성능을 평가하였다. 댐 수위 예측값 개선을 위해 하이퍼파라미터의 '최적값'이 존재하는 범위를 줄여나가는 하이퍼파라미터 최적화를 두 가지 방법으로 진행하였다. 첫 번째 방법은 수동적 탐색(Manual Search) 방법으로 Sequence Length를 24, 48, 72시간, Hidden Layer를 1, 3, 5개로 설정하여 하이퍼파라미터의 조합에 따른 LSTM와 GRU의 민감도를 평가하였다. 두 번째 방법은 Grid Search로 최적의 하이퍼파라미터를 찾았다. 이 두가지 방법에서는 같은 하이퍼파라미터 안에서 GRU가 LSTM에 비해 더 높은 예측 정확도를 보였고 Sequence Length가 높을수록 정확도가 높아지는 경향을 보였다. Manual Search 방법의 경우 R2가 최대 0.72의 정확도를 보였고 Grid Search 방법의 경우 R2가 0.79의 정확도를 보였다. 본 연구 결과는 가뭄과 홍수와 같은 물 재해에 사전 대응하고 기후변화에 적응할 수 있는 댐 운영 개선에 도움을 줄 수 있을 것으로 판단된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.264-266
• /
• 2022

In order to apply the RNN model to the radio fingerprint-based indoor path generation technology, the data set must be continuous and sequential. However, Wi-Fi radio fingerprint data is not suitable as RNN data because continuity is not guaranteed as characteristic information about a specific location at the time of collection. Therefore, continuity information of sequential positions should be given. For this purpose, clustering is possible through classification of each region based on signal data. At this time, the continuity information between the clusters does not contain information on whether actual movement is possible due to the limitation of radio signals. Therefore, correlation information on whether movement between adjacent clusters is possible is required. In this paper, a deep learning network, a recurrent neural network (RNN) model, is used to predict the path of a moving object, and it reduces errors that may occur when predicting the path of an object by generating continuous location information for path generation in an indoor environment. We propose a method of giving correlation between clustering for generating an improved moving path that can avoid erroneous path prediction that cannot move on the predicted path.