• 대한원격탐사학회지
• /
• 제38권4호
• /
• pp.327-341
• /
• 2022

Cloud removal is often required to construct time-series sets of optical images for environmental monitoring. In regression-based cloud removal, the selection of an appropriate regression model and the impact analysis of the input images significantly affect the prediction performance. This study evaluates the potential of Gaussian process (GP) regression for cloud removal and also analyzes the effects of cloud-free optical images and spectral bands on prediction performance. Unlike other machine learning-based regression models, GP regression provides uncertainty information and automatically optimizes hyperparameters. An experiment using Sentinel-2 multi-spectral images was conducted for cloud removal in the two agricultural regions. The prediction performance of GP regression was compared with that of random forest (RF) regression. Various combinations of input images and multi-spectral bands were considered for quantitative evaluations. The experimental results showed that using multi-temporal images with multi-spectral bands as inputs achieved the best prediction accuracy. Highly correlated adjacent multi-spectral bands and temporally correlated multi-temporal images resulted in an improved prediction accuracy. The prediction performance of GP regression was significantly improved in predicting the near-infrared band compared to that of RF regression. Estimating the distribution function of input data in GP regression could reflect the variations in the considered spectral band with a broader range. In particular, GP regression was superior to RF regression for reproducing structural patterns at both sites in terms of structural similarity. In addition, uncertainty information provided by GP regression showed a reasonable similarity to prediction errors for some sub-areas, indicating that uncertainty estimates may be used to measure the prediction result quality. These findings suggest that GP regression could be beneficial for cloud removal and optical image reconstruction. In addition, the impact analysis results of the input images provide guidelines for selecting optimal images for regression-based cloud removal.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1167-1174
• /
• 2022

With the sustainable development and transformation of the city, public art as a business card of the famous city of culture has become a hot topic of research. The intervention of public art in public space not only brings users a sense of space experience, but also becomes a unique carrier of urban and rural image making. Although there is much research on the classification, aesthetics and function of public art, there is few quantitative research on user satisfaction. This paper takes the basic features of airport public art as a research object and the basic features of airport public art as the theoretical basis to study the impact of the basic characteristics of airport public art on user satisfaction. Research methods were based on questionnaire data of 247 people, in which models and hypotheses were tested using SPSS 21.0 software, based on the induction and extraction of nine influential factors in the basic characteristics of public art. The study found that public interpretation, media patterns, color perception, modeling form, place perception, city image and memory have significant positive effects on user satisfaction. The sharedness of public art, cognition and communication in public culture and spatial relations do not affect satisfaction. Conclusion, inspiration and prospect provide suggestions for designers and reference data and theoretical support for public art evaluation.

• 상하수도학회지
• /
• 제36권4호
• /
• pp.239-248
• /
• 2022

The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.

• 한국컴퓨터정보학회논문지
• /
• 제27권10호
• /
• pp.155-162
• /
• 2022

본 연구에서는 Web of Science 데이터베이스에 최근 22년여(2000~2022)간 게재된 메타버스 관련 연구 결과들을 기반으로, 메타버스와 관련된 국제적 연구 동향과 특성을 분석하였다. 분석 절차는 기술 통계분석, 다차원 척도법, 키워드 네트워크분석 및 시각화로 구성되었다. 게재 연구 결과들의 특성과 동향에 따라 2000~2020년, 2021~2022년 상반기 두 기간으로 나누고 R과 KH Coder를 활용하여 연결중심성 및 매개중심성을 포함하는 언어 네트워크분석을 시행하였다. 연구 결과는 언어 네트워크분석을 통해 메타버스 관련 주요 연구들과 관련 융합 연구의 동향과 특성이 정량적으로 분석, 설명될 수 있음을 보여준다. 또한 이러한 연구 결과는 기술 발전이 가져올 관련 여건 변화를 감지하고 적시성 있는 메타버스 관련 연구를 추진하기 위한 기초자료로 활용할 수 있을 것으로 기대된다.

• 방송공학회논문지
• /
• 제28권2호
• /
• pp.238-241
• /
• 2023

최근 인공지능 모델을 이용한 얼굴인식, 얼굴 수정 등 다양한 얼굴 작업들이 실생활에도 광범위하게 사용되고 있다. 그러나 모델의 학습에 사용되는 대부분의 얼굴 데이터셋은 사회활동이 활발한 특정 나이에 편중되고, 어린아이나 노인의 데이터가 적은 경향이 있다. 이와 같은 데이터셋 불균형 문제는 모델의 학습에도 좋지 않은 영향을 끼쳐, 아이나 노인같이 데이터가 적은 나이의 사람이 인공지능 모델을 사용할 때 사회활동이 활발한 나이의 사람이 사용할 때보다 성능이 떨어질 수 있고, 이들의 인공지능 모델 사용을 어렵게 할 가능성이 높다. 이를 개선하기 위해 본 논문은 특징 분해를 활용하여 얼굴 영상으로부터 나이를 분류하고 목표 나이로 합성하는 기법을 제안한다. 제안하는 기법은 FFHQ-Aging 데이터셋을 이용한 정량적, 정성적 평가를 통해 기존의 방법보다 더 나은 성능을 보인다.

• Journal of Platform Technology
• /
• 제11권4호
• /
• pp.3-12
• /
• 2023

포스트-코로나 시대에는 방역 조치의 중요성이 크게 강조되고 있으며, 이에 맞춰 딥러닝을 이용한 마스크 착용 상태 검출 및 다른 전염병 예방에 관련된 연구가 진행되고 있다. 그러나 질병 확산 방지를 위한 문화시설 관람객 탐지 및 추적 연구도 마찬가지로 중요하므로 이에 대한 연구가 진행되어야 한다. 본 논문에서는 사전 수집된 데이터 셋을 이용하여 컨볼루션 신경망 기반 객체 탐지 모델을 전이 학습시키고, 학습된 탐지 모델의 가중치를 다중 객체 추적 모델에 적용하여 방문객을 모니터링 한다. 방문객 탐지 모델은 Precision 96.3%, Recall 85.2% F1-Score 90.4%의 결과를 보여주었다. 추적 모델의 정량적 결과로 MOTA 65.6%, IDF1 68.3%. HOTA 57.2%의 결과를 보여주었으며, 본 논문의 모델과 다른 다중 객체 추적 모델 간의 정성적 비교에서 우수한 결과를 보여주었다. 본 논문의 연구는 포스트-코로나 시대의 문화시설 내 방역 시스템에 적용될 수 있을 것이다.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1997년도 춘계학술대회논문집
• /
• pp.56-60
• /
• 1997

The study of human erroneous actions has traditionally taken place along two different lines of approach. One has been concerned with finding and explaining the causes of erroneous actions, such as studies in the psychology of "error". The other has been concerned with the qualitative and quantitative prediction of possible erroneous actions, exemplified by the field of human reliability analysis (HRA). Another distinction is also that the former approach has been dominated by an academic point of view, hence emphasising theories, models, and experiments, while the latter has been of a more pragmatic nature, hence putting greater emphasis on data and methods. We have been developing a method to make predictions about error modes. The input to the method is a detailed task description of a set of scenarios for an experiment. This description is then analysed to characterise thd nature of the individual task steps, as well as the conditions under which they must be carried out. The task steps are expressed in terms of a predefined set of cognitive activity types. Following that each task step is examined in terms of a systematic classification of possible error modes and the likely error modes are identified. This effectively constitutes a qualitative analysis of the possibilities for erroneous action in a given task. In order to evaluate the accuracy of the predictions, the data from a large scale experiment were analysed. The experiment used the full-scale nuclear power plant simulator in the Halden Man-Machine Systems Laboratory (HAMMLAB) and used six crews of systematic performance observations by experts using a pre-defined task description, as well as audio and video recordings. The purpose of the analysis was to determine how well the predictions matiched the actually observed performance failures. The results indicated a very acceptable rate of accuracy. The emphasis in this experiment has been to develop a practical method for qualitative performance prediction, i.e., a method that did not require too many resources or specialised human factors knowledge. If such methods are to become practical tools, it is important that they are valid, reliable, and robust.

• 한국측량학회지
• /
• 제40권1호
• /
• pp.23-30
• /
• 2022

최근 딥러닝을 이용한 이미지 매팅 방법에 관한 다양한 연구가 진행되고 있다. 특히, 사진측량 분야에서도 고품질의 실감모형을 제작하기 위해서는 촬영된 이미지에서 유물 정보를 추출하는 과정이 필요하며, 이와 같은 과정은 많은 시간과 인력이 들어 기존에는 크로마키를 이용하여 추출하는 방법이 많이 활용되고 있다. 그러나, 기존의 방법은 세부 분류에 대한 정확도가 떨어져 고품질 실감모형에 적용하기에는 어려움이 있었다. 본 연구에서는 사전배경정보와 훈련된 학습데이터를 이용하여 고해상도 유물 이미지에서 배경정보를 제거하고 추출된 유물 이미지에 대하여 정성적, 정량적 결과를 평가하였다. 그 결과 제안된 방법과 FBA(매뉴얼 트라이맵)이 정량적으로 높은 결과를 나타냈으며, 정성적 평가에서도 유물 주변부의 분류도가 높은 정확도를 보였다. 따라서 제안된 방법은 고해상도 유물 이미지 분류에 있어 사전배경정보 취득을 통하여 높은 정확도와 빠른 처리 속도를 나타냈으며, 실내 유물 촬영에서 그 활용 가능성을 확인하였다.

• Earthquakes and Structures
• /
• 제22권5호
• /
• pp.503-515
• /
• 2022

This paper presents the development of seismic fragility curves for a precast reinforced concrete bridge instrumented with a structural health monitoring (SHM) system. The bridge is located near an active seismic fault in the Dominican Republic (DR) and provides the only access to several local communities in the aftermath of a potential damaging earthquake; moreover, the sample bridge was designed with outdated building codes and uses structural detailing not adequate for structures in seismic regions. The bridge was instrumented with an SHM system to extract information about its state of structural integrity and estimate its seismic performance. The data obtained from the SHM system is integrated with structural models to develop a set of fragility curves to be used as a quantitative measure of the expected damage; the fragility curves provide an estimate of the probability that the structure will exceed different damage limit states as a function of an earthquake intensity measure. To obtain the fragility curves a digital twin of the bridge is developed combining a computational finite element model and the information extracted from the SHM system. The digital twin is used as a response prediction tool that minimizes modeling uncertainty, significantly improving the predicting capability of the model and the accuracy of the fragility curves. The digital twin was used to perform a nonlinear incremental dynamic analysis (IDA) with selected ground motions that are consistent with the seismic fault and site characteristics. The fragility curves show that for the maximum expected acceleration (with a 2% probability of exceedance in 50 years) the structure has a 62% probability of undergoing extensive damage. This is the first study presenting fragility curves for civil infrastructure in the DR and the proposed methodology can be extended to other structures to support disaster mitigation and post-disaster decision-making strategies.

• 천문학회보
• /
• 제46권1호
• /
• pp.42.1-42.1
• /
• 2021

In this study, we present a visual explanation of a deep learning solar flare forecast model and its relationship to physical parameters of solar active regions (ARs). For this, we use full-disk magnetograms at 00:00 UT from the Solar and Heliospheric Observatory/Michelson Doppler Imager and the Solar Dynamics Observatory/Helioseismic and Magnetic Imager, physical parameters from the Space-weather HMI Active Region Patch (SHARP), and Geostationary Operational Environmental Satellite X-ray flare data. Our deep learning flare forecast model based on the Convolutional Neural Network (CNN) predicts "Yes" or "No" for the daily occurrence of C-, M-, and X-class flares. We interpret the model using two CNN attribution methods (guided backpropagation and Gradient-weighted Class Activation Mapping [Grad-CAM]) that provide quantitative information on explaining the model. We find that our deep learning flare forecasting model is intimately related to AR physical properties that have also been distinguished in previous studies as holding significant predictive ability. Major results of this study are as follows. First, we successfully apply our deep learning models to the forecast of daily solar flare occurrence with TSS = 0.65, without any preprocessing to extract features from data. Second, using the attribution methods, we find that the polarity inversion line is an important feature for the deep learning flare forecasting model. Third, the ARs with high Grad-CAM values produce more flares than those with low Grad-CAM values. Fourth, nine SHARP parameters such as total unsigned vertical current, total unsigned current helicity, total unsigned flux, and total photospheric magnetic free energy density are well correlated with Grad-CAM values.