• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• 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.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• 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.

• Journal of Korean Society of Water and Wastewater
• /
• v.36 no.4
• /
• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.155-162
• /
• 2022

In this paper, we examined the research trends and characteristics related to the metaverse in global journals published between 2000 and 2022 from the Web of Science database. The analysis included descriptive statistics, multidimensional scaling, keyword network analysis, and visualization. In addition, semantic network models were constructed, and centrality (betweenness and degree) analysis was performed using R and KH coder in two separate categories based on the trends and aspects of the publication: analysis period 1 (Jan 2000 to Dec 2020) and period 2 (Jan 2021 to Jun 2022). The results showed that the recent global research trends related to the metaverse could be quantitatively characterized using the semantic network analysis. Also, the results could be applied to suggest future research topics in the field of metaverse based on quantitative and empirical data.

• Journal of Broadcast Engineering
• /
• v.28 no.2
• /
• pp.238-241
• /
• 2023

Recently deep learning models are widely used for various tasks such as facial recognition and face editing. Their training process often involves a dataset with imbalanced age distribution. It is because some age groups (teenagers and middle age) are more socially active and tends to have more data compared to the less socially active age groups (children and elderly). This imbalanced age distribution may negatively impact the deep learning training process or the model performance when tested against those age groups with less data. To this end, we propose an age-controllable face synthesis technique using a feature decomposition to classify age from facial images which can be utilized to synthesize novel data to balance out the age distribution. We perform extensive qualitative and quantitative evaluation on our proposed technique using the FFHQ dataset and we show that our method has better performance than existing method.

• Journal of Platform Technology
• /
• v.11 no.4
• /
• pp.3-12
• /
• 2023

In the post-COVID era, the importance of quarantine measures is greatly emphasized, and accordingly, research related to the detection of mask wearing conditions and prevention of other infectious diseases using deep learning is being conducted. However, research on the detection and tracking of visitors to cultural facilities to prevent the spread of diseases is equally important, so research on this should be conducted. In this paper, a convolutional neural network-based object detection model is trained through transfer learning using a pre-collected dataset. The weights of the trained detection model are then applied to a multi-object tracking model to monitor visitors. The visitor detection model demonstrates results with a precision of 96.3%, recall of 85.2%, and an F1-score of 90.4%. Quantitative results of the tracking model include a MOTA (Multiple Object Tracking Accuracy) of 65.6%, IDF1 (ID F1 Score) of 68.3%, and HOTA (Higher Order Tracking Accuracy) of 57.2%. Furthermore, a qualitative comparison with other multi-object tracking models showcased superior results for the model proposed in this paper. The research of this paper can be applied to the hygiene systems within cultural facilities in the post-COVID era.

• Proceedings of the ESK Conference
• /
• 1997.04a
• /
• 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.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.1
• /
• pp.23-30
• /
• 2022

Recently, there are various studies underway on the deep learning-used image matting methods. Even in the field of photogrammetry, a process of extracting information about relics from images photographed is essential to produce a high-quality realistic model. Such a process requires a great deal of time and manpower, so chroma-key has been used for extraction so far. This method is low in accuracy of sub-classification, however, it is difficult to apply the existing method to high-quality realistic models. Thus, this study attempted to remove background information from high-resolution relic images by using prior background information and trained learning data and evaluate both qualitative and quantitative results of the relic images extracted. As a result, this proposed method with FBA(manual trimap) showed quantitatively better results, and even in the qualitative evaluation, it was high in accuracy of classification around relics. Accordingly, this study confirmed the applicability of the proposed method in the indoor relic photography since it showed high accuracy and fast processing speed by acquiring prior background information when classifying high-resolution relic images.

• Earthquakes and Structures
• /
• v.22 no.5
• /
• 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.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• 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.