Given the hazards posed by black ice, it is crucial to investigate the conditions that contribute to its formation. Two ensemble machinelearning algorithms, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), were employed to forecast the occurrence of black ice using atmospheric data. Additionally, explainable artificial intelligence techniques, including Feature Importance (FI) and partial dependence Plot (PDP), were utilized to identify atmospheric conditions that significantly increase the likelihood of black ice formation. The machinelearning algorithms achieved a forecasting accuracy of 90%, demonstrating reliable performance. FI analysis revealed distinct key predictors between the algorithms: relative humidity was the most critical for RF, whereas wind speed was paramount for XGBoost. The PDP analysis identified the specific atmospheric conditions under which black ice was likely to form. This study provides detailed insights into the atmospheric precursors of frost/fog-induced black ice formation. These findings enable road managers to implement proactive winter road maintenance strategies, such as optimizing anti-icing patrol routes and displaying warnings on various message signs, thereby enhancing road safety.

This study evaluated the short- and long-term prediction performances of a transformer-based trajectory-forecasting model for urban intersections. While a previous study focused on developing the basic structure of a transformer model for future trajectory prediction, the present study aimed to determine a practical prediction sequence length. To this end, multiple transformer models were trained with output sequence lengths ranging from 1 s to 10 s, and their performances were compared. The trajectory data used for training were generated through a microscopic traffic simulation, and the model accuracy was assessed using the metrics average displacement error (ADE) and final displacement error (FDE). The results demonstrate that the prediction accuracy decreases significantly when the output trajectory length exceeds 3 s. Specifically, straight-driving trajectories exhibit rapidly increasing errors, while turning trajectories maintained a relatively stable accuracy. In contrast, for turning-driving trajectories, prediction errors increased sharply during short-term forecasting, but the increase was more gradual in long-term forecasts. Additionally, the long-term prediction models produced higher errors even in the initial 1-second outputs, implying a tendency toward conservative inference under uncertain future scenarios. This conservative behavior is likely influenced by the model’s effort to minimize the overall loss across a broader prediction window, especially when trained with Smooth L1 loss function. This study provides practical insights into model design for edge-computing environments and contributes to the development of reliable short-term trajectory prediction systems for urban ITS applications.

기후 변화로 인해 해수면 상승과 폭풍해일 발생 빈도가 증가하면서, 해안 지역에서의 재난 위험이 심화되고 있다. 본 연구는 NOAA의 GFS(Global Forecast System) 모델과 일본 기상청의 JMA-MSM(Japan Meteorological Agency Meso-Scale Model) 데이터를 기반으로 딥 러닝 기술을 활용하여 폭풍해일 예측 알고리즘을 개발하고, 두 모델에서 제공하는 대기 데이터를 입력 변수로 사용하여 예측 성능을 비 교하는 것을 목표로 한다. CNN(Convolutional Neural Network), LSTM(Long Short-Term Memory), Attention 메커니즘을 결합한 모델을 설계하고, 조위관측소의 관측 자료를 학습 데이터로 사용하였다. 과거 한반도에 직접적인 영향을 미쳤던 네 개의 태풍 사례를 통해 모델 성능을 검 증한 결과, JMA-MSM 기반 모델이 GFS 기반 모델에 비해 서해, 남해, 동해에서 각각 평균 RMSE를 0.34cm, 0.73cm, 1.86cm, MAPE를 0.15%, 0.36%, 0.68% 개선하였다. 이는 JMA-MSM의 고해상도 자료가 지역적 기상 변화를 정밀하게 반영했기 때문으로 분석된다. 본 연구는 해안 재난 대비를 위한 폭풍해일 예측의 효율성을 높이고, 추가 기상 데이터를 활용한 향후 연구의 기반 제공이 기대된다.

This study aimed to develop a pavement management system suitable for the climate and traffic characteristics of Gangwon Province. This research focused on analyzing the asphalt pavement performance characteristics of national highways in Gangwon Province by region and developing prediction models for the current pavement performance and annual changes in performance. Quantitative indicators were collected to evaluate the condition of national highway pavements in Gangwon Province, including factors affecting road performance, such as weather data and traffic volume. The Gangwon region was then classified according to its topography, climate, weather, traffic volume, and pavement performance. Prediction models for the current pavement performance and annual changes in performance were developed for national highways. This study also compared the predicted values for the Gangwon region using a nationwide pavement performance-prediction model from other studies with the predicted values from the developed annual changes in the performance prediction model. This study established a foundation for implementing a pavement management system tailored to the unique climate and traffic characteristics of Gangwon Province. By developing region-specific performance prediction models, this study provided valuable insights into more effective and efficient pavement maintenance strategies in Gangwon Province.

In this study, the magnetocaloric effect and transition temperature of bulk metallic glass, an amorphous material, were predicted through machine learning based on the composition features. From the Python module ‘Matminer’, 174 compositional features were obtained, and prediction performance was compared while reducing the composition features to prevent overfitting. After optimization using RandomForest, an ensemble model, changes in prediction performance were analyzed according to the number of compositional features. The R2 score was used as a performance metric in the regression prediction, and the best prediction performance was found using only 90 features predicting transition temperature, and 20 features predicting magnetocaloric effects. The most important feature when predicting magnetocaloric effects was the ‘Fe’ compositional ratio. The feature importance method provided by ‘scikit-learn’ was applied to sort compositional features. The feature importance method was found to be appropriate by comparing the prediction performance of the Fe-contained dataset with the full dataset.

본 논문에서는 대규모 실시간 매칭의 생존 게임에서 플레이를 위한 유저들의 소셜 관계에 대해 연구한다. 특 히 “사전 팀 구성”을 통한 자의적인 팀 구성이 어떤 방식으로 유저들을 연결하는 지 연구하고자 한다. 다수 의 사람 간 집단 역학에서 나타나는 특성이나 패턴에 대한 조사를 중심으로 하였으며, 개인의 특성은 보조적 인 수단으로만 사용된다. 이번 연구에서는 게임을 플레이하는 유저들의 익명화 된 대규모 데이터를 활용하며 이에 대한 간소화된 집계 방법을 제안한다. 데이터 세트에는 사전 팀 구성에 관한 11,259만 줄의 속성이 포 함되어 있으며, 데이터에서 우리는 250만개의 노드와 1,182만개의 무방향 에지가 있는 협업 네트워크를 구성 하여 대규모 게임 내 협동 네트워크를 만듭니다. 연결 정도, 경로 길이, 클러스터링 및 소속 하위 컴포넌트의 크기 등 네트워크에 관한 수치를 통해 게임내 소셜 활동에 대한 이해를 높이고자 한다. 본 논문에서는 다음 의 두가지 특성을 중심으로 결론을 제시한다. 첫째, 네트워크 내에는 대규모로 연결된 2개(전체의 44% 및 2%)와 나머지의 파편화된 하위 컴포넌트로 구성 되어있다. 이 대규모 컴포넌트 중 작은 쪽은 한국 유저로만 구성되어 있다. 둘째, 컴포넌트 크기 별 평균 연결 거리와 군집화 계수, k-core를 확인함으로써 기타 다른 네 트워크 대비 이웃 간 연결이 강하면서 전체적으로는 비교적 멀리 떨어져 있음을 확인한다.

본 연구는 네트워크 이상 감지 및 예측을 위해 벡터 자기회귀(VAR) 모델의 사용을 비교 분석한다. VAR 모 델에 대한 간략한 개요를 제공하고 네트워크 이상 체크로 사용 가능한 두 가지 버전을 검토하며 두 종류의 VAR 모델을 통한 경험적인 평가를 제시한다. VAR-Filtered moving-common-AR 모델이 단일 노드 이상 감지 성능에서 우수하며, VAR-Adaptive Learning 버전은 몇 개의 노드 간 이상을 효과적으로 식별하는 데 특히 효 과적이며 두 가지 주요VAR 모델의 전반적인 성능 차이에 대한 근본적인 이유도 분석한다. 각 기술의 장단점 을 개요로 제공하고 성능 향상을 위한 제안도 제시하고자 한다.

Determining the size or area of a plant's leaves is an important factor in predicting plant growth and improving the productivity of indoor farms. In this study, we developed a convolutional neural network (CNN)-based model to accurately predict the length and width of lettuce leaves using photographs of the leaves. A callback function was applied to overcome data limitations and overfitting problems, and K-fold cross-validation was used to improve the generalization ability of the model. In addition, ImageDataGenerator function was used to increase the diversity of training data through data augmentation. To compare model performance, we evaluated pre-trained models such as VGG16, Resnet152, and NASNetMobile. As a result, NASNetMobile showed the highest performance, especially in width prediction, with an R_squared value of 0.9436, and RMSE of 0.5659. In length prediction, the R_squared value was 0.9537, and RMSE of 0.8713. The optimized model adopted the NASNetMobile architecture, the RMSprop optimization tool, the MSE loss functions, and the ELU activation functions. The training time of the model averaged 73 minutes per Epoch, and it took the model an average of 0.29 seconds to process a single lettuce leaf photo. In this study, we developed a CNN-based model to predict the leaf length and leaf width of plants in indoor farms, which is expected to enable rapid and accurate assessment of plant growth status by simply taking images. It is also expected to contribute to increasing the productivity and resource efficiency of farms by taking appropriate agricultural measures such as adjusting nutrient solution in real time.

This study was conducted to develop a model for predicting the growth of kimchi cabbage using image data and environmental data. Kimchi cabbages of the ‘Cheongmyeong Gaual’ variety were planted three times on July 11th, July 19th, and July 27th at a test field located at Pyeongchang-gun, Gangwon-do (37°37′ N 128°32′ E, 510 elevation), and data on growth, images, and environmental conditions were collected until September 12th. To select key factors for the kimchi cabbage growth prediction model, a correlation analysis was conducted using the collected growth data and meteorological data. The correlation coefficient between fresh weight and growth degree days (GDD) and between fresh weight and integrated solar radiation showed a high correlation coefficient of 0.88. Additionally, fresh weight had significant correlations with height and leaf area of kimchi cabbages, with correlation coefficients of 0.78 and 0.79, respectively. Canopy coverage was selected from the image data and GDD was selected from the environmental data based on references from previous researches. A prediction model for kimchi cabbage of biomass, leaf count, and leaf area was developed by combining GDD, canopy coverage and growth data. Single-factor models, including quadratic, sigmoid, and logistic models, were created and the sigmoid prediction model showed the best explanatory power according to the evaluation results. Developing a multi-factor growth prediction model by combining GDD and canopy coverage resulted in improved determination coefficients of 0.9, 0.95, and 0.89 for biomass, leaf count, and leaf area, respectively, compared to single-factor prediction models. To validate the developed model, validation was conducted and the determination coefficient between measured and predicted fresh weight was 0.91, with an RMSE of 134.2 g, indicating high prediction accuracy. In the past, kimchi cabbage growth prediction was often based on meteorological or image data, which resulted in low predictive accuracy due to the inability to reflect on-site conditions or the heading up of kimchi cabbage. Combining these two prediction methods is expected to enhance the accuracy of crop yield predictions by compensating for the weaknesses of each observation method.

Recently, as the possibility of unexpected outbreaks of alien insects has increased due to climate change such as global warming, the importance of early control through rapid and accurate spread of exotic forest pest and change prediction diagnosis is required. This study summarizes and reports the followings: the establishment of monitoring strategy for exotic insects by the investigation of species distribution range through field surveys and others, the development of new diagnostic technique through microstructures and life-cycle, the dispersal of exotic insects, and ecological impact assessment using ecological methods and with the expansion of exotic insects and development of ecosystem impact prediction model.

Due to COVID-19, changes in consumption trends are taking place in the distribution sector, such as an increase in non-face-to-face consumption and a rapid growth in the online shopping market. However, it is difficult for small and medium-sized export sellers to obtain forecast information on the export market by country, compared to large distributors who can easily build a global sales network. This study is about the prediction of export amount and export volume by country and item for market information analysis of small and medium export sellers. A prediction model was developed using Lasso, XGBoost, and MLP models based on supervised learning and deep learning, and export trends for clothing, cosmetics, and household electronic devices were predicted for Korea's major export countries, the United States, China, and Vietnam. As a result of the prediction, the performance of MAE and RMSE for the Lasso model was excellent, and based on the development results, a market analysis system for small and medium sellers was developed.

Radioactive contaminants, such as 137Cs, are a significant concern for long-term storage of nuclear waste. Migration and retention of these contaminants in various environmental media can pose a risk to the surrounding environment. The distribution coefficient (Kd) is a critical parameter for assessing the behavior of these contaminants and can introduce significant errors in predicting migration and remediation options. Accurate prediction of Kd values is essential to assess the behavior of radioactive contaminants and to ensure environmental safety. In this study, we present machine learning models based on the Japan Atomic Energy Agency Sorption Database (JAEA-SDB) to predict Kd values for Cs in soils. We used three different machine learning models, namely the random forest (RF), artificial neural network (ANN), and convolutional neural network (CNN), to predict Kd values. The models were trained on 14 input variables from the JAEA-SDB, including factors such as Cs concentration, solid phase properties, and solution conditions which are preprocessed by normalization and log transformation. We evaluated the performance of our models using the coefficient of determination (R2) value. The RF, ANN, and CNN models achieved R2 values of over 0.97, 0.86, and 0.88, respectively. Additionally, we analyzed the variable importance of RF using out-of-bag (OOB) and CNN with an attention module. Our results showed that the initial radionuclide concentration and properties of solid phase were important variables for Kd prediction. Our machine learning models provide accurate predictions of Kd values for different soil conditions. The Kd values predicted by our models can be used to assess the behavior of radioactive contaminants in various environmental media. This can help in predicting the potential migration and retention of contaminants in soils and the selection of appropriate site remediation options. Our study provides a reliable and efficient method for predicting Kd values that can be used in environmental risk assessment and waste management.

PURPOSES : The main purpose of this study is to identify directions for improvement of triangular islands installation warrants through analysis of the characteristics of crashes and severity with and without triangular islands on intersections. METHODS : The data was collected by referring to the literature and analyzed using statistical analysis tools. First, an independence test analyzed whether statistically significant differences existed between crashes depending on the installation of triangular islands. As a result of the analysis, individual prediction models were developed for cases with significant differences. In addition, each crash factor was derived by comparison with each model. RESULTS : Significant differences appeared in the "crash frequency of serious or fatal" and "crash severity" owing to the installation of triangular islands. As a result of comparing crash factors through the individual models, it was derived that the differences were dependent on the installation of the triangular islands. CONCLUSIONS : As a result of reviewing previous studies, it is found that improving the installation warrants of triangular islands is reasonable. Through this study, the need to consider the volume and composition ratio of right-turn vehicles when installing a triangular island was also derived; these results also need to be referred to when improving the triangular island installation warrants.

Predicting remaining useful life (RUL) becomes significant to implement prognostics and health management of industrial systems. The relevant studies have contributed to creating RUL prediction models and validating their acceptable performance; however, they are confined to drive reasonable preventive maintenance strategies derived from and connected with such predictive models. This paper proposes a data-driven preventive maintenance method that predicts RUL of industrial systems and determines the optimal replacement time intervals to lead to cost minimization in preventive maintenance. The proposed method comprises: (1) generating RUL prediction models through learning historical process data by using machine learning techniques including random forest and extreme gradient boosting, and (2) applying the system failure time derived from the RUL prediction models to the Weibull distribution-based minimum-repair block replacement model for finding the cost-optimal block replacement time. The paper includes a case study to demonstrate the feasibility of the proposed method using an open dataset, wherein sensor data are generated and recorded from turbofan engine systems.