AI-driven automation for structural design has been actively studied in structural engineering. In particular, reinforcement learning (RL) has attracted attention as a framework in which an agent interacts with an environment to autonomously search for optimal design solutions in complex design spaces. This study proposes an automated design model for rectangular reinforced-concrete (RC) columns based on a multi-agent Double Deep Q-Network (Double DQN). Extending prior RL-based automation developed for RC beam design to column members, the proposed environment explicitly incorporates key column-specific behaviors, including axial force–bending moment (P–M) interaction and moment magnification due to column buckling. Four agents independently determine the section width (b), section depth (h), number of longitudinal bars (n), and bar size. The reward function combines (i) penalty terms for violations of ACI 318-19 design constraints and (ii) an economic reward defined relative to an approximate optimal cost predicted by a quadratic regression model. After training for approximately 10,000 episodes, the proposed multi-agent Double DQN consistently generated ACI-compliant column designs across all test load cases and produced solutions with improved cost efficiency compared with the approximate optimal baseline. These results demonstrate the feasibility and practical potential of multi-agent RL for automated RC column section design.

This study estimated whole crop maize (WCM; Zea mays L.) yield damage under abnormal climate conditions using a machine-learning approach based on Representative Concentration Pathway (RCP) 8.5 and visualized the results as spatial maps. A total of 3,232 WCM observations were compiled, and climate data were obtained from the Korea Meteorological Administration (KMA) Open Data Portal. The machine learning model used DeepCrossing. Dry matter yield (DMY) was predicted using the DeepCrossing model and climate data from the Automated Synoptic Observing System (ASOS; 95 stations). The calculation of damage was the difference between the DMYnormal and DMYabnormal. The normal climate was set as the 40-year of climate data according to the year of WCM data (1978-2017). The level of abnormal climate by temperature and precipitation was set as RCP 8.5 standard. The predicted DMYnormal ranged from 13,845-19,347 kg/ha. The damage from WCM varied by region and the severity of abnormal climate, including abnormal temperature and precipitation. Under abnormal temperature conditions, damage in 2050 and 2100 ranged from –243 to –133 and –1,797 to –245 kg/ha, respectively. Under abnormal precipitation conditions, damage in 2050 and 2100 ranged from –2,998 to 1,447 and –11,308 to 29 kg/ha, respectively. Overall, DMY of WCM tended to increase with higher mean monthly temperature. The damage calculated through the RCP 8.5 standard was presented as a spatial distribution using QGIS. Although this study used an RCP scenario based on greenhouse gas concentrations, further research is needed to apply an integrated Shared Socioeconomic Pathway (SSP) that accounts for socioeconomic factors.

Crash risk in metropolitan areas arises from the interaction among driver behavior, enforcement infrastructure, and urban environmental conditions; however, microspatial evidence remains scarce. This study examines the effects of automated speed-enforcement cameras on the crash risk in Seoul at the legal-dong level using the accident risk index, which accounts for both crash frequency and injury severity. The dataset combines crash records, enforcement infrastructure, school-zone information, demographic indicators, and land-use characteristics. Methodologically, a Bayesian negative binomial regression model was employed to address overdispersed crash data, whereas gradient-boosting machine and eXtreme Gradient Boosting models with SHAP interpretations were applied to capture nonlinear effects, heterogeneity, and variable interactions. The results reveal that the crash risk is spatially concentrated, with a small proportion of districts contributing disproportionately to the overall exposure. Regression analysis highlights enforcement and behavioral factors as significant predictors, whereas machine-learning models emphasize the added importance of structural and demographic characteristics, such as road area and floating population. This divergence reflects the sensitivity of the regression to collinearity and linearity assumptions in contrast to the flexibility of tree-based methods in uncovering nonlinear and context-dependent influences. In general, the findings reflect the value of integrating statistical and machine-learning approaches for a more comprehensive understanding of crash risk at the microspatial scale. This study advances the methodological diversity in traffic-safety research and provides practical evidence that cameradeployment strategies should be context sensitive while targeting areas with concentrated risks and distinct structural and demographic profiles.

This study investigates the seismic fragility of nuclear power plant (NPP) auxiliary structures by incorporating material aging deterioration into machine learning–based response prediction models. An artificial neural network (ANN) was developed using 17 seismic and material parameters, achieving high predictive accuracy (R2 = 0.96) while significantly reducing computational demands compared with conventional finite element analyses. By combining the ANN with Monte Carlo simulations, fragility curves for Motor Control Center (MCC) cabinet anchors were derived at resonance frequencies of 10 Hz and 15 Hz. Results indicate that equipment with higher resonance frequency (15 Hz) exhibits lower seismic vulnerability due to reduced sensitivity to dominant low-frequency seismic components. When material deterioration was introduced, fragility curves shifted toward lower ground motion intensities, reflecting increased failure probabilities and approximately 20% reduction in median seismic capacity. These findings highlight the necessity of considering aging effects in probabilistic seismic risk assessments and demonstrate the efficiency of ML-based surrogate models for quantifying long-term safety margins of NPP structures.

This study compares the shear behavior of anisotropic magnetorheological elastomers (MREs) using natural rubber (NR) and silicone rubber (Si) as matrices. The effects of magnetic flux density and compressive pre-stress on the shear modulus were experimentally investigated. Results showed that silicone-based MREs exhibited a 10–20% higher magnetorheological effect than NR-based ones due to stronger particle–matrix bonding and stable chain alignment under magnetic fields. In contrast, NR-based MREs showed greater stiffness variation under compressive stress, attributed to strain-hardening and volumetric constraint effects. These findings indicate that matrix selection significantly governs the magneto-mechanical response: silicone MREs are suitable for precision control and sensing, while NR MREs perform better in high-stress damping systems. This study provides fundamental insight for tailoring MREs according to design requirements.

국제해운의 탈탄소 전환과 IMO GHG 전략에 따른 규제 강화로 선박별 정밀 배출 산정이 요구되고 있다. 그러나 실제 운항 선 박의 주기관 출력 정보는 외부 데이터베이스에 의존하는 경우가 많아 데이터 수집 단계에서 상당한 경제적 비용과 시간 지연이 발생한 다. 이러한 제약을 완화하기 위해, 본 연구는 AIS 정적 정보 중 선체길이를 단일 입력변수로 활용하여 선종별 주기관 출력을 기계학습으 로 추정하는 방법을 제안한다. 본 연구에서는 선형회귀, K-최근접이웃, 랜덤포레스트, 그래디언트부스팅, AdaBoost, XGBoost, LightGBM, CatBoost 등 8종의 기계학습 모델을 적용하였다. 수집한 데이터는 선종별로 분리한 뒤 무작위 분할하였고, 90% 학습셋에서 10-fold 교차검 증을 수행한 후 10% 홀드아웃 테스트로 최종 성능을 평가하였다. 테스트셋 기준 화물선은 CatBoost가 R²=0.96, 탱커선은 Gradient Boosting이 R²=0.96으로 가장 우수하였다. 여객선은 XGBoost가 R²=0.89, 예인선은 CatBoost가 R²=0.76을 보였다. 본 연구를 통해 AIS 데이터를 이용하여 주기관 출력을 추정할 수 있음을 확인하였다.

본 연구는 기계학습 및 설명 가능한 인공지능(xAI) 기법을 활용하여 폭발 하중을 받는 철근콘크리트 기둥의 보강 단계(Retrofit Level, RL)를 신속하게 평가하는 종합적 프레임워크를 제시한다. 파괴 유형와 보강 요구사항을 예측하기 위한 다단계 기계학습 접근 법을 개발하였으며, 이후 부분 의존성 그래프(Partial Dependence Plot, PDP) 분석을 통해 데이터 기반 보강 전략을 수립하였다. 제안 된 프레임워크는 두 가지 주요 프로세스로 구성된다: (1) 파괴유형 분류 및 RL 예측을 위한 다단계 기계학습 모델을 활용한 폭발 성능 평가, (2) 입력 변수 효과의 체계적 분석을 통한 PDP 기반 보강 전략 개발. RL 예측 모델은 광범위한 폭발 손상 평가 데이터를 바탕으 로 학습되었으며, 휨 및 전단 파괴유형에 대해 세 가지 손상 조건(심각, 보통, 경미)에서 검증되었다. PDP 분석 결과, 파괴유형과 손상 조건에 따라 서로 다른 보강 특성이 나타남을 확인하였다. PDP 기반 분석을 통해 주철근비 및 전단철근비에 대한 보강 가능 구간과 불가능 구간을 성공적으로 식별하였다.

In this study, chemicals with acute toxicity experimental data were selected as research subjects, and compareed the model derived from statistical analysis and QSAR open-source programs. The physical and chemical properties, dynamic behaviors, and toxicological estimates of the chemicals were calculated using Mordred, a molecular descriptor calculation program based on RDKit. LD50 was set as the toxicity comparison target for each chemical, and independent variables or factors with similarity to independent variables were estimated from the molecular descriptors calculated through Mordred. Molecule descriptors composed of independent variables were compared to predictions from QSAR open-source models, A regression model was created with the selected molecule descriptors and compared with predictions from QSAR programs, confirming high accuracy for specific functional groups. The QSAR model created in this study considers the characteristics and experimental values of each chemical, and provides evidence for selecting variables when constructing toxicity data for machine learning applications.

This study proposes a methodology for predicting the physical properties such as the density of polymer composites, including asphalt binders, and evaluates its feasibility by identifying the quantitative relationship between the structure and properties of individual polymers. To this end, features are constructed using molecular dynamics (MD) simulation results and descriptor calculation tools. This study investigates the changes in the calculated density depending on the characteristics of the training dataset and analyzes the feature characteristics across datasets to identify key features. In this study, 2,415 hydrocarbon and binder-derived polymer molecules were analyzed using MD simulations and 2,790 chemical descriptors generated using alvaDesc. The features were pre-processed using correlation filtering, PCA, and recursive feature elimination. The XGBoost models were trained using k-fold cross-validation and Optuna optimization. SHAP analysis was used to interpret feature contributions. The variables influencing the density prediction differed between the hydrocarbon and binder groups. However, the hydrogen atom count (H), van der Waals energy, and descriptors such as SpMAD_EA_LboR consistently had a strong impact. The trained models achieved high accuracy (R² > 0.99) across different datasets, and the SHAP results revealed that the edge adjacency, topological, and 3D geometrical descriptors were critical. In terms of predictive accuracy and interpretability, the integrated MDQSPR framework demonstrated high reliability for estimating the properties of individual binder polymers. This approach contributed to a molecular-level understanding and facilitated the development of ecofriendly and efficient modifiers for asphalt binders.

As demand grows for electric vehicles and advanced mobility technologies, developing materials for permanent magnets has become increasingly essential. Among them, SmCo-based permanent magnets are gaining attention due to their superior thermal stability compared to conventional NdFeB magnets, making them promising candidates for high-temperature motor applications. However, optimizing the magnetic properties of SmCo alloys remains challenging due to their complex phase structures and elemental interactions. In this study, we develop and optimize machine learning (ML) models to predict the saturation magnetization of SmCo permanent magnets using only composition-based descriptors. A dataset comprising various SmCo alloys was analyzed, with features extracted using Matminer and Pymatgen modules. We applied Random Forest (RF), eXtreme Gradient Boosting (XGB), and Support Vector Regression (SVR) models and compared their regression performance using R2 score and Root-mean-squared-error (RMSE). The RF model demonstrated the best generalization and prediction accuracy. To identify the most influential features, we used permutation feature importance. Further, we refined the feature set using a genetic algorithm (GA), ultimately selecting 9 key features that yielded the highest model performance (R2 = 0.963, RMSE = 4.22 emu/g). This study highlights the potential of combining machine learning with genetic optimization to accelerate the design of high-performance, thermally stable SmCo permanent magnets.

The present study introduces a machine learning approach for designing new aluminum alloys tailored for directed energy deposition additive manufacturing, achieving an optimal balance between hardness and conductivity. Utilizing a comprehensive database of powder compositions, process parameters, and material properties, predictive models—including an artificial neural network and a gradient boosting regression model, were developed. Additionally, a variational autoencoder was employed to model input data distributions and generate novel process data for aluminum-based powders. The similarity between the generated data and the experimental data was evaluated using K-nearest neighbor classification and t-distributed stochastic neighbor embedding, with accuracy and the F1-score as metrics. The results demonstrated a close alignment, with nearly 90% accuracy, in numerical metrics and data distribution patterns. This work highlights the potential of machine learning to extend beyond multi-property prediction, enabling the generation of innovative process data for material design.

This study explores a pedagogical approach to learning modern Greek imperative forms using machine translation and evaluates its relevance in language education. While imperatives frequently appear in textbooks and exams, they present challenges for beginners, highlighting the need for effective instruction. Machine translation can serve as a practical learning aid in this context. The study h as tw o k ey a ims: e valuating t he q uality of G reek-to-Korean imperative sentence translations from Google Translate and DeepL, and identifying effective learning activities for helping students recognize and acquire imperative forms, specifically in instructional texts. The analysis shows that although machine translation captures core meanings, it struggles with contextually accurate expressions and complex syntax. The study suggests using machine translation to familiarize beginners with imperative forms and support intuitive learning. For more advanced learners, comparing machine and human translations can promote deeper grammatical understanding. Ultimately, machine translation can function not only as a translation tool but also as a means for linguistic analysis and grammar awareness in second language learning.

Seismically deficient reinforced concrete(RC) structures experience reduced structural capacity and lateral resistance due to the increased axial loads resulting from green retrofitting and vertical extensions. To ensure structural safety, traditional performance assessment methods are commonly employed. However, the complexity of these evaluations can act as a barrier to the application of green retrofitting and vertical extensions. This study proposes a methodology for rapidly calculating the allowable axial force range of RC buildings by leveraging simplified structural details and seismic wave information. The methodology includes three machine-learning-based models: (1) predicting column failure modes, (2) assessing seismic performance under current conditions, and (3) evaluating seismic performance under amplified mass conditions. A machine learning model was specifically developed to predict the seismic performance of an RC moment frame building using structural details, gravity loads, failure modes, and seismic wave data as input variables, with dynamic response-based seismic performance evaluations as output data. Classifiers developed using various machine learning methodologies were compared, and two optimal ensemble models were selected to effectively predict seismic performance for both current and increased mass scenarios.

Existing reinforced concrete buildings with seismically deficient columns experience reduced structural capacity and lateral resistance due to increased axial loads from green remodeling or vertical extensions aimed at reducing CO2 emissions. Traditional performance assessment methods face limitations due to their complexity. This study aims to develop a machine learning-based model for rapidly assessing seismic performance in reinforced concrete buildings using simplified structural details and seismic data. For this purpose, simple structural details, gravity loads, failure modes, and construction years were utilized as input variables for a specific reinforced concrete moment frame building. These inputs were applied to a computational model, and through nonlinear time history analysis under seismic load data with a 2% probability of exceedance in 50 years, the seismic performance evaluation results based on dynamic responses were used as output data. Using the input-output dataset constructed through this process, performance measurements for classifiers developed using various machine learning methodologies were compared, and the best-fit model (Ensemble) was proposed to predict seismic performance.

The purpose of this study is to examine learners’ perceptions of AI-based machine translation (MT) in high school ‘Reading British and American Literature’ classes. This research explored how students perceived the impact of MT on their class participation, learning motivation, confidence in English use, and improvement in English ability. The study also examined how the effectiveness of MT use differed according to students’ English proficiency levels. A total of 153 third-year students participated in a nine-week English literature course. Data were collected through an online survey and statistically analyzed. The findings reveal that students showed positive perceptions regarding class participation, learning motivation, confidence in English use, and improvement in English ability. Notably, participation in the English literature classes using AI-based MT was significantly higher than that in other English classes. Analysis by English proficiency levels showed no significant differences in class participation and affective factors (learning motivation and confidence). However, lower-proficiency learners perceived greater improvement in English proficiency compared to higher-proficiency learners. These results suggest that incorporating AI-based MT in English literature classes can create an inclusive learning environment that supports learners across different proficiency levels, particularly benefiting lower-proficiency students in terms of improvement in English ability.

본 연구는 성장 단계별 돼지의 평균 사료 섭취량을 추정하고, 각 매개변수 간의 상관분석을 통해 변수를 선별한 후, 기계학습 기반 회귀분석을 통해 돼지의 사료 섭취량(FI)을 예측하는 모델을 만들고자 한다. 본 실험은 2023년 9월 14일부터 2023년 12월 15일까지 93일 동안 진행하였다. 사료는 09:00와 17:00 하루에 2회 제공하였으며, 제공된 사료의 양은 돼지의 평균 체중의 5%를 지급하였다. 돼지의 몸무게(PBW)는 매일 09:00에 이동식 돈형기를 사용하여 측정하였다. 축산환경관리시스템(LEMS) 센서를 이용하여, 돈사 내 온도(RT), 상대습도(RH), NH3를 5분 간격으로 수집하였다. 성장 단계를 3단계로 나누었으며, 각 GS1, GS2 및 GS3으로 명명하였다. 각 성장 단계별 평균 사료 섭취량과 표준편차를 구하여, 유의미성과 성장 단계별 사료 섭취의 경향을 분석하였다. 각 모델의 성능평가( , RMSE, MAPE) 시 8:2의 비율로 데이터를 분할하여, 정확도 검증을 수행하였다. 연구 결과 성장 단계별 돼지의 사료 섭취량에 유의미한 차이(p < 0.05)가 있음과 돼지가 성장할수록 일정한 양의 사료를 섭취하는 것을 확인하였다. 또한 각 변수의 상관분석 시 FI와 PBW에서 강한 상관관계가 나타났으며(R > 0.94), 각 모델의 성능평가 결과 RFR 모델이 가장 높은 정확성(  = 0.959, RMSE = 195.9, MAPE = 5.739)을 보였다.

본 연구는 표현 형질 생육 데이터인 엽장, 엽 수와 기상 데이 터인 생육도일을 활용하여 여러 기계 학습을 통해 마늘의 생 체중을 예측하는 모델을 개발하고자 하였다. 검증 데이터에 서 random forest 모델의 결정계수가 0.924, 평균제곱근오차 (g)는 13.583 그리고 평균절대오차는 8.885로 가장 우수하였 다. 평가 데이터에서는 Catboost 모델이 결정계수가 0.928, 평균제곱근오차(g)는 13.486 그리고 평균절대오차는 9.181 로 가장 우수하였다. 그러나 Catboost, Random forest 그리고 LightGBM 모델을 0.5, 0.3 그리고 0.2 가중치를 두어 학습한 Weighted ensemble 모델이 마늘 생체중 예측의 검증 및 평가 에 있어서 검증 데이터의 결정계수가 0.922, 평균제곱근오차 (g)가 13.752 그리고 평균절대오차는 8.877이었으며 평가 데 이터에서는 결정계수가 0.923, 평균제곱근오차(g)가 13.992 그리고 평균절대오차가 9.437로 두 번째로 우수한 결과를 나 타내었다. 이러한 결과들을 종합적으로 미루어 보았을 때, Weighted ensemble 모델이 모델의 안정성 측면에서 최적의 모델이라고 판단하였다. 따라서 농가들이 표현 형질과 기상 데이터만으로도 기계학습 기법을 통하여 마늘의 생체중 예측 을 통해 작형 모니터링이 가능할 것으로 보이며 추가적으로 다년도 데이터 취득과 검증을 통하여 성능을 고도화가 가능할 것으로 판단된다.