Purpose: This study aimed to examine the impact of resilience and learning agility on organizational commitment among nurses who experienced job rotation. Methods: This descriptive correlational study was conducted with a convenience sample of 180 nurses who experienced job rotation within one year at a university hospital in C city. Data were collected from July to August 2022. A total of 176 valid responses were analyzed using scales measuring organizational commitment, resilience, and learning agility. Data analysis included descriptive statistics, Pearson's correlation coefficients, and multiple regression using the SPSS 27.0 program. Results: The results demonstrated that resilience emerged as the most significant predictor of organizational commitment among nurses who experienced job rotation, followed by satisfaction with their current department and the reason for departmental change. Conclusion: The results indicate that resilience significantly influences organizational commitment among job-rotated nurses. Future research should focus on developing and implementing programs to enhance resilience among nurses who experience job rotation, thereby improving their organizational commitment.

Galaxy evolution studies require the measurement of the physical properties of galaxies at different redshifts. In this work, we build supervised machine learning models to predict the redshift and physical properties (gas-phase metallicity, stellar mass, and star formation rate) of star-forming galaxies from the broad-band and medium-band photometry covering optical to near-infrared wavelengths, and present an evaluation of the model performance. Using 55 magnitudes and colors as input features, the optimized model can predict the galaxy redshift with an accuracy of σ(Δz/1+z) = 0.008 for a redshift range of z < 0.4. The gas-phase metallicity [12 + log(O/H)], stellar mass [log(Mstar)], and star formation rate [log(SFR)] can be predicted with the accuracies of σNMAD = 0.081, 0.068, and 0.19 dex, respectively. When magnitude errors are included, the scatter in the predicted values increases, and the range of predicted values decreases, leading to biased predictions. Near-infrared magnitudes and colors (H, K, and H −K), along with optical colors in the blue wavelengths (m425–m450), are found to play important roles in the parameter prediction. Additionally, the number of input features is critical for ensuring good performance of the machine learning model. These results align with the underlying scaling relations between physical parameters for star-forming galaxies, demonstrating the potential of using medium-band surveys to study galaxy scaling relations with large sample of galaxies.

지능정보사회에 대응한 교육 환경의 변화가 예상됨에 따라 본 연구에서는 학습자가 AI 기반 학습플랫 폼을 어떻게 인식하고 있는지 학업정서와 학습동기적 측면에 대해 질적으로 탐색하고자 하였다. 이를 위 해 AI 기반 학습플랫폼을 경험한 초등학생 및 중􌝆고등학생 7명을 연구참여자로 선정하였으며 그들이 경험 한 학업정서 및 학습동기에 대해 반구조화된 면담을 실시하였다. 면담 자료는 연구문제를 중심으로 자료 를 체계적으로 정리하여 기술하는 방법인 질적 내용분석(Qualitative content analysis: QCA)을 통해 분석 하였다. 그 결과 학업정서는 2개의 상위범주와 9개의 하위범주로 구성되었다. 구체적으로, 연구참여자들은 AI 기반 학습플랫폼을 사용하면서 긍정정서와 부정정서를 경험한 것으로 나타났다. 긍정정서로는 만족감, 성취감, 기대감, 즐거움, 안도감을 경험하였으며, 부정정서로는 답답함, 우울함, 좌절감, 불안함을 경험하였 다. 학습동기는 5개의 하위범주로 나뉘어졌고, AI 학습이 학습동기에 도움을 준 이유는 5개의 주제묶음으 로 구성되었다. 결과를 구체적으로 상술하면, AI 기반 학습플랫폼을 사용한 학습자들은 몰입, 자율성, 흥 미, 자기효능감, 자기조절성을 경험한 것으로 확인되었다. 또한 AI 학습을 경험한 학습자들은 AI 학습플랫 폼이 학습동기에 도움을 준 이유로 AI의 기능적 측면, AI 콘텐츠, 보상, 피드백, 게임 요소 등을 꼽았다. 이러한 결과를 기반으로 선행연구와 연계하여 논의하였다.

작물 증발산량은 잠재 증발산량에서 작물계수를 곱하여 작 물의 요수량을 산출할 수 있어 수자원 관리에 널리 사용되는　 방법이다. 특히 유엔식량농업기구(FAO)가 관개 및 배수 논 문 NO.56에서 발표한 Penman-Monteith　방정식(FAO 56-PM) 은 잠재 증발산량을 추정하는 표준방법으로, 평균온도, 최대 온도, 최소온도, 상대습도, 풍속 및 일사량의 6가지 기상 데이 터가 필요하다. 그러나　농경지 인근에 설치된 기상센서는 설 치 및 유지보수 비용이 높아 결측, 이상치와 같은 데이터 신뢰 성 문제를 야기하여 정확한 증발산량 계산을 복잡하게 만든 다. 본 연구에서는 인근 기상청의 데이터를 사용하여 필요한 6가지 기상 변수를 예측함으로써 기상 센서 없이 작물 증발산량을 추정할 수 있는지 조사하였다. 우리는 기상청의 API를 통해 수집할 수 있는 22개의 기상 변수를 입력 데이터로 활용 했다. 9개의 회귀 모델을 학습한 후 성능에 따라 상위 3개를 선 택하고 하이퍼파라미터 튜닝을 적용하여 최적의 모델을 식별 했다. 가장 좋은 성능을 보인 모델은 Extreme Gradient Boosting Regression(XGBR)이었으며 평균온도, 최대온도, 최소온도, 상대습도, 풍속 및 일사량에서 결정계수(R2)가 각 0.98, 0.99, 0.99, 0.91, 0.72, 0.86로 높은 결과를 얻을 수 있었다. 이러한 결과는 XGBR 모델이 작물 기상 데이터를 사용하여 작물 증 발산 모델에 필요한 입력 값을 정확하게 예측할 수 있어 값비 싼 기상 센서가 필요 없음을 시사한다. 이 접근 방식은 센서 설 치 및 유지보수가 어려운 지역에서 특히 유용할 수 있으며, 직 접적인 센서 데이터 없이도 표준 증발산 모델의 사용을 가능 하게 한다.

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.

Background: The increasing demand for real-time professional fitness coaching has led to a need for accurate exercise posture recognition using artificial intelligence. Objectives: To compare the performance of Feedforward Neural Network (FNN) and Stacked Long Short-Term Memory (LSTM) models in classifying fitness posture images using detailed joint coordinate labeling. Design: Comparative analysis of machine learning models using a labeled dataset of fitness posture images. Methods: A dataset from AI-hub containing images and data of 41 exercises was used. Five exercises were selected and processed using a custom program. Data was converted from JSON to CSV format, augmented with joint condition information, and analyzed using Google Colab. Results: The best FNN model achieved a training error of 1.21% and test error of 9.08%. The Stacked LSTM model demonstrated superior performance with a training error of 1.05% and test error of 6.09%. Conclusion: Both FNN and Stacked LSTM models effectively classified sequential fitness images, with Stacked LSTM showing superior performance. This indicates the potential of Stacked LSTM models for accurate fitness posture classification in real-time coaching scenarios.

Background: The evaluation of Human Movements based on Taekwondo poomsae (movement patterns) is inherently subjective, leading to concerns about bias and inconsistency in scoring. This emphasizes the need for objective and reliable scoring systems leveraging artificial intelligence technologies. Objectives: This study seeks to enhance the accuracy and fairness of Taekwondo poomsae scoring through the application of camera-based pose estimation and advanced neural network models. Design: A comparative analysis was conducted to evaluate the performance of machine learning models on a large-scale Taekwondo poomsae dataset. Methods: The analysis utilized a dataset comprising 902,306 labeled frames from 48 participants performing 62 distinct poomsae movements. Five models—LSTM, GRU, Simple RNN, Random Forest, and XGBoost—were evaluated using performance metrics, including accuracy, precision, recall, F1- score, and log loss. Results: The LSTM model outperformed all others, achieving an accuracy, precision, recall, and F1-score of 0.81, alongside the lowest log loss value of 0.55. The GRU model demonstrated comparable performance, while traditional models such as Random Forest and XGBoost were less effective in capturing the temporal and spatial patterns of poomsae movements. Conclusion: The LSTM model exhibited superior capability in modeling the temporal and spatial complexities inherent in Taekwondo poomsae, establishing a robust foundation for the development of objective, scalable, and reliable poomsae evaluation systems.

Background: Automated classification systems using Artificial Intelligence (AI) and Machine Learning (ML) can enhance accuracy and efficiency in diagnosing pet skin diseases within veterinary medicine. Objectives: This study created a system that classifies pet skin diseases by evaluating multiple ML models to determine which method is most effective. Design: Comparative experimental study. Methods: Pet skin disease images were obtained from AIHub. Models, including Multi-Layer Perceptron (MLP), Boosted Stacking Ensemble (BSE), H2O AutoML, Random Forest, and Tree-based Pipeline Optimization Tool (TPOT), were trained and their accuracy assessed. Results: The TPOT achieved the highest accuracy (94.50 percent), due to automated pipeline optimization and ensemble learning. H2O AutoML also performed well at 94.25 percent, illustrating the effectiveness of automated selection for intricate imaging tasks. Other models scored lower. Conclusion: These findings highlight the potential of AI-driven solutions for faster and more precise pet skin disease diagnoses. Future investigations should incorporate broader disease varieties, multimodal data, and clinical validations to solidify the practicality of these approaches in veterinary medicine.

Background: problem-based learning (PBL) is effective in learning majors in health care colleges. Objectives: To analyzed the effectiveness of self-efficacy, academic resilience, and self-directed learning in physical therapy students after PBL. Design: Questionnaire design. Methods: 44 participated in a study using a Mandal-art chart for PBL in a first-year medical terminology class. Surveys assessing self-efficacy, academic resilience, and self-directed learning were conducted before and after the semester. The study evaluated changes in these competencies through structured questionnaires. Cronbach's α was calculated to confirm the reliability of each questionnaire scale. A paired t-test was conducted to compare pre and post PBL class levels of self-efficacy, academic resilience, and self-directed learning, and the correlations between the measurement variables were analyzed using Spearman’s rank correlation coefficient. Results: Self-efficacy, academic resilience, and self-directed increased statistically significantly after the PBL class compared to before the class. A significant positive correlation was observed between self-efficacy and academic resilience, as well as between self-efficacy and self-directed learning. Additionally, academic resilience and self-directed learning also showed a significant positive correlation. Conclusion: PBL enhances self-efficacy, resilience, and self-directed learning, which show positive correlations and interact to improve physical therapy education outcomes.

This study aims to examine whether social support has a mediating effect on the relationship between optimism and learning flow as a strategy to promote learning flow in nursing students. The subjects of the study were first-, second-, third-, and fourth year students enrolled in the department of nursing at a four-year university located in city G. Data collection was conducted from September to October 2024. The data were analyzed using descriptive statistics, Pearson correlation coefficient, and Baron and Kenny's regression analysis. The results of the correlation analysis between the variables in this study are as follows. Optimism and social support (r=.372, p<.001), social support and learning flow (r=.445, p<.001), and optimism and learning flow (r=.437, p<.001) all showed positive correlations. The results of the mediating effect of social support on the relationship between optimism and learning flow according to Baron and Kenny's regression analysis are as follows. In step 1, optimism showed a positive effect on social support (β=.372. p<.001). In step 2, optimism showed a positive effect on learning flow (β=.437. p<.001). In step 3, social support showed a partial mediating effect between optimism and learning flow (β=.315. p<.001, β=.328. p<.001). Overall, these findings suggest that strategies that promote optimism and social support are needed to enhance learning flow among nursing students.

This study is a descriptive research conducted to identify the levels of self-directed learning ability, class participation, and learning satisfaction in the online learning environment of university students, and to examine the relationships among them and their effects on learning satisfaction. The subjects of this study were 172 students enrolled in a four-year university located in J province. The collected data were analyzed using the SPSS 23.0 program, with frequency, percentage, mean, standard deviation, t-test, ANOVA, Scheffe's post-hoc test, Pearson’s correlation coefficient, and multiple regression analysis. The results of the study showed that the mean score for self-directed learning was 3.73±0.47, for class participation was 3.00±0.54, and for learning satisfaction was 3.44±0.74. The factors influencing learning satisfaction were class participation and major satisfaction. This study suggests that class participation and major satisfaction affect learning satisfaction in an online learning environment. . Therefore, as a method to enhance learning satisfaction in online learning environments, it is necessary to adopt various teaching methods that increase class participation and design learner-centered courses that consider major satisfaction

Efficient and safe maritime navigation in complex and congested coastal regions requires advanced route optimization methods that surpass the limitations of traditional shortest-path algorithms. This study applies Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) reinforcement learning (RL) algorithms to generate and refine optimal ship routes in East Asian waters, focusing on passages from Shanghai to Busan and Ulsan to Daesan. Operating within a grid-based representation of the marine environment and considering constraints such as restricted areas and Traffic Separation Schemes (TSS), both DQN and PPO learn policies prioritizing safety and operational efficiency. Comparative analyses with actual vessel routes demonstrate that RL-based methods yield shorter and safer paths. Among these methods, PPO outperforms DQN, providing more stable and coherent routes. Post-processing with the Douglas-Peucker (DP) algorithm further simplifies the paths for practical navigational use. The findings underscore the potential of RL in enhancing navigational safety, reducing travel distance, and advancing autonomous ship navigation technologies.

This study investigated the relationship between changes in language learning beliefs and English proficiency among 41 Korean university students who participated in a short-term English program. Participants’ beliefs were assessed using the Beliefs About Language Learning Inventory (BALLI), and their proficiency was measured using the Test of English for International Communication (TOEIC). Frequency analysis, descriptive statistics, paired-sample t-tests, and correlation analysis were employed to analyze the data. The study found significant improvements in both listening and reading scores, and changes in beliefs varied with proficiency gains. Students with higher proficiency gains demonstrated improved confidence and self-efficacy, and decreased instrumental motivation, whereas those with lower gains exhibited minimal changes in beliefs. Correlation analysis revealed that belief shifts, such as reduced selfconsciousness and increased integrative motivation, were positively related to proficiency gains. These findings suggest the dynamic nature of learners’ beliefs and their potential impact on language learning outcomes, highlighting the importance of addressing belief systems in English language education.

Rapidly changing environmental factors due to climate change are increasing the uncertainty of crop growth, and the importance of crop yield prediction for food security is becoming increasingly evident in Republic of Korea. Traditionally, crop yield prediction models have been developed by using statistical techniques such as regression models and correlation analysis. However, as machine learning technique develops, it is able to predict the crop yield more accurate than the statistical techniques. This study aims at proposing the onion yield prediction framework to accurately predict the onion yield by using various environmental factor data. Temperature, humidity, precipitation, solar radiation, and wind speed are considered as climate factors and irrigation water and nitrogen application rate are considered as soil factors. To improve the performance of the prediction model, ensemble learning technique is applied to the proposed framework. The coefficient of determination of the proposed stacked ensemble framework is 0.96, which is a 24.68% improvement over the coefficient of determination of 0.77 of the existing single machine learning model. This framework can be applied to the particular farmland so that each farm can get their customized prediction model, which is visualized by the web system.

This study develops a machine learning-based tool life prediction model using spindle power data collected from real manufacturing environments. The primary objective is to monitor tool wear and predict optimal replacement times, thereby enhancing manufacturing efficiency and product quality in smart factory settings. Accurate tool life prediction is critical for reducing downtime, minimizing costs, and maintaining consistent product standards. Six machine learning models, including Random Forest, Decision Tree, Support Vector Regressor, Linear Regression, XGBoost, and LightGBM, were evaluated for their predictive performance. Among these, the Random Forest Regressor demonstrated the highest accuracy with R2 value of 0.92, making it the most suitable for tool wear prediction. Linear Regression also provided detailed insights into the relationship between tool usage and spindle power, offering a practical alternative for precise predictions in scenarios with consistent data patterns. The results highlight the potential for real-time monitoring and predictive maintenance, significantly reducing downtime, optimizing tool usage, and improving operational efficiency. Challenges such as data variability, real-world noise, and model generalizability across diverse processes remain areas for future exploration. This work contributes to advancing smart manufacturing by integrating data-driven approaches into operational workflows and enabling sustainable, cost-effective production environments.

The current study examines the digital behaviors of 124 university students enrolled in a blended learning class in Korea. The students were divided into two groups (upper and lower) based on their scores on a self-regulated learning questionnaire. Their digital behaviors were compared across four areas: (a) task completion scores; (b) strategy use; (c) the days on which tasks were completed; and (d) learning gains. The results revealed a significant difference in task completion scores between the upper and lower groups. However, no meaningful difference was observed in strategy use between the two groups. Students in the upper group were more proactive in completing videos, homework, and TOEIC tests, often finishing these tasks ahead of deadlines. In contrast, students in the lower group tended to complete their assignments on the due date. Finally, there were no significant differences in learning gains between the two groups. These findings may inform the design and management of online L2 learning programs.

Bearing-shaft systems are essential components in various automated manufacturing processes, primarily designed for the efficient rotation of a main shaft by a motor. Accurate fault detection is critical for operating manufacturing processes, yet challenges remain in sensor selection and optimization regarding types, locations, and positioning. Sound signals present a viable solution for fault detection, as microphones can capture mechanical sounds from remote locations and have been traditionally employed for monitoring machine health. However, recordings in real industrial environments always contain non-negligible ambient noise, which hampers effective fault detection. Utilizing a high-performance microphone for noise cancellation can be cost-prohibitive and impractical in actual manufacturing sites, therefore to address these challenges, we proposed a convolution neural network-based methodology for fault detection that analyzes the mechanical sounds generated from the bearing-shaft system in the form of Log-mel spectrograms. To mitigate the impact of environmental noise in recordings made with commercial microphones, we also developed a denoising autoencoder that operates without requiring any expert knowledge of the system. The proposed DAE-CNN model demonstrates high performance in fault detection regardless of whether environmental noise is included(98.1%) or not(100%). It indicates that the proposed methodology effectively preserves significant signal features while overcoming the negative influence of ambient noise present in the collected datasets in both fault detection and fault type classification.

This study analyzes the impact of ESG (Environmental, Social, and Governance) activities on Corporate Financial Performance(CFP) using machine learning techniques. To address the linear limitations of traditional multiple regression analysis, the study employs AutoML (Automated Machine Learning) to capture the nonlinear relationships between ESG activities and CFP. The dataset consists of 635 companies listed on KOSPI and KOSDAQ from 2013 to 2021, with Tobin's Q used as the dependent variable representing CFP. The results show that machine learning models outperformed traditional regression models in predicting firm value. In particular, the Extreme Gradient Boosting (XGBoost) model exhibited the best predictive performance. Among ESG activities, the Social (S) indicator had a positive effect on CFP, suggesting that corporate social responsibility enhances corporate reputation and trust, leading to long-term positive outcomes. In contrast, the Environmental (E) and Governance (G) indicators had negative effects in the short term, likely due to factors such as the initial costs associated with environmental investments or governance improvements. Using the SHAP (Shapley Additive exPlanations) technique to evaluate the importance of each variable, it was found that Return on Assets (ROA), firm size (SIZE), and foreign ownership (FOR) were key factors influencing CFP. ROA and foreign ownership had positive effects on firm value, while major shareholder ownership (MASR) showed a negative impact. This study differentiates itself from previous research by analyzing the nonlinear effects of ESG activities on CFP and presents a more accurate and interpretable prediction model by incorporating machine learning and XAI (Explainable AI) techniques.

This study investigated a learning environment that can enhance memory using LED lighting. Thus, it employed experimental verification to evaluate the effect of LED lighting's illuminance and correlated color temperature on long-term memory. The lighting environment was created under six conditions: two illuminance levels of 400 lx and 1,000 lx, and three correlated color temperatures of 3,000 K, 5,000 K, and 7,000 K. The participants of this study consisted of 30 cognitively healthy adults, with an average age of 21.7 years (SD = 1.73). The learning (memory) task used meaningless letters of only seven consonants, and the word fragment completion task measured memory retention after 20 minutes. The results of the study revealed that a relatively dim light of 400 lx, 5,000 K condition yielded the best long-term memory (Mean = 37.67, SD = 14.55), while the 1,000 lx, 5,000 K condition elicited the worst long-term memory (Mean = 25.67, SD = 12.78).

본 연구는 K-공간 기반 노이즈 제거 딥러닝(DL)을 이용한 확산강조영상(DWI)의 유용성을 평가하고자 하였다. 연구 를 위해 간세포암으로 확진된 환자 30명을 대상으로 DL 기법 적용 전후의 DWI에 각각 확산경사자계(b-value) 50 과 800을 적용하여 영상화하였다. 획득한 영상에서 간세포암 조직과 정상 간 조직에 관심 영역을 설정하여 b50, b800에서의 신호대잡음비(SNR)와 대조대잡음비(CNR)를 측정하였고 두 명의 관찰자가 각 영상에서 간세포암 조직 을 측정하여 겉보기확산계수(ADC) 값을 계산하였다. 모든 측정값의 평가는 T-검정(T-test)을 사용하여 상관관계 를 평가하였으며 급내상관계수(ICC)를 이용하여 두 관찰자 간 ADC 측정값의 일치도와 신뢰도를 평가하였다. 연구 결과, DL 적용 후 영상에서 SNR과 CNR이 모두 높아졌으며 통계적으로 유의한 것으로(p<0.05) 나타났다. 또한, 간세포암의 ADC 값은 통계적으로 유의하지 않은 것으로(p<0.05) 나타났지만 두 관찰자 간 ADC 측정값의 일치에 대한 신뢰도는 상관계수가 0.75 이상으로 우수하였고, 간세포암의 고유한 성질로 인해 ADC 값의 변화가 적은 점을 고려한다면 충분히 유의한 결과라고 볼 수 있다. 결론적으로 DL DWI은 영상 획득 시간을 단축하면서도 기존 DWI 보다 질적으로 더 나은 영상을 획득했다. 향후 다양한 MRI 검사에 DL이 적용된다면 더욱 유용하게 사용될 것으로 사료 된다.