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.

For the OPR1000, a standard power plant in Korea, an analytical model of the containment building considering voids and deterioration was built with multilayer shell elements. Voids were placed in the vulnerable parts of the analysis model, and the deterioration effects of concrete and rebar were reflected in the material model. To check the impact of voids and deterioration on the seismic performance of the containment building, iterative push-over analysis was performed on four cases of the analytical model with and without voids and deterioration. It was found that the effect of voids with a volume ratio of 0.6% on the seismic performance of the containment building was insignificant. The effect of strength reduction and cross-sectional area loss of reinforcement due to deterioration and the impact of strength increase of concrete due to long-term hardening offset each other, resulting in a slight increase in the lateral resistance of the containment building. To determine the limit state that adequately represents the seismic performance of the containment building considering voids and deterioration, the Ogaki shear strength equation, ASCE 43-05 low shear wall allowable lateral displacement ratio, and JEAC 4601 shear strain limit were compared and examined with the analytically derived failure point (ultimate point) in this study.

Existing reinforced concrete (RC) building frames constructed before the seismic design was applied have seismically deficient structural details, and buildings with such structural details show brittle behavior that is destroyed early due to low shear performance. Various reinforcement systems, such as fiber-reinforced polymer (FRP) jacketing systems, are being studied to reinforce the seismically deficient RC frames. Due to the step-by-step modeling and interpretation process, existing seismic performance assessment and reinforcement design of buildings consume an enormous amount of workforce and time. Various machine learning (ML) models were developed using input and output datasets for seismic loads and reinforcement details built through the finite element (FE) model developed in previous studies to overcome these shortcomings. To assess the performance of the seismic performance prediction models developed in this study, the mean squared error (MSE), R-square (R2), and residual of each model were compared. Overall, the applied ML was found to rapidly and effectively predict the seismic performance of buildings according to changes in load and reinforcement details without overfitting. In addition, the best-fit model for each seismic performance class was selected by analyzing the performance by class of the ML models.

This study aims to predict return-to-work outcomes for workers injured in industrial accidents using a TabNet-RUSBoost hybrid model. The study analyzed data from 1,383 workers who had completed recuperation. Key predictors identified include length of recuperation, disability grade, occupation activity, self-efficacy, and socioeconomic status. The model effectively addresses class imbalance and demonstrates superior predictive performance. These findings underscore the importance of a holistic approach, incorporating both medical and psychosocial factors.

The design variables and material properties as well as the external loads concerned with structural engineering are used to be deterministic in optimization process. These values, however, have variability from expected performance. Therefore, deterministic optimum designs that are obtained without taking these uncertainty into account could lead to unreliable designs, which necessitates the Reliability-Based Design Optimization(RBDO). RBDO involves an evaluation of probabilistic constraints which constitutes another optimization procedure. So, an expensive computational cost is required. Therefore, how to decrease the computational cost has been an important challenge in the RBDO research field. Approximation models, response surface model and Kriging model, are employed to improve an efficiency of the RBDO.

콩과 같은 밭작물은 주로 토양으로부터 수분을 공급받으며 토양 수분 조건에 따라 생육 반응이 민감하게 반응한다. 작물의 생육과 재배 지역의 토양 조건, 기상 등에 따라 적정 토양 수분을 유지하는 것은 작물 생산량의 증가를 위해 중요하다. 따라서, 본 연구에서는 머신러닝 기법을 이용하여 토양 수분 함량 예측 모델을 개발하였다. 깊이에 따른 토양 수분과 외기, 강수량 등 기상 변수와의 상관 관계를 구명하고, 깊이별 토양 수분예측을 위한 부분최소제곱회귀(PLSR) 모델을 알고리즘을 개발하였다. 콩 재배포장의 10cm, 20cm, 30cm 깊이의 토양수분은 FDR 방식의 센서로 측정하였 고, 콩 작물 주변 환경인자(재배환경의 기온, 상대습도, 풍속, 일사량, 일조시간)는 주변의 기상관측소에서 측정된 데이터를 이용하였다. 이를 이용하여 깊이별 미래의 토양수분함량 예측 모델을 개발한 결과, 10cm와 20cm깊이에서 주요 인자는 현재 토양수분함량과 기온이었으며, 30cm 깊이에서의 주요 인자는 현재 토양수분함량과 기온, 풍속으로 나타났다. 토양 깊이가 깊어짐에 따라 토양수분함량 예측 정확도가 향상되었으며, 이는 표면에 가까울수록 토양수분함량이 변화가 크기 때문으로 예상된다. 또한 미래의 토양 수분함량예측시 1시간 후 예측 정확도가 가장 우수하였으며, 이때의 Rv 2와 RMSEV가 10cm 깊이에서 0.993와 1.069%, 20cm 깊이에서 0.994와 0.821% 였으며, 30cm 깊이에서 0.999와 0.149% 였다. 본 연구 결과는 콩 생육환경 진단을 위해 재배 포장의 토양수분함량을 토양층별로 미래의 토양수분함량도 예측이 가능함을 보여준다.

목적: 본 연구는 인간작업 모델을 기반으로 한 여가활동이 지역사회 거주 장애인의 삶의 질, 자기효능감, 시간 사용에 미치는 영향을 알아보고자 하였다. 연구방법: 본 연구는 보건소 지역사회 재활 사업에 참여하는 지역사회 거주 장애인 15명을 선정하여 대상으로 했다. 대상자와 작업치료 학부생 봉사자 2~3명을 매칭하였고, 지역사회 재활 담당 작업치료사와 작업치료학과 교수의 지도하에 평가와 중재를 제공하였다. 연구설계는 단일집단 사전⋅사후 설계를 적용했다. 중재는 10주 동안 10회기 실시하였으며 중재 전⋅후를 비교하기 위해 삶의 질 평가를 위해 한국판 WHO 삶의 질 척도-단축형(Korean Version of The World Health Organization Quality of Life Brief Version), 자기효능감 평가를 위해 일반적 자기효능감 척도(General Self-efficacy Scale), 시간 사용 평가를 위해 작업 질문지(Occupational Questionnaire; OQ)를 사용하였다. 결과: 10주간의 인간 작업모델을 기반으로 한 여가활동을 통해 지역사회 거주 장애인의 삶의 질은 전반적 삶의 질, 신체적 건강, 사회적 관계에서 상승을 보였다. 자기효능감은 유의한 변화를 보이지 않았다. 시간사용은 OQ의 전 문항에서 유의하게 변화가 있었다. 결론: 지역사회 거주 장애인이 삶에서 원하는 여가활동을 할 수 있도록 많은 방문재활이 이루어지기를 기대한다.

In the military, ammunition and explosives stored and managed can cause serious damage if mishandled, thus securing safety through the utilization of ammunition reliability data is necessary. In this study, exploratory data analysis of ammunition inspection records data is conducted to extract reliability information of stored ammunition and to predict the ammunition condition code, which represents the lifespan information of the ammunition. This study consists of three stages: ammunition inspection record data collection and preprocessing, exploratory data analysis, and classification of ammunition condition codes. For the classification of ammunition condition codes, five models based on boosting algorithms are employed (AdaBoost, GBM, XGBoost, LightGBM, CatBoost). The most superior model is selected based on the performance metrics of the model, including Accuracy, Precision, Recall, and F1-score. The ammunition in this study was primarily produced from the 1980s to the 1990s, with a trend of increased inspection volume in the early stages of production and around 30 years after production. Pre-issue inspections (PII) were predominantly conducted, and there was a tendency for the grade of ammunition condition codes to decrease as the storage period increased. The classification of ammunition condition codes showed that the CatBoost model exhibited the most superior performance, with an Accuracy of 93% and an F1-score of 93%. This study emphasizes the safety and reliability of ammunition and proposes a model for classifying ammunition condition codes by analyzing ammunition inspection record data. This model can serve as a tool to assist ammunition inspectors and is expected to enhance not only the safety of ammunition but also the efficiency of ammunition storage management.

This study introduces and experimentally validates a novel approach that combines Instruction fine-tuning and Low-Rank Adaptation (LoRA) fine-tuning to optimize the performance of Large Language Models (LLMs). These models have become revolutionary tools in natural language processing, showing remarkable performance across diverse application areas. However, optimizing their performance for specific domains necessitates fine-tuning of the base models (FMs), which is often limited by challenges such as data complexity and resource costs. The proposed approach aims to overcome these limitations by enhancing the performance of LLMs, particularly in the analysis precision and efficiency of national Research and Development (R&D) data. The study provides theoretical foundations and technical implementations of Instruction fine-tuning and LoRA fine-tuning. Through rigorous experimental validation, it is demonstrated that the proposed method significantly improves the precision and efficiency of data analysis, outperforming traditional fine-tuning methods. This enhancement is not only beneficial for national R&D data but also suggests potential applicability in various other data-centric domains, such as medical data analysis, financial forecasting, and educational assessments. The findings highlight the method's broad utility and significant contribution to advancing data analysis techniques in specialized knowledge domains, offering new possibilities for leveraging LLMs in complex and resource- intensive tasks. This research underscores the transformative potential of combining Instruction fine-tuning with LoRA fine-tuning to achieve superior performance in diverse applications, paving the way for more efficient and effective utilization of LLMs in both academic and industrial settings.

In the manufacturing industry, dispatching systems play a crucial role in enhancing production efficiency and optimizing production volume. However, in dynamic production environments, conventional static dispatching methods struggle to adapt to various environmental conditions and constraints, leading to problems such as reduced production volume, delays, and resource wastage. Therefore, there is a need for dynamic dispatching methods that can quickly adapt to changes in the environment. In this study, we aim to develop an agent-based model that considers dynamic situations through interaction between agents. Additionally, we intend to utilize the Q-learning algorithm, which possesses the characteristics of temporal difference (TD) learning, to automatically update and adapt to dynamic situations. This means that Q-learning can effectively consider dynamic environments by sensitively responding to changes in the state space and selecting optimal dispatching rules accordingly. The state space includes information such as inventory and work-in-process levels, order fulfilment status, and machine status, which are used to select the optimal dispatching rules. Furthermore, we aim to minimize total tardiness and the number of setup changes using reinforcement learning. Finally, we will develop a dynamic dispatching system using Q-learning and compare its performance with conventional static dispatching methods.

The threat of North Korea's long-range firepower is recognized as a typical asymmetric threat, and South Korea is prioritizing the development of a Korean-style missile defense system to defend against it. To address this, previous research modeled North Korean long-range artillery attacks as a Markov Decision Process (MDP) and used Approximate Dynamic Programming as an algorithm for missile defense, but due to its limitations, there is an intention to apply deep reinforcement learning techniques that incorporate deep learning. In this paper, we aim to develop a missile defense system algorithm by applying a modified DQN with multi-agent-based deep reinforcement learning techniques. Through this, we have researched to ensure an efficient missile defense system can be implemented considering the style of attacks in recent wars, such as how effectively it can respond to enemy missile attacks, and have proven that the results learned through deep reinforcement learning show superior outcomes.

As environmental concerns escalate, the increase in recycling of aluminum scrap is notable within the aluminum alloy production sector. Precise control of essential components such as Al, Cu, and Si is crucial in aluminum alloy production. However, recycled metal products comprise various metal components, leading to inherent uncertainty in component concentrations. Thus, meticulous determination of input quantities of recycled metal products is necessary to adjust the composition ratio of components. This study proposes a stable input determination heuristic algorithm considering the uncertainty arising from utilizing recycled metal products. The objective is to minimize total costs while satisfying the desired component ratio in aluminum manufacturing processes. The proposed algorithm is designed to handle increased complexity due to introduced uncertainty. Validation of the proposed heuristic algorithm's effectiveness is conducted by comparing its performance with an algorithm mimicking the input determination method used in the field. The proposed heuristic algorithm demonstrates superior results compared to the field-mimicking algorithm and is anticipated to serve as a useful tool for decision-making in realistic scenarios.

In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetration including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder’s status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multivariate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.