This study proposes a weight optimization technique based on Mixture Design of Experiments (MD) to overcome the limitations of traditional ensemble learning and achieve optimal predictive performance with minimal experimentation. Traditional ensemble learning combines the predictions of multiple base models through a meta-model to generate a final prediction but has limitations in systematically optimizing the combination of base model performances. In this research, MD is applied to efficiently adjust the weights of each base model, constructing an optimized ensemble model tailored to the characteristics of the data. An evaluation of this technique across various industrial datasets confirms that the optimized ensemble model proposed in this study achieves higher predictive performance than traditional models in terms of F1-Score and accuracy. This method provides a foundation for enhancing real-time analysis and prediction reliability in data-driven decision-making systems across diverse fields such as manufacturing, fraud detection, and medical diagnostics.

Defective product data is often very few because it is difficult to obtain defective product data while good product data is rich in manufacturing system. One of the frequently used methods to resolve the problems caused by data imbalance is data augmentation. Data augmentation is a method of increasing data from a minor class with a small number of data to be similar to the number of data from a major class with a large number of data. BAGAN-GP uses an autoencoder in the early stage of learning to infer the distribution of the major class and minor class and initialize the weights of the GAN. To resolve the weight clipping problem where the weights are concentrated on the boundary, the gradient penalty method is applied to appropriately distribute the weights within the range. Data augmentation techniques such as SMOTE, ADASYN, and Borderline-SMOTE are linearity-based techniques that connect observations with a line segment and generate data by selecting a random point on the line segment. On the other hand, BAGAN-GP does not exhibit linearity because it generates data based on the distribution of classes. Considering the generation of data with various characteristics and rare defective data, MO1 and MO2 techniques are proposed. The data is augmented with the proposed augmentation techniques, and the performance is compared with the cases augmented with existing techniques by classifying them with MLP, SVM, and random forest. The results of MO1 is good in most cases, which is believed to be because the data was augmented more diversely by using the existing oversampling technique based on linearity and the BAGAN-GP technique based on the distribution of class data, respectively.

Molybdenum-tungsten (Mo-W) alloy sputtering targets are widely utilized in fields like electronics, nanotechnology, sensors, and as gate electrodes for TFT-LCDs, owing to their superior properties such as hightemperature stability, low thermal expansion coefficient, electrical conductivity, and corrosion resistance. To achieve optimal performance in application, these targets’ purity, relative density, and grain size of these targets must be carefully controlled. We utilized nanopowders, prepared via the Pechini method, to obtain uniform and fine powders, then carried out spark plasma sintering (SPS) to densify these powders. Our studies revealed that the sintered compacts made from these nanopowders exhibited outstanding features, such as a high relative density of more than 99%, consistent grain size of 3.43 μm, and shape, absence of preferred orientation.

The metal bush assembling process is a process of inserting and compressing a metal bush that serves to reduce the occurrence of noise and stable compression in the rotating section. In the metal bush assembly process, the head diameter defect and placement defect of the metal bush occur due to metal bush omission, non-pressing, and poor press-fitting. Among these causes of defects, it is intended to prevent defects due to omission of the metal bush by using signals from sensors attached to the facility. In particular, a metal bush omission is predicted through various data mining techniques using left load cell value, right load cell value, current, and voltage as independent variables. In the case of metal bush omission defect, it is difficult to get defect data, resulting in data imbalance. Data imbalance refers to a case where there is a large difference in the number of data belonging to each class, which can be a problem when performing classification prediction. In order to solve the problem caused by data imbalance, oversampling and composite sampling techniques were applied in this study. In addition, simulated annealing was applied for optimization of parameters related to sampling and hyper-parameters of data mining techniques used for bush omission prediction. In this study, the metal bush omission was predicted using the actual data of M manufacturing company, and the classification performance was examined. All applied techniques showed excellent results, and in particular, the proposed methods, the method of mixing Random Forest and SA, and the method of mixing MLP and SA, showed better results.

This study investigates the effect of the DDL (Data-Driven Learning) approach on the English sentence writing ability of 6th graders in elementary school. To this end, a total of seven English textbooks were used to build a corpus. Five teachers were then asked to conduct five lessons using a weak version of DDL in their 6-grade EFL classrooms. Students were asked to complete a pre- and post-test and a pre- and post-survey, and a selected number of students and four of the five teachers had in-depth interviews with the researcher. The results are as follows: First, DDL using the textbook corpus was found to be adequate for helping elementary students improve their sentence-writing ability. Second, DDL had a significant effect on upper, middle, and lower level groups of students. Third, the students felt that DDL was neither unfamiliar nor difficult. Fourth, teachers with little teaching experience found it easy to conduct their classes using the DDL approach. This study implies that DDL is an effective approach to teaching communicative functions and language forms in the elementary English classroom and can be useful for all levels of elementary students.

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

사출성형공정은 열가소성 수지를 가열하여 유동상태로 만들어 금형의 공동부에 가압 주입한 후에 금형 내에서 냉각시키는 공정으로, 금형의 공동모양과 동일한 제품을 만드는 방법이다. 대량생산이 가능하고, 복잡한 모양이 가능한 공정으로, 수지온도, 금형온도, 사출속도, 압력 등 다양한 요소들이 제품의 품질에 영향을 미친다. 제조현장에서 수집되는 데이터는 양품과 관련된 데이터는 많은 반면, 불량품과 관련된 데이터는 적어서 데이터불균형이 심각하다. 이러한 데이터불균형을 효율적으로 해결하기 위하여 언더샘플링, 오버샘플링, 복합샘플링 등이 적용되고 있다. 본 연구에서는 랜덤오버샘플링(ROS), 소수 클래스 오버 샘플링(SMOTE), ADASTN 등의 소수클래스의 데이터를 다수클래스만큼 증폭시키는 오버샘플링 기법을 활용하고, 데이터마이닝 기법을 활용하여 품질예측을 하고자 한다.

Environmental issues such as global warming due to fossil fuel use are now major worldwide concerns, and interest in renewable and clean energy is growing. Of the various types of renewable energy, green hydrogen energy has recently attracted attention because of its eco-friendly and high-energy density. Electrochemical water splitting is considered a pollution-free means of producing clean hydrogen and oxygen and in large quantities. The development of non-noble electrocatalysts with low cost and high performance in water splitting has also attracted considerable attention. In this study, we successfully synthesized a NiCo2O4/NF electrode for an oxygen evolution reaction in alkaline water splitting using a hydrothermal method, which was followed by post-heat treatment. The effects of heat treatment on the electrochemical performance of the electrodes were evaluated under different heat-treatment conditions. The optimized NCO/NF-300 electrode showed an overpotential of 416 mV at a high current density of 50 mA/cm2 and a low Tafel slope (49.06 mV dec-1). It also showed excellent stability (due to the large surface area) and the lowest charge transfer resistance (12.59 Ω). The results suggested that our noble-metal free electrodes have great potential for use in developing alkaline electrolysis systems.

Tungsten disulfide (WS2) nanosheets have attracted considerable attention because of their unique optical and electrical properties. Several methods for fabrication of WS2 nanosheets have been developed. However, methods for mass production of high-quality WS2 nanosheets remain challenging. In this study, WS2 nanosheets were fabricated using mechano-chemical ball milling based on the synergetic effects of chemical intercalation and mechanical exfoliation. The ball-milling time was set as a variable for the optimized fabricating process of WS2 nanosheets. Under the optimized conditions, the WS2 nanosheets had lateral sizes of 500–600 nm with either a monolayer or bilayer. They also exhibited high crystallinity in the 2H semiconducting phase. Thus, the proposed method can be applied to the exfoliation of other transition metal dichalcogenides using suitable chemical intercalants. It can also be used with highperformance WS2-based photodiodes and transistors used in practical semiconductor applications.

The demand for chiller equipment that keeps each machine at a constant temperature to maintain the best possible condition is growing rapidly. PID (Proportional Integral Derivation) control is a popular temperature control method. The error, which is the difference between the desired target value and the current system output value, is calculated and used as an input to the system using a proportional, integrator, and differentiator. Through such a closed-loop configuration, a desired final output value of the system can be reached using only the target value and the feedback signal. Furthermore, various temperature control methods have been devised as the control performance of various high-performance equipment becomes important. Therefore, it is necessary to design for accurate data-driven temperature control for chiller equipment. In this research, support vector regression is applied to the classic PID control for accurate temperature control. Simulated annealing is applied to find optimal PID parameters. The results of the proposed control method show fast and effective control performance for chiller equipment.