Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

This study investigated the effects of exposure frequency, depth of processing, and activity repetition types on vocabulary learning. In total, 78 South Korean fifth-grade students were divided into four conditions. Students in each condition were asked to read a passage with four of the eight target words (exposure: four times) and the other four words (exposure: once) for three days, and to perform the vocabulary activities assigned to each condition. According to the results, exposure frequency and activity repetition type had significant effects on vocabulary learning. Activity repetition type also had a significant interaction effect with exposure frequency and depth of processing. Notably, presenting a word 12 times (4x3) in reading intervals had a more positive impact on vocabulary learning than presenting it three times (1x3), particularly when different vocabulary activities were repeated. Meanwhile, when the same activity was repeated, an activity with a higher depth of processing was more effective for vocabulary learning.

다중 에이전트 강화학습의 발전과 함께 게임 분야에서 강화학습을 레벨 디자인에 적용하려는 연구가 계속되 고 있다. 플랫폼의 형태가 레벨 디자인의 중요한 요소임에도 불구하고 지금까지의 연구들은 플레이어의 스킬 수준이나, 스킬 구성 등 플레이어의 매트릭에 초첨을 맞춰 강화학습을 활용하였다. 따라서 본 논문에서는 레 벨 디자인에 플랫폼의 형태가 사용될 수 있도록 시각 센서의 가시성과 구조물의 복잡성을 고려하여 플랫폼 이 플레이 경험에 미치는 영향을 연구한다. 이를 위해Unity ML-Agents Toolkit과MA-POCA 알고리즘, Self-play 방식을 기반으로2vs2 대전 슈팅 게임 환경을 개발하였으며 다양한 플랫폼의 형태를 구성하였다. 분석을 통해 플랫폼의 형태에 따른 가시성과 복잡성의 차이가 승률 밸런스에는 크게 영향을 미치지 않으나 전체 에피소 드 수, 무승부 비율, Elo의 증가폭에 유의미한 영향을 미치는 것을 확인했다.

With the recent surge in YouTube usage, there has been a proliferation of user-generated videos where individuals evaluate cosmetics. Consequently, many companies are increasingly utilizing evaluation videos for their product marketing and market research. However, a notable drawback is the manual classification of these product review videos incurring significant costs and time. Therefore, this paper proposes a deep learning-based cosmetics search algorithm to automate this task. The algorithm consists of two networks: One for detecting candidates in images using shape features such as circles, rectangles, etc and Another for filtering and categorizing these candidates. The reason for choosing a Two-Stage architecture over One-Stage is that, in videos containing background scenes, it is more robust to first detect cosmetic candidates before classifying them as specific objects. Although Two-Stage structures are generally known to outperform One-Stage structures in terms of model architecture, this study opts for Two-Stage to address issues related to the acquisition of training and validation data that arise when using One-Stage. Acquiring data for the algorithm that detects cosmetic candidates based on shape and the algorithm that classifies candidates into specific objects is cost-effective, ensuring the overall robustness of the algorithm.

본 연구는 좌우뇌 활용 능력 향상을 위한 한자 교육 콘텐츠 개발의 후속 연구로, 개발한 콘텐츠에 대한 전문 가 평가로 마무리된 연구에 이어서 사용자 관점에서 문제점을 발견하고 이를 보완함으로써 교육 콘텐츠로서 의 학습 가이드라인을 제시하는 것을 목적으로 한다. 1차 사용자 평가는 사용자 관찰법을 통해 진행하여 발견된 문제에 대하여 보완하고, 2차 사용자 평가에서는 참여자에 대한 뇌성향 검사를 진행하고, 인지면접법을 통해 사용자 평가를 진행하였다. 본 연구에서는 다음과 같은 결론을 제시할 수 있다. 첫째, 좌뇌 성향과 우뇌 성향 사용자에 대하여 교육접근 의 방법에 있어서 일부는 달리 접근해야 할 수 있음을 인지하여야 한다. 둘째, 시각적 접근을 하는 문항에서 는 하나의 답만 맞도록 설계하여야 한다. 셋째, 언어적 접근을 하는 문항에서는 대조로 인한 차이가 명확하 게 나타나도록 답지로 제시하고, 기준이 되는 한자와 다른 점 하나를 답으로 찾아보는 형태로 접근한다. 넷 째, 콘텐츠에서 학습대상으로 활용될 한자는 회의자 중에서 대상을 택하는 것이 적절하다. 다섯째, 우뇌 성향 의 사용자는 시각적으로 강제 결합한 이미지 안에서 의미를 파악하는 유형을 가장 선호하였고, 좌뇌 성향 사 용자는 요소를 조합하여 의미를 파악하는 유형을 가장 선호하였다.

This study investigated the convergence of content and language integrated learning, translanguaging, and global citizenship education in an EFL tertiary English class. Conceptualized within translanguaging as an assemblage for meaning-making, machine translation was incorporated into the course in a way that EFL bilinguals could fully avail themselves of their linguistic repertoire for the learning of global citizenship and language. The analyses of thirty-three students’ response essays and survey results demonstrate the success of MT as both a scaffold for bridging language-content gaps and a tool for language acquisition. Design features, perceived as important, were a careful introduction and training on MT use and teacher feedback on MT-assisted writing. Survey results emphasize the crucial role of the students’ L1 in meaning-making. The study offers a practical guide for educators interested in using MT in L2 writing instruction and encourages further research on the theoretical and pedagogical applications of translanguaging in diverse EFL contexts.

인공 고관절 치환술에 사용되는 금속 삽입물은 크기와 성분에 따라 주변 조직과 크고 작은 자화율의 차이를 일으켜 다양한 금속 인공물의 원인이 되며, 영상에 진단적 가치를 떨어뜨린다. 수신대역폭을 높이는 것은 인공물 감소에 효과가 있으나, 높은 수신대역폭은 획득 영상의 신호대잡음비를 감소시키는 단점이 있어 일정 수치 이상으로는 적용 하기에는 어려움이 있다. 딥러닝 알고리즘은 영상의 신호대잡음비를 높이고 전체 영상에서 균일하게 배경 잡음을 제거하는 데 매우 효과적이다. 이에 본 연구에서는 금속 인공물 감소를 위해 기존에 높은 수신대역폭을 이용하는 MARS(metal artifact reduction sequence) 프로토콜과 더욱 높은 수신대역폭을 설정한 프로토콜(Ultra MARS) 을 획득한 후 딥러닝을 이용하여 딥러닝 Ultra MARS로 변환한 후에 금속 인공물의 차이를 비교하였다. 딥러닝 적 용 후 Ultra MARS에서 적용 전 또는 기존의 MARS 기법보다 인공물의 크기가 작게 측정이 되었다. 또한, 인공물의 전체적인 SSIM(structural similarity index measure)에서도 기존의 MARS 기법보다 전체면적이 작게 측정되었 다. 더 나아가 SSIM의 결과 딥러닝 적용 전후의 구조적 유사성 역시 유사하게 나왔다. 딥러닝 알고리즘을 기존에 인공물을 줄이기 위해 사용하는 MARS와 같은 기법에서도 월등하게 높은 수치를 사용하는 강조영상을 획득 가능하 며 영상의 인공물도 줄이며, 영상의 대조도 또한 유지되는 영상을 제공할 수 있을 것으로 사료된다.

기존의 스타크래프트II 내장AI는 미리 정의한 행동 패턴을 따르기 때문에 사용자가 전략을 쉽게 파악할 수 있어 사용자의 흥미를 오랫동안 유지시키기 힘들다. 이를 해결하기 위해, 많은 강화학습 기반의 스타크래프 트II AI 연구가 진행되었다. 그러나 기존의 강화학습AI는 승률에만 중점을 두고 에이전트를 학습시킴으로써 소수의 유닛을 사용하거나 정형화 된 전략만을 사용하여 여전히 사용자들이 게임의 재미를 느끼기에 한계가 존재한다. 본 논문에서는 게임의 재미를 향상시키기 위하여, 강화학습을 활용하여 실제 플레이어와 유사한 AI을 제안한다. 에이전트에게 스타크래프트II의 상성표를 학습시키고, 정찰한 정보로 보상을 부여해 유동적 으로 전략을 변경하도록 한다. 실험 결과, 사용자가 느끼는 재미와 난이도, 유사도 부분에서 고정된 전략을 사용하는 에이전트보다 본 논문에서 제안하는 에이전트가 더 높은 평가를 받았다..

This study investigated the effects of multisensory memory strategies of pairing visual and aural learning strategies of aural lexical advance organizers (LAO) and read-alouds on 146 Korean high school students learning the meaning and pronunciation of 18 unfamiliar English words. In this quasi-experimental design, the control group learned the words on a single mode of written LAO and silent reading as opposed to two treatment groups of aural LAO and silent reading, and of aural LAO and read-alouds, respectively. The effects were tested three times via pre-, post-(immediately after learning), and delayed (30 days later) tests. The immediate and long-term effects were examined by detecting the differences across the three groups in post- and delayed-tests by one-way ANOVA, and the retention of effects was examined by paired t-tests in each group across the three tests. The results indicated that pairing aural LAO and read-aloud strategies was most effective in learning and retention of both vocabulary meaning and pronunciation.

본 연구는 간호대학생의 진로적응력을 증진하기 위한 고려로 낙관성과 진로적응력 간 관계에서 학습몰입의 매개 효과를 파악하고자 수행된 서술적 조사연구이다. 연구대상은 G시와 M시의 4년제 대학 간호학과에 재학 중인 학생이며, 자료는 2023년 4월부터 5월까지 수집하였다. 자료 분석을 위해 기술적 통 계, Pearson 상관계수, Baron과 Kenny의 회귀분석을 실시하였다. 연구결과, 첫째, 낙관성은 학습몰입에 정 적인 영향을 나타냈다. 둘째, 낙관성은 진로적응력에 정적인 영향을 나타냈다. 셋째, 학습몰입은 낙관성과 진로적응력 사이에서 부분 매개효과를 나타냈다. 이로써 간호대학생의 진로적응력을 증진하기 위해서는 낙 관성과 학습몰입을 촉진하기 위한 전략들이 간호교육현장에서 필요함을 알 수 있다.

This paper proposes an algorithm for the Unrelated Parallel Machine Scheduling Problem(UPMSP) without setup times, aiming to minimize total tardiness. As an NP-hard problem, the UPMSP is hard to get an optimal solution. Consequently, practical scenarios are solved by relying on operator's experiences or simple heuristic approaches. The proposed algorithm has adapted two methods: a policy network method, based on Transformer to compute the correlation between individual jobs and machines, and another method to train the network with a reinforcement learning algorithm based on the REINFORCE with Baseline algorithm. The proposed algorithm was evaluated on randomly generated problems and the results were compared with those obtained using CPLEX, as well as three scheduling algorithms. This paper confirms that the proposed algorithm outperforms the comparison algorithms, as evidenced by the test results.

This study aimed to explore nursing students' experience of learning cardiopulmonary resuscitation (CPR) in a web-based virtual simulation (vSim) through analysis of the reflection journals. Method: From June to July 2020, data were collected from 48 fourth-year nursing students who performed the simulation by reviewing prompt feedback on their CPR performance. The contents of the reflection journals were analyzed using NVivo qualitative data analysis software. Results: Nursing students experienced unfamiliarity with the English-based virtual environment as well as psychological pressure and anxiety about emergencies. Incorrect interventions were identified in the following order of frequency: violation of defibrillator guidelines, missing fundamental nursing care, error in applying an electrocardiogram monitor, inadequate initial response to cardiac arrest, insufficient chest compression, and inadequate ventilation. Lastly, the participants learned the importance of embodied knowledge, for knowing and acting accurately and reacting immediately, and their attitudes as nurses, such as responsibility, calmness, and attentiveness. Learning strategies included memory retention through repetition, real-time feedback analysis, pre-learning, and imagining action sequences in advance. The level of achievement, time required, CPR quality, and confidence improved with behavior-modification strategies developed through self-reflection. Conclusion: Educational interventions that are based on understanding accurate algorithms can strengthen selfawareness of mistakes to improve efficient imparting of CPR education.

PURPOSES : Construction cost estimates are important information for business feasibility analysis in the planning stage of road construction projects. The quality of current construction cost estimates are highly dependent on the expert's personal experience and skills to estimate the arithmetic average construction cost based on past cases, which makes construction cost estimates subjective and unreliable. An objective approach in construction cost estimation shall be developed with the use of machine learning. In this study, past cases of road projects were analyzed and a machine learning model was developed to produce a more accurate and time-efficient construction cost estimate in teh planning stage. METHODS : After conducting case analysis of 100 road construction, a database was constructed including the road construction's details, drawings, and completion reports. To improve the construction cost estimation, Mallow's Cp. BIC, Adjusted R methodology was applied to find the optimal variables. Consequently, a plannigs-stage road construction cost estimation model was developed by applying multiple regression analysis, regression tree, case-based inference model, and artificial neural network (ANN, DNN). RESULTS : The construction cost estimation model showed excellent prediction performance despite an insufficient amount of learning data. Ten cases were randomly selected from the data base and each developed machine learning model was applied to the selected cases to calculate for the error rate, which should be less than 30% to be considered as acceptable according to American Estimating Association. As a result of the analysis, the error rates of all developed machine learning models were found to be acceptable with values rangine from 17.3% to 26.0%. Among the developed models, the ANN model yielded the least error rate. CONCLUSIONS : The results of this study can help raise awareness of the importance of building a systematic database in the construction industry, which is disadvantageous in machine learning and artificial intelligence development. In addition, it is believed that it can provide basic data for research to determine the feasibility of construction projects that require a large budget, such as road projects.

This study aimed to investigate the impact of implementing team-based learning (TBL) in postpartum nursing simulation practical education for nursing college students. Methods: The study design was a non-equivalent control group pretest-posttest quasi-experimental design. 128 nursing students divided into two groups: 61 in the experiment group and 67 in the control group. During the winter break in January 2023, students participating in simulation practicals were assigned to the control group, while students participating in simulation practicals during the regular semester (April 2023) were assigned to the experimental group, to prevent crossontamination between the groups due to experimental treatment. Both groups completed selfdministered questionnaires to assess self-directed learning abilities, collaborative self-efficacy, academic achievement, and learning satisfaction. Results: The experimental group showed significantly better compared to the control group, the experimental group showed higher levels of academic achievement and learning satisfaction. Conclusion: It was evident that TBL applied to postpartum nursing simulation practical education is a pedagogical teaching strategy that enhances academic achievement and learning satisfaction. It is necessary to develop and apply team-based simulation practical education not only for challenging obstetric cases but also for labor and delivery nursing, antepartum nursing, and other related areas in clinical practice.

The purpose of this study was to determine the effect of simulation-based Korea advanced life support training on new nurses' knowledge, clinical performance ability, performer confidence, and learning satisfaction. Methods: This is a non-equivalent controlled pre-post quasi-experimental study. A simulation-based CPR training program was applied to 37 new nurses. Results: The experimental group scored lower on emergency management knowledge (83.65±7.61) than the control group (84.55±9.22), which was not significant (t=-4.46, p=.657). However, the clinical performance ability score was significantly higher in the experimental group (109.59±9.98) than in the control group (100.24±11.87) (t=3.581, p <.001). Performer confidence was significantly higher in the experimental group (23.43±3.29) than in the control group (19.90±3.85) (t=3.69, p〈.001). In addition, the learning satisfaction score of the experimental group (96.16±5.64) was significantly higher than the control group (88.42±11.13) (t=3.72, p< .001). Conclusion: This study confirmed that simulation training is an efficient way to improve new nurses' clinical performance ability, and performer confidence. Therefore, applying simulation training in scenarios can improve new nurses' work competence and contribute to improving the quality of patient care.

The study is aimed at exploring impacts of self-assessment on students’ self-regulated learning and satisfaction at a university setting. Twenty-one students taking a foreign language pedagogy course participated in the study. Weekly self-assessment was assigned for 8 weeks to see if it improved students’ self-regulated learning. Student questionnaire was collected twice on the 7th and the 15th week; in addition, in-depth interviews were conducted to gather students’ perceptions of self-assessment in terms of its benefits and drawbacks. Findings based on quantitative and qualitative analysis are as follows. Firstly, significant positive impacts of self-assessment were found in all three domains of self-regulated learning: cognitive, motivational, and behavioral. Secondly, students found self-assessment overall satisfactory and useful in their studies. In-depth interviews further revealed that self-assessment helped to regulate their study behaviors effectively, which, in turn, led to a better understanding of the subject matter and greater participation in class activities. At the same time, however, some students expressed some burden as a drawback of self-assessment. Pedagogical implications and research suggestions for future study were discussed.

Numerous factors contribute to the deterioration of reinforced concrete structures. Elevated temperatures significantly alter the composition of the concrete ingredients, consequently diminishing the concrete's strength properties. With the escalation of global CO2 levels, the carbonation of concrete structures has emerged as a critical challenge, substantially affecting concrete durability research. Assessing and predicting concrete degradation due to thermal effects and carbonation are crucial yet intricate tasks. To address this, multiple prediction models for concrete carbonation and compressive strength under thermal impact have been developed. This study employs seven machine learning algorithms—specifically, multiple linear regression, decision trees, random forest, support vector machines, k-nearest neighbors, artificial neural networks, and extreme gradient boosting algorithms—to formulate predictive models for concrete carbonation and thermal impact. Two distinct datasets, derived from reported experimental studies, were utilized for training these predictive models. Performance evaluation relied on metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analytical outcomes demonstrate that neural networks and extreme gradient boosting algorithms outshine the remaining five machine learning approaches, showcasing outstanding predictive performance for concrete carbonation and thermal effect modeling.

인공지능은 4차 산업혁명의 프레임이 소개된 이후 점차 보편적인 기술로 자리를 잡아가고 있으며, 인공지능 관련 특허 출원도 크게 증가하고 있다. 최근에는 특허 생태계가 출원 건수 위주의 양적 경쟁에서 고품질의 특허 확보라는 질적 경쟁으로 패러다임이 변화되면서, 저품질 특허로 인한 비용 손실에 관심이 높아지고 있다. 이러한 배경으로 본 연구에서는 머신러닝과 Doc2Vec 알고리즘을 활용하여 특허 품질을 예측하는 방법을 제안하고자 한다. 본 연구를 위해 WIPO에서 정의한 CPC 코드를 활용하여 미국 특허청(USPTO)에 등록된 인공지능 관련 특허 데이터를 추출하였고, 이를 통해 정형 데이터 기반 19개 변수, 비정형 데이터 기반 7개 변수를 개발하였다. 특히, 새롭게 제안하는 Doc2Vec 알고리즘을 이용한 제목과 초록 텍스트 유사도 변수는 고품질 특허를 예측하는데 영향을 미칠 것으로 판단된다. 이에 유사도 변수의 효과를 확인하기 위해 유사도 변수를 포함한 앙상블 기반 머신러닝 모델과 포함하지 않은 모델을 개발하여 비교하였다. 실험 결과, 유사도 변수를 포함한 모델이 AUC 0.013, f1-score 0.025가 높게 나타나 더 우수한 성능을 보였다. 이는 유사도 변수가 고품질 특허 예측에 기여한다는 것을 시사한다. 또한, SHAP을 이용하여 블랙박스 형태의 머신러닝 변수 영향도를 설명하였다. 본 연구를 통해 핵심 기술 분야인 인공지능과 같은 영역에서 특허의 품질을 예측하고, 고품질 특허 개발을 장려함으로써 사회적 가치를 실현하는 데 기여할 수 있을 것으로 기대한다.