• 디지털융복합연구
• /
• 제16권9호
• /
• pp.29-37
• /
• 2018

본 연구는 직장인들의 자기주도적 학습에 영향을 미치는 요인을 파악하는 데 연구의 목적을 두었다. 이를 위하여 충청남도 서북부 2개의 시에서 직장인 335명을 대상으로 하여 설문조사를 실시하였다. 결과 분석은 일반적 특성에 따른 자기주도적 학습의 차이 검정(T-test, ANOVA), 주요 변인 간의 상관분석, 그리고 희망과 성장 마인드셋이 자기주도적 학습에 미치는 영향을 파악하기 위하여 집단을 사원급과 대리급 이상으로 나누어 위계적 회귀분석을 실시하였다. 주요한 연구결과는 다음과 같다. 첫째, 자기주도적 학습은 성별에 따라 차이를 보였다. 둘째, 상관분석 결과 희망과 성장 마인드셋 및 자기주도적 학습은 모두 정적 상관관계를 나타내었다. 셋째, 회귀분석 결과 사원급인 경우 희망의 경로사고와 성장 마인드셋의 지능이 자기주도적 학습에 영향을 미쳤고 대리급 이상인 경우 희망의 경로사고가 영향을 미치는 것으로 나타났다. 끝으로 직위에 따라 자기주도적 학습을 높이기 위한 정책적 방안을 논의하였다.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제32권3호
• /
• pp.275-296
• /
• 2018

본 연구에서는 수학영재 학생들을 대상으로 분석법을 이용한 증명 학습을 하게 한 후 나타나는 시선의 변화 및 시선의 변화로 야기되는 학습 성취도의 변화가 어떠한지를 알아보고자 하였다. 시선의 변화를 알아보기 위해 시선추적기법을 도입하였으며, 시선추적기를 통해 분석법의 학습효과를 좀 더 객관적으로 파악하고자 하였다. 본 연구의 결과로서, 분석법을 학습한 후 학생들이 증명 문제를 풀 때, 증명 아랫부분에서부터 증명 윗부분으로 올라가는 방식으로 시선의 이동방향이 변화하였으며 증명 아랫부분에 대한 시선 점유 비율이 윗부분에 비해 높아짐을 알 수 있었다. 또한 분석법 학습으로 야기된 시선의 변화는 증명 학습 성취도와 상관관계가 있으며 증명 학습 성취도를 향상시킨다는 것을 알 수 있었다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권3호
• /
• pp.123-140
• /
• 2018

Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

• 품질경영학회지
• /
• 제48권3호
• /
• pp.421-431
• /
• 2020

Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.

• 한국멀티미디어학회논문지
• /
• 제21권9호
• /
• pp.1027-1034
• /
• 2018

CCTV has been known to possess high level of objectivity and utility. Hence, the government has recently focused on replacing low quality CCTV with higher quality ones or even by adding high resolution CCTV. However, converting all existing low-quality CCTV to high quality can be extremely costly. Furthermore, low quality videos prior to CCTV replacement are likely to be of poor quality and thus not utilized correctly. In order to solve these problems, this paper proposes a method to improve videos quality of images using SRGAN(Super Resolution Generative Advisory Networks). Through experiments, we have proven that it is possible to improve low quality CCTV videos clearly. For this experiment, a total of 4 types of CCTV videos were used and 10,000 images were sampled from each type. Those images could then be used for machine learning. The fact that the pre-process for machine learning has been done manually and the long time that required for machine learning seems to be complementary.

• 한국초등수학교육학회지
• /
• 제10권2호
• /
• pp.151-169
• /
• 2006

수학교육의 본질과 목표에 부합하는 교수-학습을 하기 위해서 Gagn'e의 학습 위계론, Piaget의 인지발달론, Bruner의 인지경로이론, Skemp의 범례제시 학습 이론 가운데 현장 수학과 교실 수업과 밀접한 관련이 있는 부분을 수학과 교수-학습에 적용해 보고 그 효과를 고찰해 본다. 이 연구의 결과는 첫째, 논리적인 계통성이 뚜렷한 수학과 학습을 학습위계에 따른 학습과제 분석표를 교사들이 작성하여 현장 수업에 활용하는 것이 미흡하였고, 둘째, 인지발달론에 따른 수학적 보존개념 형성시기에 적합한 개인차를 고려한 수학학습 지도는 효과적이었으며, 셋째 수학적인 개념을 조작${\rightarrow}$영상${\rightarrow}$상징의 인지경로에 따른 학습지도는 학업성취에 긍정적인 효과가 있었고, 넷째, 범례제시를 통한 개념형성 학습은 새로운 수학적인 개념을 쉽게 이해하고 학습의 흥미도와 자신감을 높여주고 있음을 알 수 있었다.

• 한국과학교육학회지
• /
• 제24권4호
• /
• pp.687-708
• /
• 2004

The purpose of this study is to investigate the relationships between cognitive conflict and students' causal attributions and to find out what kinds of attributions affect successful resolution of cognitive conflict in learning physics. Twenty-nine college students who attended a base general physics course took an attribution test and a conceptual pretest related to action and reaction concept. Of these, twenty students who revealed alternative conceptions were selected. They were confronted with a discrepant demonstration and took part in the cognitive conflict level test, a posttest, and delayed posttest. Those students who experienced high levels of cognitive conflict were selected and interviewed to find out what kinds of attributions affect resolving the conflict. When confronted with the discrepant event, the students who attributed success outcomes to "effort" experienced higher levels of cognitive conflict than those to "task difficulty." However, those students who revealed high levels of cognitive conflict and attributed success outcomes to effort did not always produce conceptual change. They had different perspectives on effort and conducted different effort activities to resolve the cognitive conflict. In addition, these effort activities appeared to include their motivational beliefs, metacognitive and volitional strategies. The results of this study indicate that in order for the conflicts to lead to change, students need to have the perspective on effort implying the use of the self-regulated learning strategy and to conduct effort activities based on them. Beyond cold conceptual change, this article suggests that there is a management strategy of cognitive conflict in the classroom context.

• Journal of Korean Biological Nursing Science
• /
• 제15권2호
• /
• pp.90-98
• /
• 2013

Purpose: The purpose of this study was to develop a clinical practice nursing students' microbiology program based on the mastery learning model, and to evaluate the effects of the program on nursing students' knowledge, self-efficacy, performance, and satisfaction related to the nursing students' microbiology program. Methods: The program was developed by using the processes of the mastery learning model. The pre-experimental research design involved a one group pretest-posttest design. The setting was a university located in Incheon, Korea. A total of 130 nursing students participated in the program including a theoretical lecture, clinical practice, and formative and summative evaluation. Results: Using the program that was designed and developed, results for the total score of self-efficacy, knowledge, and performance in the post-test application were significantly higher than in the pre-test application (p<.05). The satisfaction of hand hygiene and disinfection/contaminated hand microbial culture and disinfection test received the highest ratings. Conclusion: The application of a clinical practice nursing students' microbiology program was effective, and can be expanded to other nursing students. Future research with other study designs was warranted in order to prove the effect of a microbiology program based on the mastery learning model.

• 한국공간구조학회논문집
• /
• 제21권2호
• /
• pp.99-110
• /
• 2021

This study presents the estimation of crack depth by analyzing temperatures extracted from thermal images and environmental parameters such as air temperature, air humidity, illumination. The statistics of all acquired features and the correlation coefficient among thermal images and environmental parameters are presented. The concrete crack depths were predicted by four different machine learning models: Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB), and AdaBoost (AB). The machine learning algorithms are validated by the coefficient of determination, accuracy, and Mean Absolute Percentage Error (MAPE). The AB model had a great performance among the four models due to the non-linearity of features and weak learner aggregation with weights on misclassified data. The maximum depth 11 of the base estimator in the AB model is efficient with high performance with 97.6% of accuracy and 0.07% of MAPE. Feature importances, permutation importance, and partial dependence are analyzed in the AB model. The results show that the marginal effect of air humidity, crack depth, and crack temperature in order is higher than that of the others.

• 디지털융복합연구
• /
• 제19권9호
• /
• pp.411-421
• /
• 2021

본 연구는 학습자질문중심학습법과 온라인 퀴즈기반학습법을 생리학과 약리학 교과목에 순차적으로 적용하고 학습에 대한 효과를 비교하고자 간호학과 학생 총 173명을 대상으로 수행되었다. 전체 학생들의 학습동기는 8주차에 비해 15주차에 유의하게 낮아졌고(T=2.843, p=.005), 두 학습법을 적용한 순서에 따라서도 유의한 차이가 없는 것으로 나타났다. 그러나, 약리학 교과목 학습자들의 학습만족도는 온라인 퀴즈기반학습법만을 적용하였을 때 학습자질문중심학습법을 적용하였을 때보다 유의하게 높았다(t=2.184, p=.003). 본 연구 결과, 기초간호학교과목에 학습자질문중심학습법과 온라인 퀴즈기반학습법 중 어느 것이 더 효과적이라고 말할 수 없으며 순차적인 병용효과도 없으므로, 향후 수업 설계에서는 한 과목에 단일 학습법을 적용하거나 두 가지 학습법을 처음부터 병행하여 사용할 것을 제안한다.