• The Journal of the Acoustical Society of Korea
• /
• v.35 no.2
• /
• pp.143-148
• /
• 2016

Deep neural network that effectively capture the characteristics of data has been widely used in various applications. However, the amount of sound database is often insufficient for learning the deep neural network properly, so resulting in overfitting problems. In this paper, we propose a transfer learning framework that can effectively train the deep neural network even with insufficient sound event data by employing rich speech or music data. A series of experimental results verify that proposed method performs significantly better than the baseline deep neural network that was trained only with small sound event data.

• Journal of The Korean Association of Information Education
• /
• v.6 no.2
• /
• pp.120-129
• /
• 2002

In this paper, I survey the field which students use ICT and propose a teaching and learning model to improve students' ability in using ICT. Also, I apply it and prove its' effect. Because Problem Based Learning treats ill-structured problem which reflects actuality, Students can pick up the actual knowledge and become verse in general principle or concept which can transmit resemble problem or situation. Therefore, I hope a teaching and learning model which I propose in this paper has an effect to improve students' ability in using ICT.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.333-342
• /
• 2021

The purpose of this study is to compare the differences in transfer motivation and learning self-efficacy before and after applying virtual simulation for nursing in psychiatric nursing practice, and to provide them as basic data for effective psychiatric practical education. This study was conducted from October to December 2020. The subjects were 41 people who were enrolled in the third year of a located in U city, and who had received psychiatric nursing practice education using virtual simulation for nursing. Data were analyzed by paired t-test and pearson's correlation coefficient. After practice compared to before psychiatric nursing practice with virtual simulation nursing applied, transfer motivation was significantly increased and learner self-efficacy increased, but it was not statistically significant. Therefore, It was confirmed that psychiatric nursing practice education using virtual simulation for nursing is partly an effective practice strategy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.768-771
• /
• 2024

인간의 산업 활동으로 인하여 동물들의 생존이 위협받으면서, 동물의 서식 분포를 효과적으로 파악할 수 있는 자동 야생동물 모니터링 기술의 필요성이 점점 더 커지고 있다. 그중에서도 동물 소리 분류 기술은 시각적으로 식별이 어려운 동물에게도 효과적으로 적용할 수 있는 장점으로 인하여 널리 사용되고 있다. 최근 심층학습 기반의 분류 모델들이 좋은 판별 성능을 보여주고 있어 동물 소리 분류에 많이 사용되고 있지만, 희귀종과 같이 개체 수가 적어 데이터가 부족한 경우에는 학습이 제대로 이루어지지 않을 수 있다. 또한, 이러한 모델들은 모델 내부에서 일어나는 추론 과정을 알 수 없어 결과를 완전히 신뢰하고 사용하는 데 제약이 따른다. 이에 본 논문에서는 전이 학습을 통해 데이터 부족 문제를 고려하고, SHAP을 이용하여 분류 모델의 추론 과정을 해석하는 설명가능한 동물 소리 분류 기법을 제안한다. 실험 결과, 제안하는 기법은 지도 학습을 한 경우보다 분류 성능이 향상됨을 확인하였으며, SHAP 분석을 통해 모델의 분류 근거를 이해할 수 있었다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.259-268
• /
• 2023

The purpose of this study was to verify the effectiveness of mental simulation practice training using standardized patients for nursing students. This study is a single-group pre- and post-design study, and for data collection, a structured questionnaire was provided to 95 nursing students from a university located in J. The collected data was analyzed using the SPSS/WIN 27.0 program. Results of the study The mental simulation practice training program using standardized patients improved the subject's learning motivation (t=-2.011, p=.046), learning self-efficacy (t=-2.225, p=.027), and learning satisfaction (t=-). 3.428, p=.001) and transfer motivation (t=-2.628, p=.009). In addition, as a result of analyzing the self-assessment contents by text mining, words related to mental simulation practice education using standardized patients included situation, experience, acting, communication, scenario, and mental nursing clinical practice, and words related to satisfaction were actual, There was help, response, understanding, variety, etc. As a result of this study, an environment similar to the actual situation was implemented, and the mental simulation training program applying various cases was found to be effective in practical education of nursing students, so it is necessary to actively utilize it to improve the ability to adapt to the field in the future.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.9-18
• /
• 2019

This study investigates the factors affecting the educational satisfaction and the transfer of learning of cyber crime prevention education students in order to confirm the effectiveness of the current education. Based on the CIPP model, we confirmed whether the level of social demand and the level of knowledge in the context evaluation, recency of subjects in the input evaluation and interaction in the process evaluation affect the educational satisfaction and the transfer of learning of the students by conducting the survey for the students. As a result of analysis, it was proved that the level of knowledge, recency of subjects and interaction had a significant relationship with the educational satisfaction and recency of subjects, interaction and educational satisfaction significantly affect transfer of learning. Based on the findings, this study provides a few constructive suggestions to improve the effectiveness of the cyber crime prevention education program.

• Conservation Science in Museum
• /
• v.31
• /
• pp.55-70
• /
• 2024

Style transfer algorithms are currently undergoing active research and are used, for example, to convert ordinary images into classical painting styles. However, such algorithms have yet to produce appropriate results when applied to Korean cultural heritage images, while the number of cases for such applications also remains insufficient. Accordingly, this study attempts to develop a style transfer algorithm that can be applied to styles found among Korean cultural heritage. The algorithm was produced by improving data comprehension by enabling it to learn meaningful characteristics of the styles through representation learning and to separate the cultural heritage from the background in the target images, allowing it to extract the style-relevant areas with the desired color and texture from the style images. This study confirmed that, by doing so, a new image can be created by effectively transferring the characteristics of the style image while maintaining the form of the target image, which thereby enables the transfer of a variety of cultural heritage styles.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.339-348
• /
• 2021

In recent software defect prediction research, defect prediction between cross projects and cross-version projects are actively studied. Cross-version defect prediction studies assume WP(Within-Project) so far. However, in the CV(Cross-Version) environment, the previous work does not consider the distribution difference between project versions is important. In this study, we propose an automated Bayesian optimization framework that considers distribution differences between different versions. Through this, it automatically selects whether to perform transfer learning according to the difference in distribution. This framework is a technique that optimizes the distribution difference between versions, transfer learning, and hyper-parameters of the classifier. We confirmed that the method of automatically selecting whether to perform transfer learning based on the distribution difference is effective through experiments. Moreover, we can see that using our optimization framework is effective in improving performance and, as a result, can reduce software inspection effort. This is expected to support practical quality assurance activities for new version projects in a cross-version project environment.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.4
• /
• pp.35-48
• /
• 2018

This study aims to assess the training effect of QFD(Quality Functional Deployment) program for 3 years over startups, adopted from the conventional QFD widely used in the large companies to break up to a sluggish sales and growth, for employees working in startup whether the participants in startup and venture company taking this lessons into their real tasks or not. In particular, the focus of this study falls on figuring out whether individual characteristics of the participants play a role in moderating effect over transfer intension factors and its link path structure. The research results drive out two significant findings. First, in terms of relationship between the influence of transfer intension by self-efficacy and the validity of training content with the learner's readiness, the moderating effect of demographic features of the participants is effective partially by the sex and fully by their working position, but not statistically significant by age, education, and the prior startup career. This research deliver the following significant implication that the active participation of CEO level, decision-maker guarantee the higher performance of the training program like QFD program, more stresses falling on practical implementation in real business rather than just ending up with career training. This study gives significant policy implication to quasi-government organization running all public startup training projects.