• 공학교육연구
• /
• 제15권5호
• /
• pp.54-59
• /
• 2012

It is reported that the constructivistic learning method (CLM) enhances the understanding of the students in the learning process, especially in engineering classes. In CLM-based classes, the students can take the initiative in the learning process, which is called the student-centered model of the learning process. This is different from the traditional learning method based on the teacher-centered model, where a teacher plays the central role in the learning process of students. The authors have applied the method of CLM to one of the Engineering classes, namely production planning and inventory control (PPIC) class for undergraduate students. The PPIC class provides multimedia-based study materials and factory visits as well as regular lecture sections to cover the whole subject of inventory control theory and practice. In the review sessions, students are divided into several groups, and question-and-answer discussions were actively carried out among these groups under the support of the teacher as a facilitator. It was observed that the student engagement in the class was very active compared to the conventional lecture-based classes. As for further support of students understanding on the subject, simulation-based materials are also under study for the class. This paper presents the review of case study of CLM-based PPIC class and discusses the feasibility of simulation-based study materials for further improvement of the class.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• 한국멀티미디어학회논문지
• /
• 제6권4호
• /
• pp.676-684
• /
• 2003

eLearning can be defined as an approach to teaching and teaming that utilises Internet technologies to communicate and collaborate in an educational context. This includes technology that supplements traditional classroom training with web-based components and learning environments where the educational process is experienced online. The use of hypertext as an educational tool has a very rich history. The advent of the internet and one of its major application, the world wide web (WWW), has given a tremendous boost to the theory and practice of hypermedia systems for educational purposes. However, the web suffers from an inability to satisfy the heterogeneous needs of a large number of users. For example, web-based courses present the same static teaming material to students with widely differing knowledge of the subject. Adaptive hypermedia techniques can be used to improve the adaptability of eLearning. In this paper we report an approach to the design a unified implementation framework suitable for web-based eLearning that accommodates the three main dimensions of hypermedia adaptation: content, navigation, and presentation. The framework externalises the adaptation strategies using XML notation. The separation of the adaptation strategies from the source code of the eLearning software enables a system using the framework to quickly implement a variety of adaptation strategies. This work is a part of our more general ongoing work on the design of a framework for adaptive content delivery. parts of the framework discussed in this paper have been imulemented in a commercial eLearning engine.

• 정보교육학회논문지
• /
• 제21권2호
• /
• pp.183-190
• /
• 2017

본 연구는 스마트 블렌디드 수업 전략이 역사수업에서 어떤 효과가 나타나는지에 대한 분석을 하였다. 수업전략의 효과성은 학업 성취도와 학습 흥미도로 설정하고 역사수업에 참가한 초등학생들을 대상으로 제안된 스마트 블렌디드 수업전략을 적용하여 비교집단과 비교하였다. t-검증 결과, 제안된 수업전략이 학생들의 학업성취도 및 학습흥미도에 긍정적인 영향을 주었다. 또한 질적 분석을 통하여 학생들이 수업의 이해도가 높아졌고 집중력이 향상되는 효과를 보여주었다.

• Journal of Information Processing Systems
• /
• 제1권1호
• /
• pp.14-21
• /
• 2005

Even though mainly statistical methods have been used in anomaly network intrusion detection, to detect various attack types, machine learning based anomaly detection was introduced. Machine learning based anomaly detection started from research applying traditional learning algorithms of artificial intelligence to intrusion detection. However, detection rates of these methods are not satisfactory. Especially, high false positive and repeated alarms about the same attack are problems. The main reason for this is that one packet is used as a basic learning unit. Most attacks consist of more than one packet. In addition, an attack does not lead to a consecutive packet stream. Therefore, with grouping of related packets, a new approach of group-based learning and detection is needed. This type of approach is similar to that of multiple-instance problems in the artificial intelligence community, which cannot clearly classify one instance, but classification of a group is possible. We suggest group generation algorithm grouping related packets, and a learning algorithm based on a unit of such group. To verify the usefulness of the suggested algorithm, 1998 DARPA data was used and the results show that our approach is quite useful.

• Korean journal of medical education
• /
• 제30권4호
• /
• pp.359-364
• /
• 2018

Purpose: Learning physiological concepts and their practical applications in the appropriate contexts remains a great challenge for undergraduate medical students. Hence the present study aimed to analyze the learning experience of undergraduate medical students during an active learning process of 'preparation of models' depicting physiological concepts. Methods: A total of 13 groups, involving 55 undergraduate medical students with three to five individuals in each group, were involved in model preparation. A total of 13 models were exhibited by the students. The students shared their learning experiences as responses to an open-ended questionnaire. The students' responses were analyzed and generalized comments were generated. Results: Analysis of the results showed that the act of 'model preparation' improved concept understanding, retention of knowledge, analytical skills, and referral habits. Further, the process of 'model preparation' could satisfy all types of sensory modality learners. Conclusion: This novel active method of learning could be highly significant in students' understanding and learning physiology concepts. This approach could be incorporated in the traditional instructor-centered undergraduate medical curriculum as a way to innovate it.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4246-4267
• /
• 2020

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

• East Asian mathematical journal
• /
• 제38권2호
• /
• pp.215-240
• /
• 2022

In this study, we proposed a learning-centered DIY mathematics instruction for students to actively design instructions and developed important competencies. The research problems of this study were as follows. First, how did learning-centered DIY mathematics instruction affect math academic achievement? Second, how did learning-centered DIY mathematics instruction affect the affective domain? Third, what was the reaction of students to the implementation of the learning-centered DIY mathematics instruction? For this purpose, this study was conducted with 58 students in 2 classes of 2nd grade of 00 High School located in 00 Metropolitan City. As a result of the study, first, it could be seen that the study group that taught the learning-centered DIY mathematics instruction was very helpful in the change of mathematics academic achievement compared to the comparative group who taught the explanatory instruction based on traditional textbooks. Second, the research group showed a significant improvement in the affective domain compared to the comparison group. Third, the responses of the students in the research group through the learning-centered DIY mathematics instruction improved in a positive direction, and there were some negative responses.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권2호
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

• 무역학회지
• /
• 제46권6호
• /
• pp.191-209
• /
• 2021

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.