• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.411-418
• /
• 2020

In the field of information security, IDS(Intrusion Detection System) is normally classified in two different categories: signature-based IDS and anomaly-based IDS. Many studies in anomaly-based IDS have been conducted that analyze network traffic data generated in cyberspace by machine learning algorithms. In this paper, we studied pre-processing methods to overcome performance degradation problems cashed by rare classes. We experimented classification performance of a Machine Learning algorithm by reconstructing data set based on rare classes and semi rare classes. After reconstructing data into three different sets, wrapper and filter feature selection methods are applied continuously. Each data set is regularized by a quantile scaler. Depp neural network model is used for learning and validation. The evaluation results are compared by true positive values and false negative values. We acquired improved classification performances on all of three data sets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.503-523
• /
• 2022

Nowadays, many attendance applications utilise biometric techniques such as the face, fingerprint, and iris recognition. Biometrics has become ubiquitous in many sectors. Due to the advancement of deep learning algorithms, the accuracy rate of biometric techniques has been improved tremendously. This paper proposes a web-based attendance system that adopts facial recognition using open-source deep learning pre-trained models. Face recognition procedural steps using web technology and database were explained. The methodology used the required pre-trained weight files embedded in the procedure of face recognition. The face recognition method includes two important processes: registration of face datasets and face matching. The extracted feature vectors were implemented and stored in an online database to create a more dynamic face recognition process. Finally, user testing was conducted, whereby users were asked to perform a series of biometric verification. The testing consists of facial scans from the front, right (30 - 45 degrees) and left (30 - 45 degrees). Reported face recognition results showed an accuracy of 92% with a precision of 100% and recall of 90%.

• Journal of Digital Convergence
• /
• v.15 no.5
• /
• pp.71-77
• /
• 2017

This study examines the effects of in-company English programs on Korean employees' English learning. During the twelve weeks, 68 employees in Korea engaged in an English learning program in the workplace. Before and after the program, pre- and post-tests were conducted to see if their English proficiency improved. Pre- and post-surveys and interviews were also administered to understand how they perceived the program. Results show that the employees improved their English oral proficiency and their attitudes toward English learning positively changed, as a result of participating in the program. Also, the program appeared to be successful, meeting their needs. Given that little research has investigated the effects of in-company English learning, this study provides insights on the effectiveness of English programs in the workplace in Korea.

• Journal of Convergence for Information Technology
• /
• v.9 no.11
• /
• pp.212-217
• /
• 2019

This study is a convergence study attempted to understand the learning effects of oral health education class applying action learning on the communication ability and problem-solving ability in dental hygiene students. The subjects of this study were 37 students in the third year of dental hygiene department. As a result, the learning effects of oral health education class applying action learning on the communication ability(p<0.001) and problem-solving ability(p<0.001) showed positive changes in the pre and post comparison. The changes in the scores of sub-dimensions of the communication ability and problem-solving ability were also significant in the pre and post comparison. As the class applying action learning is effective in improving the learner's communication ability and problem-solving ability, it should be utilized as the leaner participation-oriented teaching method for design and operation of dental hygiene education.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1227-1236
• /
• 2021

Adversarial attack, one of the attacks on deep learning classification model, is attack that add indistinguishable perturbations to input data and cause deep learning classification model to misclassify the input data. There are various adversarial attack algorithms. Accordingly, many studies have been conducted to detect adversarial attack but few studies have been conducted to classify what adversarial attack algorithms to generate adversarial input. if adversarial attacks can be classified, more robust deep learning classification model can be established by analyzing differences between attacks. In this paper, we proposed a model that detects and classifies adversarial attacks by constructing a random forest classification model with input features extracted from a target deep learning model. In feature extraction, feature is extracted from a output value of hidden layer based on class predicted by the target deep learning model. Through Experiments the model proposed has shown 3.02% accuracy on clean data, 0.80% accuracy on adversarial data higher than the result of pre-existing studies and classify new adversarial attack that was not classified in pre-existing studies.

• Journal of The Korean Association For Science Education
• /
• v.32 no.4
• /
• pp.703-716
• /
• 2012

Frequently, pre-service elementary teachers are asked to write reflective journals on their teaching during teacher education program. However, writing reflective journals can not guarantee pre-service teachers to learn from their experience. In this study, 44 reflective journals of pre-service elementary teachers on their science teaching were analyzed in terms of 'productive reflection', a concept suggested by Davis (2006). Productive reflection may help teachers' effective learning by considering interrelationships among aspects of teaching including learners and learning, subject matter knowledge, assessment, and instruction. The result showed what aspects of teaching were included, emphasized, and integrated in the pre-service elementary teachers' reflective journals. Implications for teacher education would be discussed.

• Journal of Engineering Education Research
• /
• v.18 no.2
• /
• pp.77-88
• /
• 2015

Recently, there has been an increasing interest in 'Flipped Learning,' an IT-based learner-centered teaching-learning method corresponding to meet the paradigm of the future education. For smooth Flipped Learning, there are three steps in total: a pre-class should precede; then, in the structure of classes in the classroom, in-class learning among peer learners should be done; and lastly, the operation of a post-class should be done. For successful Flipped Learning, class elements in each step should be designed with a time difference, interconnected so as to achieve a single educational objective. However, it was found that there was a limitation in that the teaching-learning model of the preceding Flipped Learning consisted of the order of analysis, design, development, implementation and evaluation as general procedures, so it would not sufficiently consider the situations of Flipped Learning only. On this background, this thesis proposes a differentiated Flipped Learning model for mastery learning in a subject of an institute of technology as a model of systematic instructional design and presents a case of a class applied to an actual subject of computer engineering.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.483-492
• /
• 2020

Considering the fact that many students and parents spend a considerable amount of time and economic power on prior learning and that the environments of internet-based society change rapidly, it is worth examining the status and effectiveness of prior learning. In response, the study surveyed 186 first-year students of A high school in Changwon on the basic status of science prior learning. By the analysis results for the status, 39.8% of the students surveyed said they had experience in prior learning in science. Among the students experienced, 56 students who started science prior learning after the start of winter vacation in the third grade of middle school were analyzed the specific status of science prior learning and the impact of science prior learning on science achievements. The semi-subject form of pre-learning in science showed the highest response rate with 50.0 percent, and the motivation for pre-learning in science was the highest with 33.9 percent improvement in test scores. The confidence and learning intention were positive when conducting prior learning in a semi-subject form, and interest and value were positive when conducting prior learning in a self-directed form. As a result of the survey on the effect of science prior learning, 71.4% of the students who experienced science prior learning showed positive scientific achievement.

• Journal of Korean Home Economics Education Association
• /
• v.31 no.1
• /
• pp.77-88
• /
• 2019

This study was to execute the flipped learning as a learner-centered teaching and learning method in the course on family living culture for home economics education students in a college of education, and to investigate its effect. Flipped learning was designed in three stages(Pre class/In class/After class), and a questionnaire survey was distributed to 40 students to measure the class satisfaction. In addition, class worksheets and reflection journals that students wrote after every class were analyzed. Students positively evaluated flipped learning because they could take non-competition class with questions and discussion, etc. escaping from a one-way lecture. This study found that the level of class satisfaction was high due to high learning effect as the dual learning was available in case of prerequisite learning or individual learning. In particular, the class using Visual Thinking was considered interesting and useful in understanding and summarizing the learning contents. This study has shown that the willingness to take other flipped learning class in their major was high. To conclude, this study has found positive learning effects in the learner-centered teaching and learning method or flipped learning for the course concerning family living culture. This researcher expects that flipped learning may be utilized in the secondary education in the future as an effective learner-centered teaching and learning method for the purpose of fostering talents for the future in the era of the fourth industrial revolution.