• Journal of Korea Multimedia Society
• /
• v.22 no.8
• /
• pp.844-851
• /
• 2019

In this paper, we propose a loss function in CNN that introduces inter-class amplitudes to increase inter-class loss and reduce intra-class loss to increase of face recognition performance. This loss function increases the distance between the classes and decreases the distance in the class, thereby improving the performance of the face recognition finally. It is confirmed that the accuracy of face recognition for visible light image of proposed loss function is 99.62%, which is better than other loss functions. We also applied it to face recognition of visible and near-infrared complex images to obtain satisfactory results of 99.76%.

• The Journal of the Korea Contents Association
• /
• v.22 no.1
• /
• pp.324-336
• /
• 2022

The purpose of this study is to comparatively analyze academic achievement and class satisfaction in college general mathematics between face-to-face classes and remote classes. For this study, we selected 97 first-year students from three departments of an engineering college at M University. Among the subjects of the study, 39 students in Department A and 36 students in Department B took remote classes using pre-recorded class videos, and 22 students in Department C took face-to-face classes. The subjects of this study were evaluated by one professor as the same type of problem with the same content for the same textbook. Among the subjects of the study, 35 students in department A, 34 students in department B, and 17 students in department C who entered through rolling admissions were collected and homogeneity tests were conducted. And then we analyzed the scores of these students' midterm and final exams for general mathematics in the first semester of 2021. Also, we compared and analyzed the academic achievement and class satisfaction of general mathematics subjects for face-to-face classes and remote classes for all study subjects. The results of this study are as follows. First, there is a significant difference in students' academic achievement of general mathematics between face-to-face classes and remote classes. Second, there is a significant difference in class satisfaction between face-to-face classes and non- face-to-face remote classes.

• Journal of Korea Multimedia Society
• /
• v.22 no.6
• /
• pp.655-664
• /
• 2019

In this paper, we propose a novel way of combining multiple deep convolutional neural network (DCNN) architectures which work well for accurate video face identification by adopting a serial combination of 3D and 2D DCNNs. The proposed method first divides an input video sequence (to be recognized) into a number of sub-video sequences. The resulting sub-video sequences are used as input to the 3D DCNN so as to obtain the class-confidence scores for a given input video sequence by considering both temporal and spatial face feature characteristics of input video sequence. The class-confidence scores obtained from corresponding sub-video sequences is combined by forming our proposed class-confidence matrix. The resulting class-confidence matrix is then used as an input for learning 2D DCNN learning which is serially linked to 3D DCNN. Finally, fine-tuned, serially combined DCNN framework is applied for recognizing the identity present in a given test video sequence. To verify the effectiveness of our proposed method, extensive and comparative experiments have been conducted to evaluate our method on COX face databases with their standard face identification protocols. Experimental results showed that our method can achieve better or comparable identification rate compared to other state-of-the-art video FR methods.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.57-62
• /
• 2022

This study was conducted with the purpose of listening to the explanations of artworks in the non-face-to-face class and confirming the learner's feelings as a result of the class. The proposed system listens to the explanation of the artwork, inputs the learner's emotions with a dedicated key, and expresses the result in music. To this end, the direction of the non-face-to-face art appreciation class model using the emotion key was set, and based on this, a system for non-face-to-face art appreciation was constructed. The learner will use the 'smart device using the emotion key' proposed in this study to listen to the explanation of the artwork and to input the emotion for the question presented. Through the proposed system, learners can express their emotional state in online art classes, and instructors receive the results of class participation and use them in various ways for educational analysis.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.519-524
• /
• 2021

As the COVID-19 situation continued to spread to the local community along with the spread due to influx, each university had to conduct all online classes and partially online classes. The purpose of this study was to investigate the satisfaction of learners with the content and lecture contents by paying attention to online non-face-to-face classes according to the change of the class environment in the Corona 19 situation. Satisfaction survey on online non-face-to-face class major subjects was analyzed using questionnaires from June 1 to June 11, 2021, targeting 2nd and 3rd year students in the Department of Radiology at S University in Daegu. As a result of the study, satisfaction with content and class content was found to be an average of 3.78 ± 0.75 points, and learning satisfaction was found to be an average of 3.00 ± 1.14 points. In addition, when taking online non-face-to-face classes, the correlation between students' class attitude and content and class content satisfaction was the highest (r=0.555, p<0.01), and it was found that there was also a correlation between content and class content satisfaction and learning satisfaction. (r=0.331, p<0.01). I think that satisfaction with non-face-to-face online classes can be improved if the quality of content is improved during non-face-to-face online major classes as well as more active interactions between students and professors.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.8
• /
• pp.279-290
• /
• 2021

As the university's academic management was not carried out smoothly due to COVID-19, and most of them were conducted as non-face-to-face classes, students' dropout is steadily increasing. In this study focus group interviews were conducted to analyze physics students and professors' recognition of the COVID-19 non-face-to-face class environment. Based on the results, the implications of non-face-to-face classes for physics education were presented. Physics students described their feelings about un-tact teaching as 'the class in which the body is comfortable but the mind is uncomfortable', 'a person who is smarter than me seems to explain a book, reading it' and 'a short clip lecture which may be comfortable but cause losses to me', while the professors also described them as 'a fully transformed class system' and 'a online class putting much burden on me'. Regarding school dropout, students said that the concerns about dropout during non-face-to-face classes were deepened about transfer or transfer. The professors said that the department atmosphere had lost vitality due to the increase in non-face-to-face classes and academic dropouts, and had a lot of worries because of the recruitment rate and external university evaluation. The implications of the COVID-19 non-face-to-face class situation for physics education suggest that it is required to strengthen the interaction between professors and students, finding ways to enhance the sense of reality to supplement laboratory classes and giving opportunities to professors to share their pedagogical contents knowledge in physics.

• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.277-282
• /
• 2021

The purpose of this thesis is to suggest the direction of various online education media to be developed in the future by studying the necessity and cases of non-face-to-face online craft education programs. To this end, among the online class platforms currently operated in Korea, four places that contain craft education programs were selected and analyzed for comparison. Class101, Hobbyful, Conects-Hobby Class, and Air Klass are examples. As a result of the study, the common features and advantages of the convenience of accessing contents and the diversity of class composition were found. However, there was a limitation in that the real-time inquiry and response system was not systematically implemented in most online class platforms. In particular, as the number of users of the online class platform is gradually increasing in the untact era caused by Covid-19, continuous research and development will be required to ensure that interaction, the most important characteristic of face-to-face, can also be performed well on online platforms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.157-164
• /
• 2020

In 2020, due to COVID-19, all universities in Korea were conducting non-face-to-face classes. The purpose of this study is to study what factors affect academic achievement under such non-face-to-face instruction, especially for engineering students where practical training is important. Validity of the statistical hypothesis defined in this study by applying a structural equation model using questionnaires about academic achievement for engineering students at University D for this study. In addition, I would like to suggest what factors should be considered in non-face-to-face classes, especially in engineering colleges. As a result of the study, it was found that students' Q&A, feedback and e-learning system had a direct influence on academic achievement. In addition, it was confirmed that they had an indirect influence on academic achievement through the parameters of theory class and practical class.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.645-647
• /
• 2022

코로나 팬더믹으로 인한 비대면 수업은 지속적인 운영을 통해 개선·발전되었다. 2022학년도부터 대면수업으로 전환되면서 온라인 플랫폼에 대한 적응력이 높아지고, 비대면 수업 경험이 축적된 학습자들을 위한 대면 수업의 변화가 필요하게 되었다. 본 논문은 프로그래밍 수업에서 비대면 방식과 대면 방식에 대한 경험이 있는 학습자들의 수업방식에 따른 만족도 및 의견을 조사·분석함으로써 서로 다른 두 방식의 장점을 활용한 수업모델을 모색하는데 필요한 학습자 의견 도출에 그 목적이 있다. 조사 결과, 학습자들은 대면 수업을 선호하나 비대면 학습경험이 많을수록 대면 수업에서의 단점을 비대면 수업을 통해서 해소할 수 있는 부분이 있음을 인지하고, 비대면 방식을 대면 수업에 활용하는 것을 긍정적으로 생각하는 것으로 나타났다. 이를 통해 향후 대면 프로그래밍 수업에서 비대면 방식을 결합한 하이드리드 방식의 수업 운영을 통한 수업 효과 증진 모델이 필요한 것으로 사료된다.