• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.608-620
• /
• 2021

Recent deep learning-based face super-resolution (FSR) works showed significant performances by utilizing facial prior knowledge such as facial landmark and dictionary that reflects structural or semantic characteristics of the human face. However, most of these methods require additional processing time and memory. To solve this issue, this paper propose an efficient FSR models using knowledge distillation techniques. The intermediate features of teacher network which contains dictionary information based on major face regions are transferred to the student through adversarial multi-scale features distillation. Experimental results show that the proposed model is superior to other SR methods, and its effectiveness compare to teacher model.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.885-896
• /
• 2022

Motor failure in manufacturing plays an important role in future A/S and reliability. Motor failure is detected by measuring sound, current, and vibration. For the data used in this paper, the sound of the car's side mirror motor gear box was used. Motor sound consists of three classes. Sound data is input to the network model through a conversion process through MelSpectrogram. In this paper, various methods were applied, such as data augmentation to improve the performance of classifying fault motors and various methods according to class imbalance were applied resampling, reweighting adjustment, change of loss function and representation learning and classification into two stages. In addition, the curriculum learning method and self-space learning method were compared through a total of five network models such as Bidirectional LSTM Attention, Convolutional Recurrent Neural Network, Multi-Head Attention, Bidirectional Temporal Convolution Network, and Convolution Neural Network, and the optimal configuration was found for motor sound classification.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.230-240
• /
• 2022

Sharing of online videos via internet is an emerging and important concept in different types of applications like surveillance and video mobile search in different web related applications. So there is need to manage personalized web video retrieval system necessary to explore relevant videos and it helps to peoples who are searching for efficient video relates to specific big data content. To evaluate this process, attributes/features with reduction of dimensionality are computed from videos to explore discriminative aspects of scene in video based on shape, histogram, and texture, annotation of object, co-ordination, color and contour data. Dimensionality reduction is mainly depends on extraction of feature and selection of feature in multi labeled data retrieval from multimedia related data. Many of the researchers are implemented different techniques/approaches to reduce dimensionality based on visual features of video data. But all the techniques have disadvantages and advantages in reduction of dimensionality with advanced features in video retrieval. In this research, we present a Novel Intent based Dimension Reduction Semi-Supervised Learning Approach (NIDRSLA) that examine the reduction of dimensionality with explore exact and fast video retrieval based on different visual features. For dimensionality reduction, NIDRSLA learns the matrix of projection by increasing the dependence between enlarged data and projected space features. Proposed approach also addressed the aforementioned issue (i.e. Segmentation of video with frame selection using low level features and high level features) with efficient object annotation for video representation. Experiments performed on synthetic data set, it demonstrate the efficiency of proposed approach with traditional state-of-the-art video retrieval methodologies.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.19-33
• /
• 2022

With the explosive growth of social media, its abundant text-based data generated by web users has become an important source for data analysis. For example, we often witness online movie reviews from the 'Naver Movie' affecting the general public to decide whether they should watch the movie or not. This study has conducted analysis on the Naver Movie's text-based review data to predict the actual ratings. After examining the distribution of movie ratings, we performed semantics analysis using Korean Natural Language Processing. This research sought to find the best review rating prediction model by comparing machine learning and deep learning models. We also compared various regression and classification models in 2-class and multi-class cases. Lastly we explained the causes of review misclassification related to movie review data characteristics.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.9-11
• /
• 2016

최근 UHDTV(ultra high definition television) 등의 고해상도 디스플레이가 시장에 등장하면서, 기존의 저해상도 FHD(full high definition) 영상을 고해상도 영상으로 변환할 수 있는 초해상화(super-resolution, SR) 기법들이 각광을 받고 있다. 그 중, 선형 매핑(linear mapping)을 사용하여 저해상도 패치(patch)로부터 고해상도 패치를 복원하는 초해상화 기법은 상대적으로 낮은 복잡도로 좋은 품질의 고해상도 영상을 생성한다. 그러나 이러한 기법은 단순한 선형 매핑을 기반으로 하기 때문에 복잡한 비선형적(nonlinear) 저해상도-고해상도 관계를 예측하기 힘든 단점이 있다. 최근 각광받는 딥러닝(deep learning) 기술은 다층(multi-layer) 네트워크를 쌓아 입력과 출력 간의 복잡한 비선형 관계를 훈련시켜 좋은 성능을 보이는데, 이를 바탕으로 본 논문에서는 다중의 레이어로 구성된 다층 선형 매핑(multi-layer linear mappings, MLLM)을 기반으로 하는 초해상화 기법을 새롭게 제안한다. 제안하는 다층 선형 매핑은 기존 선형 매핑보다 비선형적 관계를 더 잘 예측하여 높은 품질의 고해상도 영상을 생성할 수 있게 한다. 제안된 초해상화 기법은 딥러닝 기반 초해상화 기법과 필적하는 품질의 고해상도 영상을 생성하면서도 더 낮은 복잡도를 지니는 것을 확인하였다.

• Hwankyungkyoyuk
• /
• v.11 no.2
• /
• pp.14-25
• /
• 1998

The Quality of human living depends on the environmental quality of the region sustaining the life. The environmental deterioration of the modern society is due to mechanical environmentalism. For the better quality of the life, The changes of recognition and attitude on the environments are required. These changes of mind are also important in environmental education for teenagers. The 7th national curriculum, officially anounced December 1998, focuses on the change of attitude to environments and practical behavior in real life for “Environments”, the environmental education curriculum in middle school. Basic elements of the curriculum are cultivation of the pro-environmental thinking, multi-levelling of teaching materials and methods, and encouraging of student participating activity. Actually, the curriculum construction is composed of stepped-levelling of teaching and learning, reasonable contents volume, encouraging of student practice, and suggesting of evaluation standards of textbook writing. Three main subjects of environmental education for middle school consist of (1) man and environment, (2) recognition of environmental problem, and (3) protection activity for environment. Methodology of environmental education can include multi-disciplinary approaches, variable teaching methods, and continuing evaluation of student practice and participation attitude. Environmental education for teenagers relating to the 7th national curriculum focuses on recognition of the environmental problems and practice activity in daily life. The recognition includes considering relationship of human life to environment, solving environmental problems in regional context, and development of comprehensive understanding concept of the environments. For the practice education, variable teaching methods, such as field survey and application of multi-media, are needed.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.573-579
• /
• 2019

To achieve fully autonomous driving, the perceptual skills of the surrounding environment must be superior to those of humans. The $60^{\circ}$ angle, $120^{\circ}$ wide angle cameras, which are used primarily in autonomous driving, have their disadvantages depending on the viewing angle. This paper uses a multi-angle object recognition system to overcome each of the disadvantages of wide and narrow-angle cameras. Also, the aspect ratio of data acquired with wide and narrow-angle cameras was analyzed to modify the SSD(Single Shot Detector) algorithm, and the acquired data was learned to achieve higher performance than when using only monocular cameras.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.4-7
• /
• 2022

Recently, multi-view depth estimation methods using deep learning network for the 3D scene reconstruction have gained lots of attention. Multi-view video contents have various characteristics according to their camera composition, environment, and setting. It is important to understand these characteristics and apply the proper depth estimation methods for high-quality 3D reconstruction tasks. The camera setting represents the physical distance which is called baseline, between each camera viewpoint. Our proposed methods focus on deciding the appropriate depth estimation methodologies according to the characteristics of multi-view video contents. Some limitations were found from the empirical results when the existing multi-view depth estimation methods were applied to a divergent or large baseline dataset. Therefore, we verified the necessity of obtaining the proper number of source views and the application of the source view selection algorithm suitable for each dataset's capturing environment. In conclusion, when implementing a deep learning-based depth estimation network for 3D scene reconstruction, the results of this study can be used as a guideline for finding adaptive depth estimation methods.

• Journal of The Korean Association of Information Education
• /
• v.6 no.1
• /
• pp.42-52
• /
• 2002

For an effective listening to music, a repeated listening to music should be possible without any restriction of time and space as well as to music for a music class and the various multi-media learning materials for listening to music is required. However, an individualized and repeated listening is difficult and an individualized listening materials are lacking. To solve these problems, learning system for listening to music in elementary school sharing learning materials required for it and including learning factors of listening to music is required. Therefore, this study analyzes learning factors of listening to music in elementary school and the learning system for listening to music is designed and developed to make elementary students have their own active listening to music and feel achievement and confidence by teacher's evaluation of their writings after listening to music and experience a joyful musical activity. And it is applied to elementary school.

• Cartoon and Animation Studies
• /
• s.48
• /
• pp.271-310
• /
• 2017

This paper examines the composition and the content of media art which is an art education subject in a national curriculum of Australia; and discusses implications for Korean education curriculums. Media covered by Media Art subject in Australia are the multi types of general media including TV, movie, video, newspaper, radio, video game, the internet, and mobile media; and their contents. The purpose of ACARA's media art education curriculum is to improve creative use, knowledge, understanding, and technology of communication techniques for multiple purposes and the audiences. Through the Media Art subject, both the students and the community are able to participate in the actual communications with the rich culture surrounding them and to develop the knowledge and understanding of the 5 core concepts of language, technology, system, audience and re-creation while testing the culture. The implication of this study is as the following. ACARA's media art education curriculum has been developed as an independent educational program and has a special significance within Australian education curriculums. Although ACARA's media art education curriculum is formed as an independent subject, it is suggested within the curriculum to instruct in close connection with other subjects upon execution. Its organization and elaborateness in curriculum composition are very effective in terms of the teacher's teaching-learning design and as well as the evaluation. This seems to show a good model of leading media literacy curriculum. ACARA's media art education curriculum can be a great reference in introducing media literacy to Korean national education curriculums.