• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.672-684
• /
• 2020

Restoring a low resolution and motion blurred light field has become essential due to the growing works on parallax-based image processing. These tasks are known as light-field enhancement process. Unfortunately, only a few state-of-the-art methods are introduced to solve the multiple problems jointly. In this work, we design a framework that jointly solves light field spatial super-resolution and motion deblurring tasks. Particularly, we generate a straight-forward neural network that is trained under low-resolution and 6-degree-of-freedom (6-DOF) motion-blurred light field dataset. Furthermore, we propose the strategy of local region optimization on the adversarial network to boost the performance. We evaluate our method through both quantitative and qualitative measurements and exhibit superior performance compared to the state-of-the-art methods.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.2
• /
• pp.55-60
• /
• 2010

We usually encounter Electro-magnetics phenomenons and only feel some part of that, but it is hard to feel it visually. Moreover understanding physically and quantitatively is not a easy work. These electrostatic field theory, magnetostatic field theory and interchange magnetic field theory combined with electromagnetic field are formulated experimentally and theoretically by James Clerk Maxwell in 1873. Electromagnetic field takes electro-magnetic phenomenons as a expansion of formula originated in Maxwell equations. Since this is based on expansion of formula, it is hard to understand for many students not only middle school and high school students learning it at the first time but also college students studying physics as a elementary class and even majors in electromagnetic field. The program is developed as a visual aid to cope with these problems, and even to deal with complex problem to estimate solution using numerical method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.10
• /
• pp.2279-2284
• /
• 2011

Recently as AR(Augmented Reality) is focus of attention, AR is applied to various fields and is expected its valuable use. In this paper, we suggested the method to combine existing e_Book with augmented reality technology based on mobile equipment. We ascertained that augmented reality contents implemented on PC work well in pITX embedded lines (CPU Intel ATOM Z530) and we implemented augmented reality using marker in e_ Book in pITX embedded lines through these experiments. As the result of it, we could show the contents at the same time which had difficulty to be expressed on e_Book before. Also the existing augmented reality contents could be used as it is. Finally we expected that the user could interact with virtual contents or services directly and intuitively in the real world.

• Journal of Korean society of Dental Hygiene
• /
• v.15 no.1
• /
• pp.137-146
• /
• 2015

Objectives: This study was obtained to identify current education status of the community dental hygiene practice. Methods: It was designed cross section and self-reported on-line questionnaire(Survey monkey). It was performed probability sampling by targeting 82 dental hygiene schools(each one faculty member) in charge of community dental hygiene curriculum and 254 community health centers's community dental hygienists whom was working at oral health section. The response rate was 60% and 53%, respectively. The questionnaire consisted of time, duration, practice group, evaluation method, and practice contents including 63 learning objectives of dental hygiene. Results: Nearly half of these schools conduct such community field work practice in the spring semester of the junior year. This practice was mainly progressed based on average 4 students as one team per each one school for 7-8 hours a day during the period of more than 5 weeks(p<0.05). However, in case of both school and community health center, almost half of feedback after practice was not achieved and there was a difference in needs for practice education between schools and community health center. Conclusions: We should be considered that a sufficient consultation for the practice environment and its contents between schools and community health centers. It was considered that development of a standardized practice manual reflecting such requirement.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.180-191
• /
• 2016

When up-scaling algorithms for visible light images are applied to infrared (IR) images, they rarely work because IR images are usually blurred. In order to solve such a problem, this paper proposes an up-scaling algorithm for IR images. We employ adaptive dynamic range encoding (ADRC) as a simple classifier based on the observation that IR images have weak details. Also, since human visual systems are more sensitive to edges, our algorithm focuses on edges. Then, we add pre-processing in learning phase. As a result, we can improve visibility of IR images without increasing computational cost. Comparing with Anchored neighborhood regression (A+), the proposed algorithm provides better results. In terms of just noticeable blur, the proposed algorithm shows higher values by 0.0201 than the A+, respectively.

• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.75-85
• /
• 2007

One of important factors for improving the learning achievement of students in computer programming education is to provide plenty of opportunities of problem-solving experiences through variety forms of assignments, However, for the most cases, evaluation of programming assignments is performed manually by instructors and automated tools for the accurate evaluation are not equipped at the present time. Under this restricted environment instructors need much work and time to grade assignments so that instructors could not deliver sufficient programming assignments to students, In order to overcome this problem. au automated programming assignment evaluation system is needed that would enable instructors to evaluate assignments easily in an effective and consistent way and also to detect any plagiarism activities among students in program source codes readily, Accordingly, in this paper we design and implement a Web-based programming assignment grading system that allows instructors to evaluate program performance automatically as well as to evaluate program styles and piagiarism easily with appropriate feedback.

• Journal of Korean Society on Water Environment
• /
• v.24 no.1
• /
• pp.91-98
• /
• 2008

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.20 no.1
• /
• pp.15-26
• /
• 2016

Objectives Syndrome differentiation and treatment (辨證論治) was one of the core theories in Korean medicine and syndrome differentiation (辨證) constitutes a branch of disease diagnosis in Korean medicine. Yoon Gil-Young, one of the modern outstanding scholar of basic medical science in Korean medicine, wrote on basic theories of Korean medicine such as physiology, pathology, formula science, etc. Hereby we will analyze and discuss his works to understand his recognition of historical changes in the syndrome differentiation. Methods We conducted researches into the two works of Yoon Gil-Young's, which are "The Clinical Formula Science of Eastern Medicine (東醫臨床方劑學)" and "The theory of Four-Constitution Medicine (四象體質醫學論)". From Yoon's academic standpoint which connects the basic medical science with the clinical medicine, we analyzed his opinion about the system in the Theory of 'Syndrome Differentiation'. Results According to Yoon's research work on the Theory of 'Syndrome Differentiation', the system of syndrome differentiation, which had its deep root in the theory of Yin and Yang (陰陽) & the theory of abbreviation of the five circuit phases (五運) and the six atomspheric influences (六氣) of the "Huangdi's Internal Classic (黃帝內經)". Conclusions Yoon Gil-Young's theory of differentiation of syndromes and treatment is widespread so much that he studied on the learning field of Traditional Korean Mediciine and ingenious as well. He explain on the main principles of differentiation of syndromes based on "Huang Di Nei Jing" and the system of differentiation of syndromes is composed of Traditional Korean Medical Physiology.

• The KIPS Transactions:PartD
• /
• v.19D no.1
• /
• pp.21-28
• /
• 2012

Predication of protein interaction sites for monomer structures can reduce the search space for protein docking and has been regarded as very significant for predicting unknown functions of proteins from their interacting proteins whose functions are known. In the other hand, the prediction of interaction sites has been limited in crystallizing weakly interacting complexes which are transient and do not form the complexes stable enough for obtaining experimental structures by crystallization or even NMR for the most important protein-protein interactions. This work reports the calculation of 3D surface patches of complex structures and their properties and a machine learning approach to build a predictive model for the 3D surface patches in interaction and non-interaction sites using support vector machine. To overcome classification problems for class imbalanced data, we employed an under-sampling technique. 9 properties of the patches were calculated from amino acid compositions and secondary structure elements. With 10 fold cross validation, the predictive model built from SVM achieved an accuracy of 92.7% for classification of 3D patches in interaction and non-interaction sites from 147 complexes.

• Convergence Security Journal
• /
• v.18 no.5_1
• /
• pp.59-66
• /
• 2018

The performance of a network intrusion detection system using the machine learning method depends heavily on the composition and the size of the feature set. The detection accuracy, such as the detection rate or the false positive rate, of the system relies on the feature composition. And the time it takes to train and detect depends on the size of the feature set. Therefore, in order to enable the system to detect intrusions in real-time, the feature set to beused should have a small size as well as an appropriate composition. In this paper, we show that the size of the feature set can be further reduced without decreasing the detection rate through using Pearson correlation coefficient between features along with the multi-objective genetic algorithm which was used to shorten the size of the feature set in previous work. For the evaluation of the proposed method, the experiments to classify 10 kinds of attacks and benign traffic are performed against NSL_KDD data set.