• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.378-390
• /
• 2022

With the recent development of deep composite multiplication neural network learning, deep learning techniques applied to single-image super-resolution have shown good results, and the strong expression ability of deep networks has enabled complex nonlinear mapping between low-resolution and high-resolution images. However, there are limitations in applying it to real-time or low-power devices with increasing parameters and computational amounts due to excessive use of composite multiplication neural networks. This paper uses blocks that extract hierarchical characteristics little by little using information distillation and suggests the Recursive Distillation Super Resolution Network (RDSRN), a lightweight network that improves performance by making more accurate high frequency components through high frequency residual purification blocks. It was confirmed that the proposed network restores images of similar quality compared to RDN, restores images 3.5 times faster with about 32 times fewer parameters and about 10 times less computation, and produces 0.16 dB better performance with about 2.2 times less parameters and 1.8 times faster processing time than the existing lightweight network CARN.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.185-191
• /
• 2022

This paper proposed a division algorithm of performance complexity $O{\frac{n(n+1)}{2}}$ for a change-making problem(CMP) in which polynomial time algorithms are not known as NP-hard problem. CMP seeks to minimize the sum of the x_j number of coins exchanged when a given amount of money C is exchanged for c_j,j=1,2,⋯,n coins. Known polynomial algorithms for CMPs are greedy algorithms(GA), divide-and-conquer (DC), and dynamic programming(DP). The optimal solution can be obtained by DP of O(nC), and in general, when given C>2ⁿ, the performance complexity tends to increase exponentially, so it cannot be called a polynomial algorithm. This paper proposes a simple algorithm that calculates quotient by dividing upper triangular matrices and main diagonal for k×n matrices in which only j columns are placed in descending order of c_j of n for c_j ≤ C and i rows are placed k excluding all the dividers in c_j. The application of the proposed algorithm to 39 benchmarking experimental data of various types showed that the optimal solution could be obtained quickly and accurately with only a calculator.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.44-55
• /
• 2022

In order to automatically provide information on fruits in agricultural related broadcasting contents, instance image segmentation of target fruits is required. In addition, the information on the 3D pose of the corresponding fruit may be meaningfully used. This paper represents research that provides information about tomatoes in video content. A large amount of data is required to learn the instance segmentation, but it is difficult to obtain sufficient training data. Therefore, the training data is generated through a data augmentation technique based on a small amount of real images. Compared to the result using only the real images, it is shown that the detection performance is improved as a result of learning through the synthesized image created by separating the foreground and background. As a result of learning augmented images using images created using conventional image pre-processing techniques, it was shown that higher performance was obtained than synthetic images in which foreground and background were separated. To estimate the pose from the result of object detection, a point cloud was obtained using an RGB-D camera. Then, cylinder fitting based on least square minimization is performed, and the tomato pose is estimated through the axial direction of the cylinder. We show that the results of detection, instance image segmentation, and cylinder fitting of a target object effectively through various experiments.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.2
• /
• pp.427-435
• /
• 2017

Most of the domestic city buses are equipped with the pressure vessels subjected to internal pressure applied by compressed natural gas. Pressure vessels subjected to internal pressure are used in various forms and purposes. Fuel is explosive and has flammable high pressure. The damage of the pressure vessel causes many property damage and loss of life. Safe design for pressure vessel is always necessary. Due to these reasons, many studies using finite element analysis have been conducted. In this paper, the stresses of cylindrical vessel and spherical dome were analyzed using ANSYS, a finite element analysis software. In order to verify the validity of the analysis, a model with a perfectly spherical shape of the dome was designed and observed. Based on the ASME standard in used, stress distribution was also analyzed for models designed with compressed natural gas(CNG). The FEM analysis software agreed with the theory when the dome shape was perfectly spherical. The model designed based on the ASME specification theory, stress concentration occurred in the knuckle part.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.10
• /
• pp.449-456
• /
• 2016

In this study we recomposed the life story of Min Tatyana who is a Koryo-saram, or in other words, an ethnic Korean residing Kazakhstan. The life story of an overseas Korean, or Koryo-saram to be exact, includes in itself their multi-level identity which consists of the period of the immigration of Koryo-sarams, the special incident of deportation, as well as life as people of the Soviet Union and Kazakhstan, and life as a Korean race. In this study, we were confirmed the texture of the Korean race thought ordinary korean Min Tatyana life who living in Kazakhstan. The life story of Min Tatyana was reconstituted into two stories as "growing up in a multicultural society as Koryo-Saram" and "to live a life as the descendants of independence activist". She was born in historically region Kyzylorda, where living Korean groups and now she is living in Almaty, where living the many koreans ethnic groups of Kazakhstan. Also, her parents were respected to the local residents and her grandfather of husband was famous independent activist. These aspects have helped keep her Korean ethnic identity. The life story of Min Tatyana is personal story and qualitative text, which shows social, cultural background of korean ethnic who living in Kazakhstan. This study is expected to help to confirm the Koryo-Saram characteristics and aspect of their multilayer life.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.199-206
• /
• 2017

The experience sampling method (ESM) is an innovative research method to study the immediate real emotional experience experienced in real life through the immediate reaction of research participants. ESM, which has received significant attention in recent, is considered as the research method particularly for child care teachers' emotions and happiness. This method has been shown to be able to overcome the limitations in current research methods, based on teachers' recall or surveys, in assessing child care teachers' emotional states or stress levels. Despite the expectation that the need for further research on the increased stress and negative emotional experiences of child care teachers and its appropriateness as the alternative research method to study child care teachers' immediate emotional experience, ESM has deficiencies in that research participants need to have their pencil-and-paper survey packages on hand whenever their electronic beepers randomly beep. Furthermore, ESM demands much more researcher energy and efforts to handle the voluminous data collected from each participant in effectively creating a database. In this paper, in order to apply ESM successfully to the study of child care teachers' emotional experience, we aim to develop a software program that uses mobile communication technology. Given that traditional types of data collection methods in social science research can prove too burdensome to encourage participation in surveys in the first place or ensure the return of completed surveys, the present study adopts a convergent research approach to develop a software program that is able to obtain ESM participants' answers immediately on their personal smart phones. This study deals with system construction and prototyping for software development as a basic research and evaluates the research results through indepth interview with experts.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.6
• /
• pp.407-416
• /
• 2018

The study aims to explore the possible link between lifelong education and local education·training projects to enhance vocational skills. To this end, we first looked at vocational training in lifelong educational institutions. We looked at the areas of lifelong education presented by the Lifelong Education Act and the status of job improvement in them, as well as the actual number of learners across the country. Next, we looked at local education training projects. In this case, We investigated the significance and type of education·training projects, and identified the number of programs and the number of learners. Looking at them, we looked for five possibilities the possible link of between vocational abilities and educational·training projects. The five were to strengthen employment related lifelong learning of the economically inactive population, to strengthen lifelong education related to the underprivileged people, to enhance vocational skills for lifelong education centered on the employed, to utilize lifelong education institutions and universities in the region, and to strengthen the role of local governments to guide local job demands and suppliers.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.2
• /
• pp.1-11
• /
• 2018

Recently ICT, new technologies such as IoT, Cloud, and Artificial Intelligence are changing the information society explosively. But personal information leakage incidents of consignee's company are increasing more and more because of the expansion of consignment business and the latest threats such as Ransomware and APT. Therefore, in order to strengthen the security of consignee's company, this study derived the checklists through the analysis of the status such as the feature of consignment and the security standard management system and precedent research. It also analyzed laws related to consignment. Finally we found out the relative importance of checklists after it was applied to proposed AHP(Analytic Hierarchy Process) Model. Relative importance was ranked as establishment of an internal administration plan, privacy cryptography, life cycle, access authority management and so on. The purpose of this study is to reduce the risk of leakage of customer information and improve the level of personal information protection management of the consignee by deriving the check items required in handling personal information of consignee and demonstrating the model. If the inspection activities are performed considering the relative importance of the checklist items, the effectiveness of the input time and cost will be enhanced.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.9
• /
• pp.429-442
• /
• 2017

This study was performed to investigate and analyze users' needs for m-health based prevention and intervention programs that are intended to improve the awareness of metabolic syndrome and promote health behaviors of college students. A questionnaire survey was conducted to 200 college students of 2 university in D city. Data were analyzed using descriptive statistics, t-tests, chi-square test with the SPSS Version 20.0. The result showed that users wanted customization of prescriptions and accurate measurement of health applications, and provided a positive feedback on information exchange between those who manage their health. The most preferred content was proper exercise methods, and the preferred gamification factors were goal-setting, compensation, and competition. The optimal price for wearable devices was between 10,000 to 50,000 won, and calorie consumption function was also preferred. Although users with experiences of wearable devices and health apps had a higher knowledge score pertaining to metabolic syndrome, there was no significant difference in the overall score. Concerning the health behaviors associated with lifestyles, individuals without the experiences of wearable devices and health apps showed a remarkably lower score. The research has a significance that it investigated and analyzed the contents needed for the development of effective moblie health based prevention and intervention programs targeting the population in their early adulthood. Therefore, based on the findings, we propose a rich and concrete follow-up study on the needs and characteristics of different user types by collecting a population with experiences of wearable devices, and a development of differentiated mobile health based prevention and intervention programs.