Korean | English

pISSN : 1598-849X / eISSN : 2383-9945

2020 KCI Impact Factor : 0.4
Home > Explore Content > All Issues > Article List

2020, Vol.25, No.5

  • 1.

    Improved STGAN for Facial Attribute Editing by Utilizing Mask Information

    Hyeon Seok Yang | HAN,BOKGYU | Young Shik Moon | 2020, 25(5) | pp.1~9 | number of Cited : 0
    Abstract PDF
    In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.
  • 2.

    A Study on the Outlet Blockage Determination Technology of Conveyor System using Deep Learning

    Jeong Eui-han | Suh Young Joo | Dong-Ju Kim | 2020, 25(5) | pp.11~18 | number of Cited : 0
    Abstract PDF
    This study proposes a technique for the determination of outlet blockage using deep learning in a conveyor system. The proposed method aims to apply the best model to the actual process, where we train various CNN models for the determination of outlet blockage using images collected by CCTV in an industrial scene. We used the well-known CNN model such as VGGNet, ResNet, DenseNet and NASNet, and used 18,000 images collected by CCTV for model training and performance evaluation. As a experiment result with various models, VGGNet showed the best performance with 99.03% accuracy and 29.05ms processing time, and we confirmed that VGGNet is suitable for the determination of outlet blockage.
  • 3.

    Generating Augmented Lifting Player using Pose Tracking

    Choi Jong In | Jong-Hyun Kim | 2020, 25(5) | pp.19~26 | number of Cited : 0
    Abstract PDF
    This paper proposes a framework for creating acrobatic scenes such as soccer ball lifting using various users' videos. The proposed method can generate a desired result within a few seconds using a general video of user recorded with a mobile phone. The framework of this paper is largely divided into three parts. The first is to analyze the posture by receiving the user's video. To do this, the user can calculate the pose of the user by analyzing the video using a deep learning technique, and track the movement of a selected body part. The second is to analyze the movement trajectory of the selected body part and calculate the location and time of hitting the object. Finally, the trajectory of the object is generated using the analyzed hitting information. Then, a natural object lifting scenes synchronized with the input user's video can be generated. Physical-based optimization was used to generate a realistic moving object. Using the method of this paper, we can produce various augmented reality applications.
  • 4.

    Research of Semantic Considered Tree Mining Method for an Intelligent Knowledge-Services Platform

    Juryon Paik | 2020, 25(5) | pp.27~36 | number of Cited : 0
    Abstract PDF
    In this paper, we propose a method to derive valuable but hidden infromation from the data which is the core foundation in the 4th Industrial Revolution to pursue knowledge-based service fusion. The hyper-connected societies characterized by IoT inevitably produce big data, and with the data in order to derive optimal services for trouble situations it is first processed by discovering valuable information. A data-centric IoT platform is a platform to collect, store, manage, and integrate the data from variable devices, which is actually a type of middleware platforms. Its purpose is to provide suitable solutions for challenged problems after processing and analyzing the data, that depends on efficient and accurate algorithms performing the work of data analysis. To this end, we propose specially designed structures to store IoT data without losing the semantics and provide algorithms to discover the useful information with several definitions and proofs to show the soundness.
  • 5.

    MSaGAN: Improved SaGAN using Guide Mask and Multitask Learning Approach for Facial Attribute Editing

    Hyeon Seok Yang | HAN,BOKGYU | Young Shik Moon | 2020, 25(5) | pp.37~46 | number of Cited : 0
    Abstract PDF
    Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.
  • 6.

    Stock prediction using combination of BERT sentiment Analysis and Macro economy index

    Jang Euna | HoeRyeon Choi | LEE, Hong Chul | 2020, 25(5) | pp.47~56 | number of Cited : 0
    Abstract PDF
    The stock index is used not only as an economic indicator for a country, but also as an indicator for investment judgment, which is why research into predicting the stock index is ongoing. The task of predicting the stock price index involves technical, basic, and psychological factors, and it is also necessary to consider complex factors for prediction accuracy. Therefore, it is necessary to study the model for predicting the stock price index by selecting and reflecting technical and auxiliary factors that affect the fluctuation of the stock price according to the stock price. Most of the existing studies related to this are forecasting studies that use news information or macroeconomic indicators that create market fluctuations, or reflect only a few combinations of indicators. In this paper, this we propose to present an effective combination of the news information sentiment analysis and various macroeconomic indicators in order to predict the US Dow Jones Index. After Crawling more than 93,000 business news from the New York Times for two years, the sentiment results analyzed using the latest natural language processing techniques BERT and NLTK, along with five macroeconomic indicators, gold prices, oil prices, and five foreign exchange rates affecting the US economy Combination was applied to the prediction algorithm LSTM, which is known to be the most suitable for combining numeric and text information. As a result of experimenting with various combinations, the combination of DJI, NLTK, BERT, OIL, GOLD, and EURUSD in the DJI index prediction yielded the smallest MSE value.
  • 7.

    Implementation of Digital Twin based Building Control System using Wireless Sensor Box

    Shin Sang Hoon | Park Myeong Chul | 2020, 25(5) | pp.57~64 | number of Cited : 0
    Abstract PDF
    In this paper, based on the building's 3D modeling, a digital twin-based building control system using the collection information of wireless sensor box is proposed. The proposed system applies wireless sensors, making sensor modules more expandable and usable, and more intuitive building control possible through three-dimensional modeling. In addition, effective control and visual representation are possible through BIM data. Sensor boxes have been designed for general purpose so that a variety of sensor modules can be added and have been implemented for actual university buildings to demonstrate high availability. The results of this paper could be used to implement a digital twin control platform in the future.
  • 8.

    Performance Analysis of D2D Power Control To Compensate Channel Estimation Error

    Oh Chang Yoon | 2020, 25(5) | pp.65~72 | number of Cited : 0
    Abstract PDF
    To improve the performance of D2D power control algorithm proposed in the previous work, three modified D2D power control algorithms are proposed to compensate the channel estimation error. Then, we evaluate the performance of three modified D2D power control algorithms in the channel estimation error environment. In real channel environment, the channel estimation is not perfect. To that end, the impact of imperfect channel estimation on the D2D power control algorithm, which was developed with the assumption of perfect channel estimation, has been analyzed in the previous work. Three modified D2D power control algorithms are based on 1) Retransmission, 2) SIR Margin, and 3) Retransmission and SIR Margin. Simulation results show that the Retransmission and SIR Margin approach shows best performance in the sense of the transmit power consumption and the latency.
  • 9.

    Evaluation of Low-cost MEMS Acceleration Sensors to Detect Earthquakes

    Jangsoo Lee | Kwon, Youngwoo | 2020, 25(5) | pp.73~79 | number of Cited : 0
    Abstract PDF
    As the number of earthquakes gradually increases on the Korean Peninsula, much research has been actively conducted to detect earthquakes quickly and accurately. Because traditional seismic stations are expensive to install and operate, recent research is currently being conducted to detect earthquakes using low-cost MEMS sensors. In this article, we evaluate how a low-cost MEMS acceleration sensor installed in a smartphone can be used to detect earthquakes. To this end, we installed about 280 smartphones at various locations in Korea to collect acceleration data and then assessed the installed sensors’ noise floor through PSD calculation. The noise floor computed from PSD determines the magnitude of the earthquake that the installed MEMS acceleration sensors can detect. For the last few months of real operation, we collected acceleration data from 200 smartphones among 280 installed smartphones and then computed their PSDs. Based on our experiments, the MEMS acceleration sensor installed in the smartphone is capable of observing and detecting earthquakes with a magnitude 3.5 or more occurring within 10km from an epic center. During the last several months of operation, the smartphone acceleration sensor recorded an earthquake of magnitude 3.5 in Miryang on December 30, 2019, and it was confirmed as an earthquake using STA/LTA which is a simple earthquake detection algorithm. The earthquake detection system using MEMS acceleration sensors is expected to be able to detect increasing earthquakes more quickly and accurately.
  • 10.

    A Study on the Setting of Breast Measurement Points on 3D Scan Data

    Boohyun Sohn | Hyunsook Han | 2020, 25(5) | pp.81~90 | number of Cited : 1
    Abstract PDF
    In this paper, we propose setting measurement point in the 3D scan data based on the manual measurement data. The optimal 3D body scan postures and measurement points for automatic measurement of breast were set up. The outer breast point may be different depending on the body shape or standing posture as it is on the line connected from the bisecting point of the lateral waist thickness to front armpit point. Therefore, it is necessary to consider the breast-related outer point proposed in this study. And many researches need to reduce the differences between MAM and 3D dimension items associated with the upper breast point. When measuring depth, the difference by pressing in MAM should be taken into account. And the differences in flexion depending on breast type can make a difference in the 3D measurement. So the measurement method in 3D scan should be further studied depending on the types of breast and verified by multiple subjects.
  • 11.

    Lightweight and Migration Optimization Algorithms for Reliability Assurance of Migration of the Mobile Agent

    Yonsik Lee | 2020, 25(5) | pp.91~98 | number of Cited : 1
    Abstract PDF
    The mobile agent, which handles a given task while migrating between the sensor nodes, moves including the execution commands and task processing results. This increases the size of the mobile agent, causing the network to load, leading to the migration time delay and the loss of migration reliability. This paper presents the method of lightening the mobile agent using distributed object technology and the algorithm for exploring and providing the optimal migration path that is actively performed in the event of network traffic, and it proposes a method to ensure the reliability of the mobile agent migration by applying them. In addition, through the comparative analysis experiments based on agent size and network traffic for the migration time of mobile agent equipped with active rules in sensor network-based mobile agent middleware environment, applying the proposed methods proves to ensure the autonomy and migration reliability of the mobile agent.
  • 12.

    Fuzzy Clustering with Genre Preference for Collaborative Filtering

    Soojung Lee | 2020, 25(5) | pp.99~106 | number of Cited : 0
    Abstract PDF
    The scalability problem inherent in collaborative filtering-based recommender systems has been an issue in related studies during past decades. Clustering is a well-known technique for handling this problem, but has not been actively studied due to its low performance. This paper adopts a clustering method to overcome the scalability problem, inherent drawback of collaborative filtering systems. Furthermore, in order to handle performance degradation caused by applying clustering into collaborative filtering, we take two strategies into account. First, we use fuzzy clustering and secondly, we propose and apply a similarity estimation method based on user preference for movie genres. The proposed method of this study is evaluated through experiments and compared with several previous relevant methods in terms of major performance metrics. Experimental results show that the proposed demonstrated superior performance in prediction and rank accuracies and comparable performance to the best method in our experiments in recommendation accuracy.
  • 13.

    Comparison of Middle Aged Men’s Pants Pattern using 3D Simulation

    Cha Su Joung | 2020, 25(5) | pp.107~116 | number of Cited : 0
    Abstract PDF
    The purpose of this study was to compare the pattern of two men's pants for education and two for industry, and to analyze the patterning method that is most suitable for the body shape of middle-aged men. As a result of appearance evaluation for 3D simulation, J pattern was evaluated as the best in most items, and H pattern was analyzed to be the most inappropriate. As a result of measuring the airgap, all four patterns of the waist circumference were evaluated to have very small airgap, and the J pattern had the smallest airgap for the pants. J pattern was analyzed as the most suitable pattern for middle-aged men's body shape by synthesizing the appearance evaluation of virtual wear, color distribution, sectional view, airgap, etc. However, in the case of J pattern, it was analyzed that the pants length needs to be modified. Since this study compared and analyzed only two patterns for education and two for industry, it is thought that the development of pants for middle-aged men should be developed through actual wearing experiments with J patterns.
  • 14.

    Comparison of Middle Aged Men’s Bodice Prototype using 3D Simulation

    Cha Su Joung | 2020, 25(5) | pp.117~126 | number of Cited : 1
    Abstract PDF
    In this study, a 3D simulation program was used to produce a bodice prototype of a middle-aged male in their 40s and 50s and then analyze the appearance evaluation and airgap, sectional view, color distribution through virtual wearing to compare and analyze the differences between patterns. Through this, it was intended to provide basic data necessary for pattern development to companies that manufacture and produce clothing for middle-aged men. As a result of analyzing, J pattern was analyzed as the most suitable body shape pattern for middle-aged men. E pattern was too tight and L pattern and N pattern had too much spaces. However, J patternt was analyzed that correction was necessary in setting center back and center front length. The aging phenomenon in which the back is slightly bent forward and shoulders are also inclined is expected to appear, so it is necessary to adjust the front-to-back length, shoulder angle, and shoulder length. It is considered that after developing the research pattern by modifying J pattern, it is necessary to develop a body shape prototype for middle-aged men through actual clothing experiments on middle-aged men.
  • 15.

    IoT-enabled Solutions for Tour Photography Services

    Isu Jeong | Seungwoo Baek | Eunsol An and 3other persons | 2020, 25(5) | pp.127~135 | number of Cited : 0
    Abstract PDF
    In this paper, we propose an IoT-enabled solution for tour photography services with small-size investment and resources in the travel and tourism industries, being able to impact on economic, social, and cultural values. An IoT-enabled camera is developed based on an open hardware and software platform complying with oneM2M, which can make traditional embedded systems oneM2M-compliant devices due to a middleware solution called TAS (thing adaptation software). IoT cameras deployed around photo zones in a tour site could be remotely controlled via an IoT gateway with a Web-based application on a smartphone. Users would perform a pan and tilt camera control if they want and then take and download a perfect photo picture (even though they are away from the tour site). We expect that the proposed solution will promote the deployment IoT-enabled technologies in tour and travel industries which are important parts of the tertiary sector.
  • 16.

    A Study on Breast Type Classification & Discrimination Using Manual Measurement- Focusing on Korean Women in Their 20s –

    Boohyun Sohn | 2020, 25(5) | pp.137~146 | number of Cited : 0
    Abstract PDF
    The manual measurements of 182 unmarried women subjects in their 20s was classified 4-breast types. For the breast type classification, 4 factors were identified, such as overall breast factor, upper breast internal shape factor, breast volume factor, and lower breast external shape factor. The breast shapes were 'breast with well-grown upper part', 'flat breast', 'breast with well-grown lower part', and 'protruded breast'. The breast types can be differentiated in 10 items of actual anthropometric dimension the length between frontal neck point and nipple point, length between lateral neck point and nipple point, length between the breast inner points, nipple to nipple breadth, diameter below the breast, inner depth of breast, outer length of breast, length below the breast, length between breast outer point and upper breast point, and contour line length below the breast.
  • 17.

    The Difference in Bone metabolism markers and Adipocytokine according to the applying Modern Dance with Osteopenia elderly women

    Chan-Yang Kim | Lee JinWook | 2020, 25(5) | pp.147~158 | number of Cited : 1
    Abstract PDF
    The purpose of this study is to propose an effective exercise for the prevention of osteoporosis by analyzing changes in bone metabolism markers and adipocytokines according to the application of modern dance. The objects were selected between t-score -1.0 to -2.5 and subjects were random assigned to the modern dance group(n=10) and control group(n=10). Modern dance was held three times a week for 60min, for 12weeks. For data analysis, two-way repeated measures ANOVA was analyzed using SPSS. As a result of the study, both osteocalcin(p<.01) and T-score(p<.05) were significantly increased in the modern dance group. Adiponectin(p<.05) was increased significantly and Both TNF-α (p<.05) and IL-6(p<.05) were significantly decreased in the modern dance group. As a result, modern dance is considered to be an effective strategy to prevent osteoporosis, and it is expected to have a positive effect on metabolism and function improvement in elderly women with osteopenia.
  • 18.

    Nurses awareness of paramedics and their opinions on a paramedic’s proper duties in emergency medical centers

    Yong-Seok KIM | Hyo-Young KANG | Jin-Woo KIM | 2020, 25(5) | pp.159~168 | number of Cited : 0
    Abstract PDF
    This study was designed to ask experienced nurses at local and regional emergency medical centers for their awareness of paramedics and for their opinions on a paramedic’s proper duties in emergency medical centers. The questionnaire consisted of 61 questions in total, including general questions, questions about awareness of paramedics, and questions about the duties of paramedics in emergency medical centers. For data analysis, SPSS 21.0 was applied to conduct frequency and correlation analyses. Regarding the duties of paramedics in emergency medical centers, there were positive answers in 33 questions of the questionnaire. The need for paramedics who work for emergency medical centers and the importance of their duties in emergency medical centers were high in the questionnaire. In addition, there were positive answers to the questions about the need for the professionalism of paramedics and the nees for increasing the number of paramedics in emergency medical centers. There was no difference between the groups.
  • 19.

    Awareness of Advance Directives in Gangwon-do Province’s adults

    Hong, Jeongju | Mi-Ok Lee | 2020, 25(5) | pp.169~178 | number of Cited : 0
    Abstract PDF
    This study was attempted to know the awareness of Advance Directives of adults in Gandwon-do province. Data was surveyed from 60 adults in Gangwon-do province by 42 item questionnaire for the awareness of Advance Directives. Subcategories of Advanced Directives questionnaire were knowledge, preference, experience for life-sustaining treatment and Advance Directives. The data was analyzed with the frequency and percentage using SPSS 24.0. 45% of Participants replied they knew the ‘life-sustaining treatment’ exactly. They preferred CPR 78.3%, mechanical ventilation 63.3% and blood transfusion 51.7% for their future special life-sustaining treatments. They did not preferred hemodialysis 8.3%, artificial respiration 6.7%, intensive care unit 6.7%, 8.3 percent of participants said that they well aware of Advance Directives. 86.6% of them hoped to write their Advance Directives. Despite such low awareness of the Advance Directives, the intention to write Advance Directives was high. Based on these results, it was found that the level of awareness of Advance Directives was very important for the intention to prepare Advance Directives. Therefore, regional programs and education on Advance Directives and periodic survey study for awareness of Advance Directives should be continued.
  • 20.

    A Study of Development Antibacterial Cosmetic Case using UV Wavelength

    Seung Hoon Yum | Jung In Geun | Jae Young Jeong and 1other persons | 2020, 25(5) | pp.179~186 | number of Cited : 0
    Abstract PDF
    In this study, we propose an antibacterial cosmetic case using UV wavelengths. UVC have excellent antibacterial strength in terms of economics and convenience. The purpose of experiments was to prove it and to select a suitable permeability material. In experiments, UVA, UVC machanics and the competitor product were used to measure and compare the antibacterial strength of antibacterial cosmetic case using UV wavelength. S. aureus, a gram-positive strain, was used subject to the experiment, and the antibacterial strength measured and compared the number of colonies using the plate count technique. As a result, both UVA and UVC showed antibacterial activity, and UVC showed the most powerful antibacterial activity. In Conclusion, the Quartz glass was the most suitable of the permeable materials, but the more thick the examined quartz material became the less antibacterial strength.
  • 21.

    Self-Supervised Document Representation Method

    Yun Yeo Il | Namgyu Kim | 2020, 25(5) | pp.187~197 | number of Cited : 0
    Abstract PDF
    Recently, various methods of text embedding using deep learning algorithms have been proposed. Especially, the way of using pre-trained language model which uses tremendous amount of text data in training is mainly applied for embedding new text data. However, traditional pre-trained language model has some limitations that it is hard to understand unique context of new text data when the text has too many tokens. In this paper, we propose self-supervised learning-based fine tuning method for pre-trained language model to infer vectors of long-text. Also, we applied our method to news articles and classified them into categories and compared classification accuracy with traditional models. As a result, it was confirmed that the vector generated by the proposed model more accurately expresses the inherent characteristics of the document than the vectors generated by the traditional models.
  • 22.

    The Structural Relationship between Parental Career and Care Support for Multicultural Youth and Teacher Relations, Career Preparation and Career Determination

    Lee Hyoung Ha | 2020, 25(5) | pp.199~208 | number of Cited : 1
    Abstract PDF
    The purpose of this study is to analyze the influence of career support and teacher relations of parents in order to determine the career determination of multicultural youths, and to confirm the influence of career preparation between parental career and care support and teacher relations. To this end, data from 2017 (the 7th year) was used among the data from the Multicultural Youth Panel Survey (MAPS). According to the analysis results, first, career support, teacher relations, and career preparation of multicultural youth parents have a positive impact on career determination. Second, the importance of the relative influence of career preparation, which is an internal context factor, was also confirmed in the process of determining the career path of multicultural youths. Third, it was analyzed that the higher the career and childcare support of multicultural youth parents, the more positive the teacher relationship, the higher the career determination. Career preparation was confirmed to play a role in mediating career support and teacher relations among multicultural youth parents in determining career paths. Based on the results of this analysis, practical alternatives were proposed to enhance the career determination of multicultural youths.
  • 23.

    Research on solution for protecting victim privacy of crime deposit with depository

    park | Sang-Ouk Noe | 2020, 25(5) | pp.209~216 | number of Cited : 0
    Abstract PDF
    As depository system for negotiation or reimbursement to the victim in criminal case is reflected to consideration for diminishing punishment and hence, it is very important in the process. According to the current law, one needs to fill out victim’s personal information such as name, address, and ID number for processing depository. However, if the victim is sexual violence victim, all the personal information is covered up becoming anonymous. Therefore, it becomes difficult for the accused person to get necessary information. Such covering up action is to prevent further second damage that may be caused such as threatening for the negotiation whereas victim has no willingness to forgive the accused. However, even if the accused person regrets his/her crime and make reimbursement to the victim, as they have no personal information on the victim it becomes impossible for them to make the depository. If we apply ESCROW system here it will allow victims to avoid any direct contact with the accused person as well as preventing any privacy disclosure. Also, for the accuse person, they can show how much they regret by making depository within their capability.
  • 24.

    A Study on Relationship of TOE, Blockchain Technology, and Logistics Performance in Korean Logistics’ Firms

    Seong Ho Kim | 2020, 25(5) | pp.217~227 | number of Cited : 0
    Abstract PDF
    In this paper, I propose that what factors affect logistics companies' adoption of blockchain technology and to analyze the effects of blockchain technology on logistics performance. The variables influencing the adoption of blockchain technology were presented based on the TOE frame. Expected profit, organizational readiness, technology compatibility, and competitive pressure were suggested as factors to adopt blockchain technology. Also, as a blockchain technology, smart contracts and information transparency were presented. Logistics performance suggested agility and alignment. A survey was conducted with Korean logistics companies. Looking at the results of analyzing the collected data, it was found that expected profit and technology compatibility have a positive effect on this blockchain technology (smart contract, information transparency). Organizational readiness was found to have a positive effect on information transparency. Blockchain technology was found to have a positive effect on logistics performance.
  • 25.

    Computational Thinking of Middle School Students in Korea

    Seong-Won Kim | Lee Youngjun | 2020, 25(5) | pp.229~241 | number of Cited : 1
    Abstract PDF
    In this study, we developed a test tool to measure the computational thinking ability of middle school students and investigated their computational thinking power using the tool. The test tool used exploratory factor analysis to examine the computational thinking scales of Korkmaz et al. (2017) and derive suitable factors and questions for middle school students in Korea. The developed test tool was applied to 492 middle school students to analyze differences in computational thinking ability according to gender, grade, programming experience, type of programming language, and interest. According to the study, male Korean middle school students had higher computing power than females. In addition, students who had programming experience or used text-based rather than block-based programming languages demonstrated higher computational thinking. There was no significant difference in the computational thinking of middle school students according to grade, and the level of interest in artificial intelligence only had a slight influence on computational thinking.