Korean | English

pISSN : 1975-7700 / eISSN : 2734-0570

Home > Explore Content > All Issues > Article List

2020, Vol.15, No.3

  • 1.

    Edge Enhanced Neural Network For High Accuracy Image Classification

    Suh Sangmin | 2020, 15(3) | pp.315~321 | number of Cited : 3
    Abstract PDF
    Among the several deep learning research areas, image classification is a fundamental area and has been widely applied to many practical applications. Image classification is to determine which category the given image belongs to. Since the image classification is a typical supervised learning, test images and the corresponding answers, i.e., labels are also given. And, with the given test images and labels, a neural network is trained to minimize a loss function defined by error between the label and the inference result. Therefore, as the loss decreases, the inference accuracy increases. As a result, the accuracy is a criteria of the performance of the neural network in image classification. In this paper, a new method for high accuracy image classification is suggested. Authors thinks that recognizing things mean seeing the shape of the things. With the intuition, in the proposed method, additional edge information is applied to the image and around 3% accuracy improvement is achieved in the experiment. In order to clarify the improvement, compared feature maps in the hidden layers are visualized and analyzed. And, it is also confirmed that the feature map of the proposed method is more clear and sharp than that of the conventional one. Another merit of the proposed method is that this method can easily improve the accuracy of the conventionally existing neural networks through the transfer learning because the proposed method just modifies the first layer of the conventional neural networks.
  • 2.

    A Study on the Application of TensorFlow to Determine the Correctional Distance

    Eig Seub Han | 2020, 15(3) | pp.323~329 | number of Cited : 2
    Abstract PDF
    Environmental pollution is getting serious around the world recently. Economic losses from air pollution and threats from ultra fine dust are becoming social problems. Currently, measurements are made through wood and optical measuring equipment, but there is a problem where measurements and human sense of corrective action do not match. This paper aimed to implement an algorithm of judgment to match the measured value with the human sense of visibility. Using IoT-based cameras in buildings, measured photo information is sent to the server to make corrective distance measurements, and real-time transmitted photos and existing measured photo information are processed in high-speed operation through Tensorflow, requiring high-reliability corrective distance. An algorithm that is supplemented with a SVM nonlinear regression model algorithm for existing corrective distance determination algorithms has been implemented to automate with algorithms similar to those that are directly judged by humans. In this study, a support vector machine (SVM) nonlinear regression model algorithm is used to perform high-speed computation using Tensorflow, and a system implementation model is proposed to improve reliability of the corrective judgment algorithm model.
  • 3.

    The Combat Effectiveness Analysis of Warrior Platform Improvement Using AWAM

    Se-Ho Lee , Hojun Lee , Hee-Won Yang and 1 other persons | 2020, 15(3) | pp.331~346 | number of Cited : 2
    Abstract PDF
    This study presents simulated results using AWAM for the combat effectiveness of the Warrior Platform improvement. The Army is promoting for a three-stage project that will improve the effectiveness in five fields, including the survivability of warrior, in order to upgrade the platform(i.e. gears, equipments, clothing, etc). This study analyzed the improvement effects of the Dot sight, magnifying glass, bulletproof clothing, and bulletproof helmet of the first stage project, focusing on viability and lethality. Advancement of Dot sight and magnifying glass increases firearms hit rate, and improvement of bulletproof clothing and helmet progress the protection of body parts. The firearms hit rate data were obtained through combat experiments using KCTC Miles equipment. In addition to a degree of improvement of body part protection, the manual data were analyzed and entered as the AWAM's basic data. The analysis indicator utilizes the probability of kill in terms of lethality and the probability of survive in terms of the viability as the main indicator, but also additional consideration is given to the loss exchange rate. The enemy and allied platoon scale of experimental group was organized. The eight scenarios were applied to simulate and produce results in order to statistically compare before and after improvement. The analysis showed that the probability of enemy kill in terms of lethality increased by an average of 1.5 times. Multiple regression analyses also confirmed that the survival rate of the allies, contribution of firearms, and the firing rate of the firearms have a crucial impact on the loss exchange rate. This study has a significant in that the results were quantitatively analyzed by applying statistical techniques and by linking the combat experiments with the simulation to verify the effectiveness of the Warrior Platform improvement for the first time in the Army.
  • 4.

    A Study on Adaptive Smart Platform for Intelligent Software in Big Data Environment

    kim, jeongsig , KIM, JIN HONG | 2020, 15(3) | pp.347~355 | number of Cited : 5
    Abstract PDF
    Since smart platform convergence became a main issue of 4th industrial revolution, intelligent software-centric industry has carried out a policy from Internet of Things/Everything, Big Data, Artificial Intelligent, and Deep Learning. Now a day, this highest super technology provide user’s convenience, awareness, adaptation, and reactivity from intelligent software of IT. From their user-oriented service, we could make a great new leap forward to quality of software product. In addition, various convergence system of super national level is being made to stimulate both economy and industry. Nevertheless, it must be considered that the scale of these infrastructures is very large and that the conventional methods of inspecting infrastructures are very fast and time-consuming. These conventional methods are also dangerous for inspection team since the inspectors need to move or even climb on massive infrastructures to inspect places and areas that are difficult to reach. Besides, most conventional inspection methods are visual and the approaches applied are manual. Because of these problems mentioned above, adaptive smart platform and intelligent software have become important issues for users-aspect, industry-side, and Nation-oriented as time goes on. Accordingly, in this research paper, we propose adaptive smart platform that intelligent software have analyze, process, and refinement by big data. This platform is designed based on convergent software framework, such as Hadoop, HDFS and so on architectures utilizes our platform analyze massive data on their field by streamed data processing.
  • 5.

    The Situation of E-Commerce in the United States

    Kim, Kwang-hyun , Hyun-Young Jung | 2020, 15(3) | pp.357~364 | number of Cited : 2
    Abstract PDF
    This paper outlines the US e-commerce market, which has grown rapidly among them, as the size of e-commerce market is growing greatly due to the development of information and communication technology today. The United States has quickly established itself in the e-commerce market with the rapid dissemination of the Internet and electronic devices and the development of technology. In addition, the U.S. e-commerce market has the greatest advantage of having the largest number of online consumers in the world. This is because not only the population in the U.S. but also the influx of consumers who purchase from abroad is high. For these consumers, U.S. e-commerce companies are making efforts to build a more innovative delivery service to create an environment for faster delivery to consumers, and build mobile platforms as more consumers shop on mobile devices. Companies also want to provide consumers with more convenient services through omni-channels that can increase both online and offline accessibility. Amazon, a leading U.S. e-commerce company, is also expanding its reach beyond online to offline markets through Omni Channel, and Wal-Mart is also preparing for greater growth by establishing an e-commerce system to compete with Amazon. While more small and medium-sized enterprises are growing along with leading U.S. e-commerce companies, the U.S. should prepare strategies to cope with the growth of the Chinese e-commerce market as the Chinese e-commerce market has recently shown rapid growth.
  • 6.

    Analysis of The Remaining Amount Variation of A Lithium-ion Battery Using A Neural Network

    Won-Hui Lee , JANG SUNG JIN | 2020, 15(3) | pp.365~372 | number of Cited : 1
    Abstract PDF
    Lithium-ion cells that are mounted on portable information terminals are almost impossible to find a matching cell due to various variables and unique characteristics. The method of calculating the remaining amount in a portable information terminal is an important item in terms of reliability of the terminal. In this paper, in order to measure the remaining amount of a specific lithium-ion cell, a measurement method is proposed that improves precision with a certain reference item for each element. First, the residual data value of the actual measured lithium-ion cell was trained using the error back propagation algorithm of the neural network. Second, computer simulation using Matlab was used as a type of residual quantity measurement method to make nonlinear numerical data relatively linear while reducing the error from the actual measured value for the residual information value. This method showed an unstable start in the initial state, but the result was relatively similar to the original data value as it went through the learning process of the actual measured data. This remaining amount measurement algorithm is an effective method that can be applied to portable information terminals. The analysis of the remaining amount variation of a lithium-ion battery using a neural network will be applicable to all IT devices as well as portable information terminals.
  • 7.

    The Relationship Between SNS Fatigue and University Students’ Behaviors of Academic Procrastination and Learning Flow

    CHOI EUN YOUNG , Shin, Namin | 2020, 15(3) | pp.373~382 | number of Cited : 6
    Abstract PDF
    This study investigated the relationship between Social Network Service (SNS) fatigue and behaviors of academic procrastination and learning flow among university students. Furthermore, the frequency and duration time of SNS use were studied with regrad to in its relations with the two variables. For the purpose of the study, data were gathered from 267 students (average age=21.17, S.D=2.344) enrolled in three universities located in Seoul and Pusan through online survey. The data were analyzed by use of statistical package SPSS 22.0 for correlation and multiple regression analyses. Following are the results of the data analyses. First, the variable of SNS fatigue was found to be significant in affecting students’ behaviors of academic procrastination while its effect was not proved with regard to learning flow. Second, the frequency of SNS media per day had negative effect on students’ learning flow. Third, the duration time per individual SNS use had nothing to do with either academic procrastination or learning flow. These results made it possible to suggest the following. First, students need to be informed or educated about the effect of SNS fatigue for preventing themselves from its negative effect on their management of academic behaviors. Second, the negative effect of SNS media had more to do with its frequency of use than its duration time, thus it is highly required for university students to grow self-regulation especially in the time of test preparation or performing academic tasks. Finally, we suggested future research concerning the mediating effects of the characteristics of research participants including sex or other socio-psychological variables in investigating the relations between SNS fatigue and students’ learning.
  • 8.

    A Preliminary Investigation of Metacognition and Depression

    Moon, Jong-Hoon , Won Young Sik | 2020, 15(3) | pp.383~392 | number of Cited : 1
    Abstract PDF
    The purpose of current preliminary investigation was to examine the relationship between depression and metacognition and the demographic characteristics. In this study, 70 social network service questionnaires(convenience sampling) were administered to the subjects through evaluation of the metacognition and the depression, and 57 responses were analyzed except 13 incomplete responses. The data collection period was from December 29, 2017 to January 9, 2018. The assessment tools used for the measurements were metacognitions questionnaire-30 and Beck Depression Inventory. The independent t-test was used to identify the metacognition and the depression according to the demographic characteristics of the respondents. The Pearson correlation analysis was used to identify correlations among respondents' the age, the metacognition, and the depression. In gender, marital status, and education level, the metacognition and the depression were not significantly different(p>.05). In the education level, however, ≥ graduate school was significantly higher than the university graduation in subcategory of the metacognition (cognitive confidence and cognitive self-consciousness)(p<.05). In the correlation analysis, the metacognition was significantly correlated with age and the depression(p<.05). The results of this preliminary study found the relationship between the metacognition and the depression, and can be used as basis for the development of a metacognitive treatment program for patients with psychological problems.
  • 9.

    Analysis on Impact of Violence Victimization on Discriminatory Behavior by Mediating Consciousness of Human Rights through Structure Equation Modeling

    KIM YOUNGKI | 2020, 15(3) | pp.393~404 | number of Cited : 3
    Abstract PDF
    The purpose of this study is to see level of discriminatory behavior to examine the effect of violence victimization on the discriminatory behavior and mediated effect of human rights consciousness. This study used the data of Korean Children Youth Human Rights Survey by National Youth Policy Institute. The results were as follows. First finding showed us that violence victimization of children and teenager is no lack. And parents has the largest number of perpetrator, followed by teachers, peers. Verbal violence happens more than physical. And they discriminate against peers by individual reasons as age, grades, gender, appearance than background reasons. Second finding showed that more violence victimization from parent and teacher, peer, the higher discriminatory behavior. Third finding showed that human rights consciousness only mediated the relationship between violence victimization from teachers, peers and discriminatory behavior. This study suggests as follows. First, we need to regularly and continuously provide parent-education program that parents are fully aware of dangerousness their verbal and physical violence on development of their child, Second, influence violence victimization from teachers, peers on discriminatory behavior can decrease as should all filled school and classroom with culture of human rights and by sharing desirable values. And education of human rights should consist of student activity centered than lecture centered.
  • 10.

    Effects of Mind Subtraction Meditation-Based Youth Camp on Self Control, Consideration-Communication, and Community Spirit Using a Paired-Difference Test

    MI RA YUN , Yi, In-soo , Na-Yeon Ki and 1 other persons | 2020, 15(3) | pp.405~422 | number of Cited : 1
    Abstract PDF
    The purpose of education is to enable individuals to fully demonstrate own intellectual, moral and emotional strengths in order to lead worthwhile life of living harmoniously within a community of people and nature. South Korea has one of the highest educational fervor in the world; and due to this, students’ academic achievement is top-rated among OECD nations. However, their social interaction, happiness index, regard for others as well as ability to work with others were all rated at bottom-levels as the true value of education had become de-emphasized. This study examined the effects of a Mind Subtraction Meditation youth camp on self control, consideration-communication and community spirit of participants. The camp consisted of a 7-day overnight stay program held at the J Youth Training Center in N-city. Study participants were 327 students comprised of 192 elementary and 135 middle school students who attended the camp. Data were collected via self-reported questionnaires and analyzed using a paired t-test with SPSS 24.0. The results showed that self control, consideration-communication, and community spirit among elementary and middle school students were significantly increased after participating in the camp. This was significant because the result demonstrated symmetrical enhancement effects of meditation-based youth camp on self control for proper self-development, as well as consideration-communication and community spirit which are necessary virtues as members of a society.
  • 11.

    A Comparison of Temporal Variables Using Video Shooting on Normal Swallow and Effortful Swallow in Healthy Men

    Won Young Sik , Moon, Jong-Hoon | 2020, 15(3) | pp.423~430 | number of Cited : 1
    Abstract PDF
    This study aimed to compare the temporal variables during normal swallow and effortful swallow of healthy adult men through smartphone video recording. Ten healthy adult men participated in this study. The participants swallowed 5ml of water in a sitting position, and the video image was shot using a smartphone digital camera during swallowing. All participants performed the normal swallow and the effortful swallow, and The order of normal swallow and the effortful swallow was counterbalanced. The images of all swallowing were analyzed by trained assessors at 30 frames per second. The temporal variables were swallowing onset timing (SOT), laryngeal elevation time (LET), laryngeal elevation stay duration (LESD), and swallowing duration (SD). The collected data were analyzed by using the Paired t test to compare the temporal variables for the two swallowing. In the SOT, the effortful swallow was significantly longer than the normal swallow. The LET was not different between the two swallowing methods. The effortful swallow in the LESD was significantly longer than normal swallow. In the SD, The effortful swallow was significantly longer than the normal swallow. The results of this study suggest that temporal analysis using video images is a convenient method to measure the effortful swallow and the normal swallow.
  • 12.

    Improvement of Input Processes of Article Metadata

    Yun Ji Jang , Kim Sang-Kyun , chul kim | 2020, 15(3) | pp.431~438 | number of Cited : 0
    Abstract PDF
    OASIS(Oriental Medicine Advanced Searching Integrated System) provides the information on research articles of Korean Medicine. This study aims to propose an article construction system that can manage massive metadata of articles efficiently by analyzing its repetitive input procedure. Since the articles are provided in the form of public data that can used by everyone, metadata of the articles should be constructed correctly. In the past, the metadata had been entered in three steps. Thus, it takes a lot of time to input the metadata, and many errors occur during the steps. To solve these problems, we in this paper developed an article construction system that the metadata can be corrected by preventing users’ input mistakes. After a PDF file is uploaded in this system, the publication information of the journal is extracted automatically from the file name of the PDF. Then, other metadata is entered and metadata input of the article is completed. By using the article construction system, absolute task time for constructing the information of article database was reduced and metadata input errors were prevented. In the future, we will demonstrate the performance of our system through empirical research so that other related systems can utilize the method of this system.
  • 13.

    Analysis on Effects Life Goal on Life Satisfaction by Mediating Negative Ego-identity Through Latent Growth Model

    Hur Young Ju | 2020, 15(3) | pp.439~449 | number of Cited : 3
    Abstract PDF
    The purpose of this study was examine a mediating effect of negative ego-identify on the relationship between life goal and life satisfaction. This study used the data of Korean Children Youth Panel Survey(KYPS) by National Youth Policy Institute. The data on 3th, 5th, 7th was used. The results were as follows. First, the higher justice oriented goal of 3rd students of middle school, the lower negative ego-identify. And the higher achieve oriented goal, the higher negative ego-identify. Second, the higher justice oriented goal of 2nd students of high School and 1st students after graduating from high school, greater changing ratio of negative ego-identify. And the higher achieve oriented goal of same times, the faller its changing ratio. Also, faller changing ratio of negative ego-identify is high satisfaction of life. Third, negative ego-identify partially mediate between justice oriented goal and life satisfaction, but it completely mediate between achieve oriented goal and life satisfaction. Based on the results, the following suggestions were. First, we must educate that adolescent have high justice oriented goal than achieve oriented goal. But we have to follow up on the research for promoting balanced development of various goals. Second, we need to provide education of overcoming negative ego-identify and helping think and find answers about the meaning of life for high life satisfaction of adolescent.