A Comparative Study on the Effect of Eccentric Viewing Training Using PC and VR Contents

Title : A Comparative Study on the Effect of Eccentric Viewing Training Using PC and VR Contents
Journal : International Journal on Advanced Science, Engineering and Information Technology
Authors : Dokyeong Lee, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : https://doi.org/10.18517/ijaseit.11.2.12832

Abstract
The purpose of this study is to develop PC Eccentric Viewing Training (EVT) and VR EVT Content, to conduct experiments to verify the validity of contents first through non-disabled people, and to compare and analyze VR and PC contents. Both PC and VR contents were produced with UNITY. This content model assumes that reducing inaccurate saccades by eliminating eye movement helps improve reading accuracy. In addition, the two contents are implemented in the same way as VR and PC versions. The content consists of two steps, both PC and VR. The purpose of the content is to improve reading accuracy by improving the fixation stability of Preferred Retinal Locus (PRL) and reducing inaccurate Saccades. The experiment consisted of 12 persons (within maximum visual acuity less than 0.3), and they were assigned to the PC Content group and VR Content group. The experiment was conducted a total of 5 times, except for two weeks, which is the time to adapt PRL. The experimental results showed that the reading accuracy of the VR content group was higher. In addition, When comparing VR contents with PC contents, the group that conducted the training through PC contents showed a decrease in concentration as it progressed to 1-3 steps, and the score distribution also fell overall. In conclusion, the study compared VR and PC contents, and the effectiveness of contents was verified through experiments.

Acknowledgments
This research was financially supported by the “ICT Convergence Smart Rehabilitation Industrial Education Program” through the Ministry of Trade, Industry & Energy (MOTIE). The authors are grateful to Korea Institute for Advancement of Technology (KIAT) and the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2015-0-00403) supervised by the IITP (Institute for Information & communications Technology Promotion).

Design of Middleware to Support Auto-scaling in Docker-Based Multi Host Environment

Title : Design of Middleware to Support Auto-scaling in Docker-Based Multi Host Environment
Journal : Lecture Notes in Electrical Engineering book
Authors : Minsu Chae, Sangwook Han, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : https://doi.org/10.1007/978-981-15-9343-7_42

Abstract
With the spread of smart devices, the use of big data, and the proliferation of the Internet of Things, virtualization technology for cloud servers have become important worldwide. Also, research has been conducted to efficiently manage the resources of hosts in VMs. Container-based virtualization has less performance degradation than VMs because there is no emulation for the operating system. Using the Docker API is slow to measure. In this paper, we implement the resource measurement module of Job nodes and design middleware that supports auto-scaling in auto-scaling module and Docker-based multi-host environment.

Acknowledgments
This research supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2019-2014-1-00720 & IITP-2019-2015-0-00403) supervised by the IITP (Institute for Information & communications Technology Planning & Evaluation).

Serverless Framework for Efficient Resource Management in Docker Environment

Title : Serverless Framework for Efficient Resource Management in Docker Environment
Journal : Lecture Notes in Electrical Engineering book
Authors : Sangwook Han, Minsu Chae, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : https://doi.org/10.1007/978-981-13-9341-9_32

Abstract
APIs provided by the Docker is executed through the container engine. Thus, it is a reality that the speed of creation and deletion of containers or requests for information is very slow. The load is even worse when many containers sending API requests at once. In this paper, we propose a method to apply module related to resource management in a container to reduce the load on API request generated in serverless environment. And we propose a new framework that manages resources of several containers or multiple Docker serves.

Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2017R1A2B4010570) and the Ministry of Science and ICT, Korea, under the ITRC (Information Technology Research Center) support program (IITP-2017-2015-0-00403) supervised by the IITP (Institute for Information & communications Technology Promotion).

Fine Dust Predicting using Recurrent Neural Network with GRU

Title : Fine Dust Predicting using Recurrent Neural Network with GRU
Journal : International Journal of Innovative Technology and Exploring Engineering
Authors : Thanongsak Xayasouk, Guang Yang, HwaMin Lee
Corresponding author : HwaMin Lee

Abstract
The particulate matter especially PM2.5 can cause respiratory, cardiovascular and nervous system damage as many studies prove. The monitoring and forecasting system are highly required. This paper proposed a predicting model to forecast PM10 and PM2.5 concentrations in Seoul, South Korea. The proposed model combines the recurrent neural network with GRU. The proposed model can extract the hidden patterns in the long sequence data as RNN’s feature. The proposed model proved they could make satisfying particulate matter concentration in the urban area. The prediction results are reliable even for future 20 days. Meteorological data also contribute to higher predicting results as auxiliary data for the neural network. In further work, we will try to evaluate the model’s universality with more urban cities. Additionally, try to combine other deep learning methods to improve accuracy and reduce time-consuming for prediction.

Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2017R1A2B4010570) and Soonchunhyang University Research Fund.

AIR POLLUTION PREDICTION SYSTEM USING DEEP LEARNING

Title : AIR POLLUTION PREDICTION SYSTEM USING DEEP LEARNING
Journal : WIT Transactions on Ecology and the Environment
Authors : THANONGSAK XAYASOUK, HWAMIN LEE
Corresponding author : HwaMin Lee
DOI : http://doi.org/10.2495/AIR180071

Abstract
One of the most influential factors on human health is air pollution, such as the concentration of PM10 and PM2.5 is a damage to a human. Despite the growing interest in air pollution in Korea, it is difficult to obtain accurate information due to the lack of air pollution measuring stations at the place where the user is located. Deep learning is a type of machine learning method has drawn a lot of academic and industrial interest. In this paper, we proposed a deep learning approach for the air pollution prediction in South Korea. We use Stacked Autoencoders model for learning and training data. The experiment results show the performance of the air pollution prediction system and model that proposed.

Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2017R1A2B4010570).

Performance Comparison of CRUD Operations in IoT based Big Data Computing

Title : Performance Comparison of CRUD Operations in IoT based Big Data Computing
Journal : International Journal on Advanced Science, Engineering and Information Technology
Authors : JungYeon Seo, DaeWon Lee, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : http://doi.org/10.18517/ijaseit.7.5.2674

Abstract
Nowadays, due to the development of mobile devices, the kinds of data that are generated are becoming diverse, and the amount is becoming huge. The vast amount of data generated in this way is called big data. Big data must be processed in a different way than existing data processing methods. Representative methods of big data processing are RDBMS (Relational Database System) and NoSQL method. We compare NoSQL and RDBMS, which are representative database systems. In this paper, we use MySQL query and MongoDB query to compare RDBMS and NoSQL. We gradually compare the performance of CRUD operations in MySQL and MongoDB by increasing the amount of data. MongoDB sets index and compares it again. Through result of these operations is to choose a database system that fits the situation. This makes it possible to design and analyse big data more efficiently.

Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF-2017R1A2B4010570) and the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC (Information Technology Research Center) (IITP-2016-R0992-16-1006) supervised by the IITP (Institute for Information & communications Technology Promotion).

Wine Recommendation System Using the Optimum Degree of Similarity

Title : Wine Recommendation System Using the Optimum Degree of Similarity
Journal : Advanced Science Letters
Authors : JungYeon Seo, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : https://doi.org/10.1166/asl.2016.7831

Abstract
Recently, South Korea’s drinking culture is changing. Not to take drinking, drink to enjoy the atmosphere. There is an increasing consumption of wine to enjoy wine. The taste of the wine is determined by breed, vintage, etc. Wine of the latest trends is a good assessment of the quality, grade, and in particular the lower price. In this paper, to find similar users, based on the evaluation of wine. And we are using a collaborative filtering to recommend the wine that users prefer. To distributed storage of wine data and shorten to analysis time. By adding a weighting element to the system, it is possible to obtain a more accurate recommendation.

Acknowledgments
This research was supported by the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2017-2014-0-00720) supervised by the IITP (Institute for Information and communications Technology Promotion). Basic Science Research Program through the National Research Foundation of Korea (NRF) funed by the Minisry of Science. ICT and Future Planning (NRF-2017R1A2B4010570) and Soonchunhyang University Research Fund.

VM Relocation Method for Increase the Resource Utilization in Cloud Computing

Title : VM Relocation Method for Increase the Resource Utilization in Cloud Computing
Journal : Lecture Notes in Electrical Engineering
Authors : Sangwook Han, MinSoo Chae, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : https://doi.org/10.1007/978-981-10-5041-1_45

Abstract
Virtual machines are enabled to many of physical server can be integrated into fewer physical server. Integration of the server using virtual server technology induces the efficient use of resources to bring the cost benefits. Power consumption of the data center has been increased by 45% or more every year. More than 60% of the maximum power consumption is wasted on the physical server idle state, one way to reduce energy consumption is to minimize the number of physical servers. In this paper, VM usage time (running time) applied to 0–1 Knapsack algorithm. This method is the VM arrangement technology that can minimize the use of energy.

Acknowledgments
This research was supported by the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC(Information Technology Research Center) support programs (IITP-2016-R0992-16-1006 & IITP-2016-H8601-16-1009) supervised by the IITP (Institute for Information & communications Technology Promotion).

Development of Driver Safety Assist System Using OBD Data Analysis

Title : Development of Driver Safety Assist System Using OBD Data Analysis
Journal : Advanced Science Letters
Authors : Sangwook Han, Eunkwang Jeon, Jungyeon Seo, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : https://doi.org/10.1166/asl.2016.7831

Abstract
Many products already exist which can transmit some information using OBD through network communication. However, OBD products released in the market only for providing the information regarding driving and vehicle diagnostic services. In this paper, we developed a method which provides the alarm service to the drivers when their driving behaviors are not in the good condition. This proposed method sends those information using vibration motor or multiple LED on the basis of the data they received from the vehicles. It can be divided into two part: transmission part which collects vehicle data received from OBD and receiver part which informs drivers of their driving habits using vehicle data. The result of drivers’ driving habit can be installed on vehicle’s steering wheel, so that drivers’ bad driving habits can be improved. In addition, IoT product can prevent possible car accidents and can reduce the vehicle breakdown rate. Moreover, IoT products can impact on a better gas millage.

Acknowledgments
This research was supported by the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2015-R0992-15-1006) supervised by the IITP (Institute for Information and communications Technology Promotion).

Proxy Based Mobility Management Scheme Using Prediction Algorithm

Title : Proxy Based Mobility Management Scheme Using Prediction Algorithm
Journal : Lecture Notes in Electrical Engineering
Authors : Daewon Lee, Daeyong Jung, Doo-Soon Park, HwaMin Lee
Corresponding author : HwaMin Lee
DOI : https://doi.org/10.1007/978-3-662-47895-0_6

Abstract
Nowadays, mobile users are rapidly increased and many mobile environments are proposed by the improvement of wireless devices and network. There are many mobility management protocols are proposed to provide seamless mobile network environment. In this paper, we focused on transportation environment that is one of bus, train, airplane or ship that takes passengers using mobile devices. Transportation environment has a major problem that Mobile Node (MN) moves fast through multiple cells. Each MN in transportation keeps updating its current point of attachment to its Home Agent (HA) and corresponding node that causes triangle routing problem between HA of MN and HA of Mobile Router (MR). To remove triangle routing problem and minimize cost, we proposed mobility management scheme adapting proxy scheme then we propose prediction algorithm. Based on two features, we design proxy based architecture and extend router advertisement message to alert join in proxy domain. Then, we are classified the mobility into intra proxy mobility and global mobility. And we proposed proxy based mobility management scheme using prediction algorithm. We added heuristic that takes into account real world transportation’s movement. By numerical analysis, we shows proposed scheme reduces signaling overheads and increase packet transfer rate than NEMO and proxy MIP.

Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education ((No.2014R1A1A2057878).