Hankil Kim
Korea University of Media Arts

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Web Server-based Distributed Machine Socialization System Changsu Kim; Hankil Kim; Jongwon Lee; Hoekyung Jung
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 2: April 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (328.904 KB) | DOI: 10.11591/ijece.v8i2.pp631-637

Abstract

In recent years, there has been an increasing trend of offering services that are useful to users, such as Google's Nest, through machine socialization between parts and devices in specific spaces such as automobiles, homes, and factories. The existing inter - device collaboration system is a centralized system using router, and it controls collaboration between devices by building OpenWrt and web server on router. However, due to the limited hardware resources on the router, it generates network traffic congestion as the number of requests from the client increases or the number of clients connected to the server increases. In this paper, we propose a distributed machine collaboration system based on web server using inter - device collaboration algorithm. The study of Micro Controller Unit (MCU) has reduced the traffic incidence by solving the request sent to the router from each device by oneself.
Human activity recognition by using convolutional neural network Hankil Kim; Sungock Lee; Hoekyung Jung
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 6: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (463.908 KB) | DOI: 10.11591/ijece.v9i6.pp5270-5276

Abstract

In recent years, many researchers have studied the HAR (Human Activity Recognition) system. HAR using smart home sensor is based on computing in smart environment, and intelligent surveillance system conducts intensive research on peripheral support life. The previous system studied in some of the activities is a fixed motion and the methodology is less accurate. In this paper, vision-based studies using thermal imaging cameras improve the accuracy of motion recognition in intelligent surveillance systems. We use one of the deep learning architectures widely used in image recognition systems called Convolutional Neural Networks (CNN). Therefore, we use CNN and thermal cameras to provide accuracy and many features through the proposed method.
Automatic control system based on iot data identification Hankil Kim; Jaehyun Park; Hoekyung Jung
Indonesian Journal of Electrical Engineering and Computer Science Vol 19, No 3: September 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v19.i3.pp1525-1532

Abstract

Recently, as the internet of things (IoT) technology has developed, researches are rigorously conducted to construct smart environments such as smart home, smart grid, and industrial IoT. However, currently existing systems consists of a series of events, and even if an existing task is running, unnecessary work still occurs as both works happen simultaneously. In this paper, we propose an automatic work control system to solve this problem. The proposed system transmits the data measured by the sensor to the server and identifies non-real-time tasks such as real-time work which is related to the dangerous situations, ventilation and temperature control. In addition, priority among the tasks is set in a way that existing tasks are stopped when high priority tasks occur. Accordingly, this can reduce the unnecessary waste of power, and the user is able to receive a proactive service.