Chang-Heon Oh
Korea University of Technology and Education

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

Development of Automatic Mold Shot Measurement and Management System for Smart Factory Hyun-Jun Shin; Sung-Jin Kim; Min-Ho Jeon; Chang-Heon Oh
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (628.928 KB) | DOI: 10.11591/ijece.v6i6.pp3142-3147

Abstract

Many small- and medium-sized car-part manufacturers are either still managing their mold manually or rarely managing it, and therefore, experience significant manufacturing cost and loss in time. In such a situation, a module has been developed in the present work which can count the number of mold used. Such a module is extremely important for small and medium-sized enterprises (SMEs) applying which in the production line they will be able to manage the mold life cycle and improve product quality. This is expected to have both direct and indirect effects on their business activities. The developed system uses a photo sensor, distance measurement sensor, Atmega128 MCU, tablet pc and Bluetooth communication module. The actual module developed in this study was set up on a molding equipment for test and data were collected using an existing tablet PC. The test showed that the number of shots increased when the upper mold touched the lower mold. The maximum and minimum value between the upper and lower molds could be adjusted with the automatic mold shot measurement and management system. Therefore, any molding equipment with various upper-lower gaps will be able to apply the newly developed system.
Comparative analysis of multiple classification models to improve PM10 prediction performance Yong-Jin Jung; Kyoung-Woo Cho; Jong-Sung Lee; Chang-Heon Oh
International Journal of Electrical and Computer Engineering (IJECE) Vol 11, No 3: June 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v11i3.pp2500-2507

Abstract

With the increasing requirement of high accuracy for particulate matter prediction, various attempts have been made to improve prediction accuracy by applying machine learning algorithms. However, the characteristics of particulate matter and the problem of the occurrence rate by concentration make it difficult to train prediction models, resulting in poor prediction. In order to solve this problem, in this paper, we proposed multiple classification models for predicting particulate matter concentrations required for prediction by dividing them into AQI-based classes. We designed multiple classification models using logistic regression, decision tree, SVM and ensemble among the various machine learning algorithms. The comparison results of the performance of the four classification models through error matrices confirmed the f-score of 0.82 or higher for all the models other than the logistic regression model.
Analysis of Ionospheric foF2 by Solar Activity over the Korean Peninsula Min-Ho Jeon; Chang-Heon Oh
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 1: February 2016
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1215.227 KB) | DOI: 10.11591/ijece.v6i1.pp71-81

Abstract

The F2 layer is the upper sector of the ionospheric F region, and it is ~250 km above sea level. It has a high electron density and thus plays an important role in shortwave communications. The variations of the critical frequency of the F2 layer (foF2) offer clues regarding the events happening within the entire F2 layer, and foF2 analysis is essential for stable shortwave communications. This study analyzes the seasonal and annual variations of the foF2 as well as the reactions of the F2 layer height at two locations in South Korea by employing the mean and standard deviation (SD) used in previous studies. To ensure a more elaborate analysis, the median and quartiles were used for analyzing the ionosphere. We thereby compensate for the limitations of the mean and SD in developing the SD, despite the convenience of the SD for probability analysis. The application of the median and quartiles for the analysis of ionospheric data led to analysis results with greater detail. This was achieved by determining the relative SD and concurrently displaying the outliers and range of variations
An LED-based visible light communication system for multicast Jong-Sung Lee; Dae-Hee Lee; Sung-Jin Kim; Chang-Heon Oh
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 1: January 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i1.pp265-271

Abstract

Visible Light Communication is a communication method that transmits data through light by pulsing an LED at high speed, performing broadcast communication for all devices existing in its coverage. Broadcast-based Visible Light Communication is limited to application to Internet of Things services, where various applications exist, although all receivers can communicate within the range of light sources. Therefore, this paper proposes an LED based Visible Light Communication system for multicast. The proposed system performs individual multicast by participating in communication only with receivers configured to use a specified ID value input at the transmitting side during data transmission. Experimental results show that the receiver can receive files individually according to a specified ID value.