• Journal of Practical Engineering Education
• /
• v.6 no.1
• /
• pp.37-42
• /
• 2014

The automated visual inspection system (machine vision system) for quality assurance is important factory automation equipment in the manufacturing industries, such as display, semiconductor, etc. There is a lot of demand for the machine vision engineers. However, there are no technical training courses for machine vision technologies in vocational schools, colleges and universities. In this paper, we present the implementation of line scan camera based equipment for technical training of the automated visual inspection system. The training system consists of the X-Y stage which is widely used in machine vision industries and its variable image resolution are set to $10-30{\mu}m$. Additionally, this training system can attach the industrial illumination, either the direct illuminator or coaxial illuminator, for verifying the effect of illuminations. This means that the trainee can have a practical training in various equipment conditions and the training system is similar to the automated visual inspection system in industries.

• The Korean Journal of Emergency Medical Services
• /
• v.26 no.1
• /
• pp.7-19
• /
• 2022

Purpose: The purpose of this study is to evaluate the interrupted chest compression time during the use of an automated external defibrillator (AED) depending on different AED practice training methods, and to report differences in self-efficacy before and after training. Methods: We enrolled university freshmen who have had cardiopulmonary resuscitation (CPR) training but have not or have had AED training but over 6 months. We examined differences between the group that practiced only shockable rhythms during training and the group that practiced both shockable and non-shockable rhythms. Results: A total of 72 individuals participated in this study, with 36 individuals each in the control and experimental groups. There was no statistically significant difference in the proficiency of AED usage between the two groups. In non-shockable cases, the experimental group showed shorter chest compression interruption time than the control group (2.30±1.21sec vs. 3.16±1.73 sec; p<0.01). In terms of self-efficacy before and after training, both groups showed higher self-efficacy after than before training. Conclusion: Individuals who underwent training that provided practice on both shockable and non-shockable rhythms had a shorter interrupted chest compression time when using the AED.

• Journal of The Korean Association For Science Education
• /
• v.43 no.3
• /
• pp.237-251
• /
• 2023

This study explores the possibility of automated scoring for scientific graph answers by designing an automated scoring model using convolutional neural networks and applying it to students' kinematics graph answers. The researchers prepared 2,200 answers, which were divided into 2,000 training data and 200 validation data. Additionally, 202 student answers were divided into 100 training data and 102 test data. First, in the process of designing an automated scoring model and validating its performance, the automated scoring model was optimized for graph image classification using the answer dataset prepared by the researchers. Next, the automated scoring model was trained using various types of training datasets, and it was used to score the student test dataset. The performance of the automated scoring model has been improved as the amount of training data increased in amount and diversity. Finally, compared to human scoring, the accuracy was 97.06%, the kappa coefficient was 0.957, and the weighted kappa coefficient was 0.968. On the other hand, in the case of answer types that were not included in the training data, the s coring was almos t identical among human s corers however, the automated scoring model performed inaccurately.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.7
• /
• pp.1379-1385
• /
• 2017

Virtual training is a kind of training that proceeds as if it were a real situation. In recent years, there has been a growing demand for experiencing a situation in which a virtual reality technology has not been experienced directly in the real world due to the rapid development of the technology. Especially, safety education is very necessary in Korea where safety accidents are caused by many disasters. Therefore, simulation of disaster response training using virtual reality is more urgent than ever. Although the automatic defibrillator is the medical device that is most needed to rescue patients with cardiac arrest, few people know how to use it. Therefore, there are very few cases where the use of automatic defibrillators has saved the patient's life in Korea. The proposed Automated External Defibrillator virtual training system enables immersive and experiential training in real situations and effective training at low cost.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.4 no.2
• /
• pp.91-97
• /
• 2012

The automated visual inspection system (machine vision system) for quality assurance is an important factory automation equipment in the manufacturing industries, such as display, semiconductor, etc. The world market of the machine vision components is expected 18 billon dollars in 2015. Therefore, there is a lot of demand for the machine vision engineers. However, there are no technical training courses for machine vision technologies in vocational schools, colleges and universities. In this paper, we propose a technical training program for the machine vision technology. The total time of training is 30 to 60 hours and the training program can operate flexibly by student's major, a priori knowledge and education level.

• Korean Journal of Remote Sensing
• /
• v.26 no.3
• /
• pp.317-324
• /
• 2010

In recent years, many automatic classification approaches have been employed. An automatic classification method can be effective, time-saving and can produce objective results due to the exclusion of operator intervention. This paper proposes a classification method based on automated training for high resolution multispectral images using ancillary data. Generally, it is problematic to automatically classify high resolution images using ancillary data, because of the scale difference between the high resolution image and the ancillary data. In order to overcome this problem, the proposed method utilizes the classification results of a Landsat image as a medium for automatic classification. For the classification of a Landsat image, a maximum likelihood classification is applied to the image, and the attributes of ancillary data are entered as the training data. In the case of a high resolution image, a K-means clustering algorithm, an unsupervised classification, was conducted and the result was compared to the classification results of the Landsat image. Subsequently, the training data of the high resolution image was automatically extracted using regular rules based on a RELATIONAL matrix that shows the relation between the two results. Finally, a high resolution image was classified and updated using the extracted training data. The proposed method was applied to QuickBird and SPOT-5 images of non-accessible areas. The result showed good performance in accuracy assessments. Therefore, we expect that the method can be effectively used to automatically construct thematic maps for non-accessible areas and update areas that do not have any attributes in geographic information system.

• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.397-408
• /
• 2009

Image training is a very important yet difficult state for automated visual inspection using computers. Because the size of parts for the recently produced PCB (Printed Circuit Board) becomes smaller and circuit patterns gradually become more complex, a difficult and complex training process is becoming a big problem within an industry where development cycle for new products is short and various products must be inspected. This research produced a reference image by using CAD (Gerber) file which becomes a standard for PCB automatic visual inspection. Reference image from a Gerber file guarantees PCB patterns with no defects. Through system implementation and experimentation, Gerber file is used in order to propose a plan which allows an easy training process for PCB automatic visual inspection system.

• Safety and Health at Work
• /
• v.10 no.4
• /
• pp.461-469
• /
• 2019

Background: Collisions involving workers and mobile machines continue to be a major concern in underground coal mines. Over the last 30 years, these collisions have resulted in numerous injuries and fatalities. Recently, the Mine Safety and Health Administration (MSHA) proposed a rule that would require mines to equip mobile machines with proximity detection systems (PDSs) (systems designed for automated collision avoidance). Even though this regulation has not been enacted, some mines have installed PDSs on their scoops and hauling machines. However, early implementation of PDSs has introduced a variety of safety concerns. Past findings show that workers' trust can affect technology integration and influence unsafe use of automated technologies. Methods: Using a mixed-methods approach, the present study explores the effect that factors such as mine of employment, age, experience, and system type have on workers' trust in PDSs for mobile machines. The study also explores how workers are trained on PDSs and how this training influences trust. Results: The study resulted in three major findings. First, the mine of employment had a significant influence on workers' trust in mobile PDSs. Second, hands-on and classroom training was the most common types of training. Finally, over 70% of workers are trained on the system by the mine compared with 36% trained by the system manufacturer. Conclusion: The influence of workers' mine of employment on trust in PDSs may indicate that practitioners and researchers may need to give the organizational and physical characteristics of each mine careful consideration to ensure safe integration of automated systems.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.13 no.2
• /
• pp.1-13
• /
• 2005

The objective of the study is to analyze the pilot's behavior such as preference and management technique to the automation of aircraft through Flight Management Attitude Questionnaire(FMAQ) survey. Participants in the survey are grouped in rank and nationality, and attitudes of those groups toward the automation are analyzed. Previous empirical studies have demonstrated large cross-nation differences in attitudes regarding task performance across several work domains including aviation. Analysis of the survey shows that the pilots in Asia region like the automation and its usage more than the pilots in western and Oceania regions. The trust in the automation is higher among glass cockpit pilots than among the conventional aircraft pilots. More foreign pilots than Korean pilots believe that the automation may deteriorate their flight skills. While more Korean pilots than foreign pilots agree that their flight skills can be kept by manual controls. The pilots also feel that the automated cockpits would require more verbal communications between crew members. For improving the automation management skills and the effective automation usage, the Situation Awareness training and Crew Resource Management(CRM) training are strongly suggested.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.48-53
• /
• 1999

The paper presents an automated method for generating fuzzy rules and fuzzy membership functions for pattern classification from training sets of examples and an application to the land-cover classification. Initially, fuzzy subspaces are created from the partitions formed by the minimum and maximum of individual feature values of each class. The initial membership functions are determined according to the generated fuzzy partitions. The fuzzy subspaces are further iteratively partitioned if the user-specified classification performance has not been archived on the training set. Our classifier was trained and tested on patterns consisting of the DN of each band, (XS1, XS2, XS3), extracted from KITSAT-3 multispectral scene. The result represents that our classification method has higher generalization power.