• Journal of the Korean Society for Computer Game
• /
• v.31 no.4
• /
• pp.111-119
• /
• 2018

National agencies and corporations are making a lot of efforts to educate mechanics from high school to university and enterprise training center to train as skilled mechanic. but the theoretical training using textbooks and the training using equipment not used in the field did not provide proper maintenance training. And education using special equipment or assuming dangerous situation was very dangerous, so we were carrying out education with video or photo. In recent, there have been a number of cases in which effective training simulations have been researched and developed in order to experience situations and solve problems safely through simulation from simple maintenance to special maintenance by combining VR and AR. This paper describes the comparative study of the existing APIs such as Danuri VR, DisTi Engine and Remote AR for general purpose AR/VR contents. We also proposed a AR/VR API based on Unity 3D Engine for AR/VR maintenance contents. The API can be used for maintenance contents developers efficiently.

• Journal of Practical Engineering Education
• /
• v.9 no.1
• /
• pp.49-56
• /
• 2017

Recently, due to Industry 4.0, there is a great interest in smart factory for productivity improvement and customer satisfaction in manufacturing industry, and construction is also actively pursued by government support. In particular, data integration and fieldbus communication technology to build an efficient production system are essential. Fieldbus is an open control system that is not tied to a specific vendor system and has various advantages such as compatibility with other products, accuracy of data transmission, and remote diagnosis. However, there are no educational equipment for training field buses, training courses and examples for practical training, and there are many limitations in improving the practical skills needed for building smart factories in the industrial field. Therefore, this study develops PLC based fieldbus education equipment and training course based on previous research results that selected PLC and communication technology suitable for domestic industry field for practical fieldbus training and develops the training program of Ethernet IP, Profibus DP, Modbus, CC-Link, and DeviceNet. In addition, it is confirmed that the control and remote diagnosis of distributed field devices are possible by data collection and monitoring.

• Korean Journal of Remote Sensing
• /
• v.34 no.1
• /
• pp.45-74
• /
• 2018

Landslide is a natural hazard that threats lives and properties in many areas around the world. Landslides are difficult to recognize, particularly in rainforest regions. Thus, an accurate, detailed, and updated inventory map is required for landslide susceptibility, hazard, and risk analyses. The inconsistency in the results obtained using different features selection techniques in the literature has highlighted the importance of evaluating these techniques. Thus, in this study, six techniques of features selection were evaluated. Very-high-resolution LiDAR point clouds and orthophotos were acquired simultaneously in a rainforest area of Cameron Highlands, Malaysia by airborne laser scanning (LiDAR). A fuzzy-based segmentation parameter (FbSP optimizer) was used to optimize the segmentation parameters. Training samples were evaluated using a stratified random sampling method and set to 70% training samples. Two machine-learning algorithms, namely, Support Vector Machine (SVM) and Random Forest (RF), were used to evaluate the performance of each features selection algorithm. The overall accuracies of the SVM and RF models revealed that three of the six algorithms exhibited higher ranks in landslide detection. Results indicated that the classification accuracies of the RF classifier were higher than the SVM classifier using either all features or only the optimal features. The proposed techniques performed well in detecting the landslides in a rainforest area of Malaysia, and these techniques can be easily extended to similar regions.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1109-1112
• /
• 2003

Information technology has enabled mass standards calibration to be performed through internet. For this, an automatic weight handler was manufactured. During the operation the images of weight operation and the system are provided via the measurement system and a web server. The measurement system consists of a balance, a weight handler, instruments for environment measurement and a PC. The weight handler automatically loads and unloads weights on and from the weighing pan. The weight handler allows 6 series weights to be operated for weight calibration of 100-50-20-20-10-10 gram series weight. This capability could be used for "remote training" for series weight calibration.

• Journal of Practical Engineering Education
• /
• v.13 no.2
• /
• pp.305-320
• /
• 2021

Due to COVID-19, the education and training environment in vocational competency development has changed significantly. In vocational education and training, where the proportion of face-to-face training is more extensive than in other areas of education, some training courses had no choice but to be converted to online. This study presents a distance training system plan for non-contact vocational training by analyzing the learner's non-contact learning experiences. Non-face-to-face education experiences were investigated for learners of private vocational training institutions, universities, and public higher vocational training institutions. The main contents of the survey were to analyze the non-face-to-face learning experiences of these learners for the educational environment and educational purposes. Based on the results of the learners' non-face-to-face learning experiences, a draft of a remote training system construction plan for non-face-to-face education was composed, and a Delphi study was conducted on the draft non-face-to-face remote training system. A method for establishing a distance training system including non-face-to-face teaching and learning strategies, learning and operation support was proposed with these results.

• Korean Journal of Computational Design and Engineering
• /
• v.20 no.4
• /
• pp.420-430
• /
• 2015

Operator Training Simulators (OTSs) provide macroscopic training environment for plant operation. They are equipped with simulation systems for the emulation of remote monitoring and controlling operations. OTSs typically provide 2D block diagram-based graphic user interface (GUI) and connect to process simulation tools. However, process modeling for OTSs is a difficult task. Furthermore, conventional OTSs do not provide real plant field information since they are based on 2D human machine interface (HMI). In order to overcome the limitation of OTSs, we propose a new type of plant training system. This system has the capability required for collaborative training between operators and field workers. In addition, the system provides 3D virtual training environment such that field workers feel like they are in real plant site. For this, we designed system architecture and developed essential functions for the system. For the verification of the proposed system design, we implemented a prototype training system and performed experiments of collaborative training between one operator and two field workers with the prototype system.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2002.03a
• /
• pp.45-52
• /
• 2002

Artificial neural networks (ANN) have been successfully used for classifying remotely sensed imagery. However, ANN still is not the preferable choice for classification over the conventional classification methodology such as the maximum likelihood classifier commonly used in the industry production environment. This can be attributed to the ANN characteristic built-in stochastic process that creates difficulties in dealing with unequally represented training classes, and its training performance speed. In this paper we examined some practical aspects of training classes when using a back propagation neural network model for remotely sensed imagery. During the classification process of remotely sensed imagery, representative training patterns for each class are collected by polygons or by using a region-growing methodology over the imagery. The number of collected training patterns for each class may vary from several pixels to thousands. This unequally populated training data may cause the significant problems some neural network empirical models such as back-propagation have experienced. We investigate the effects of training over- or under- represented training patterns in classes and propose the pattern repopulation algorithm, and an adaptive alpha adjustment (AAA) algorithm to handle unequally represented classes. We also show the performance improvement when input patterns are presented in random fashion during the back-propagation training.

• Proceedings of the KSRS Conference
• /
• 2007.03a
• /
• pp.33-36
• /
• 2007

토지피복분류， 식생분류， 식물피복도 분류 등 원격탐사 영상자료의 주된 이용분야에서 지상자료는 매우 중요한 부분을 차지하고 있다. 가령 감독분류를 위한 training site 에 대한 측정이나 또는 분류 정확도 검증을 위한 측면에서도 지상측정은 반드시 필요한 부분이다. 본 논문에서는 피복분류 과정에서 반드시 필요한 지상측정을 위한 표본조사에서 유의하여야 할 통계학적 측면에서 고려해야 할 사항을 검토한다.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.2
• /
• pp.192-199
• /
• 2004

Navigation simulators have been used in many marine schools and manne training centers since the early 1960's. But these simulators were very expens~ve and were almost limited only in one engine system. In this paper, a catamaran with twin engine system. controlled by two remote control levers and its economic simulator based on a personal computer shall be introduced. One of the main features of catamaran is to control variously its progressing direction. In the static state, a catamaran can move into all the directions and in the dynamic state, ship can change immediately the heading and speed. Although a good navigator can skillfully operate one engine system, it is difficult to control smoothly the catamaran of twin engine system without any threat for the safety of passengers. Thus. in order to bring up the expert navigators. the development of a simulator which makes the training effective is necessary, Therefore, in this paper, a Fuzzy Inference Technique based Maneuvering Simulator for catamaran with twin engine system was developed. In general. in order to develop a catamaran simulator for effective training, first of all. its mathematical model must be acquired. According to the acquired system modeling. the dynamics of simulator is determined, But the proposed technique can omit a complex and tedious mathematical modeling procedures by using the fuzzy inference, which dependent upon only experiences of an expert and can design an efficient training program for unskillful navigators. This developed simulator was consisted of two fuzzy inference routines and two remote control levers, and was focused on effective training of navigators for the safe maneuvering to avoid a collision in a harbor.

• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.22-30
• /
• 2022

In order to prevent chemical accidents caused by human error, a chemical accident prevention and response training program using advanced technology was developed. After designing a virtual process based on the previously built pilot plant, chemical accident response contents were developed. A part of the pilot facility was remodeled for content realization and a remote control function was given. In addition, a DCS program that can control facilities in a virtual environment was developed, and chemical process operator training (OTS) that can finally respond to virtual chemical accidents was developed in conjunction with AR. Through this, trainees can build driving skills by directly operating the device, and by responding to virtual chemical accidents, they can develop emergency response capabilities. If the next-generation OTS like this study is widely distributed in the chemical industry, it is expected to greatly contribute to the prevention of chemical accidents caused by human error.