• Journal of the Korean Geosynthetics Society
• /
• v.19 no.1
• /
• pp.45-53
• /
• 2020

There is an increasing tendency to try to make predictive analysis using measurement data based on machine learning techniques in the railway industries. In this paper, it was predicted that Track quality index (TQI) using vehicle acceleration data based on the machine learning method. The XGB (XGBoost) was the most accurate with 85% in the all data sets. Unlike the SVM model with a single algorithm, the RF and XGB model with a ensemble system were considered to be good at the prediction performance. In the case of the Surface TQI, it is shown that the acceleration of the z axis is highly related to the vertical direction and is in good agreement with the previous studies. Therefore, it is appropriate to apply the model with the ensemble algorithm to predict the track quality index using the vehicle vibration acceleration data because the accuracy may vary depending on the applied model in the machine learning methods.

• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.75-86
• /
• 2017

In this study, I propose a method to automate the method to diagnose the quality of big data. The reason for automating the quality diagnosis of Big Data is that as the Fourth Industrial Revolution becomes a issue, there is a growing demand for more volumes of data to be generated and utilized. Data is growing rapidly. However, if it takes a lot of time to diagnose the quality of the data, it can take a long time to utilize the data or the quality of the data may be lowered. If you make decisions or predictions from these low-quality data, then the results will also give you the wrong direction. To solve this problem, I have developed a model that can automate diagnosis for improving the quality of Big Data using machine learning which can quickly diagnose and improve the data. Machine learning is used to automate domain classification tasks to prevent errors that may occur during domain classification and reduce work time. Based on the results of the research, I can contribute to the improvement of data quality to utilize big data by continuing research on the importance of data conversion, learning methods for unlearned data, and development of classification models for each domain.

• Electronics and Telecommunications Trends
• /
• v.22 no.4 s.106
• /
• pp.87-95
• /
• 2007

급속한 정보통신 기술의 발달로 인하여 유비쿼터스 컴퓨팅의 기술, 네트워크 인프라, 3D 기술, 가상현실 기술 등 미래 콘텐츠 기술을 적용한 새로운 디지털 사용자 환경이 구축되고 있다. 교육 및 지식 분야에서도 동영상 기반이나 플래시 기반의 단순하고 일방형의 교육 콘텐츠를 벗어난 새로운 고품질의 이러닝 콘텐츠가 요구되고 있다. 또한 개인의 체험 중심의 학습경험과 지식을 스스로 구성해나가는 새로운 학습방법을 지원하는 이러닝 기술의 필요성이 증대되고 있다. 이에 대한 대안의 하나로 실재감과 몰입감을 촉진함으로써 학습효과를 향상시킬 수 있는 혼합현실기반의 이러닝 시스템의 개발이 시도되고 있다. 본 고에서는 혼합현실 이러닝 기술 개발 방향을 모색하기 위하여 국내외 혼합현실 이러닝 기술 동향, 시스템 사례, 교육적 효과에 대하여 살펴보고자 한다.

• Journal of Digital Convergence
• /
• v.9 no.4
• /
• pp.267-279
• /
• 2011

A variety of Web Services are being existences based on the development of the Internet. Especially, e-Learning services in the Universities make the temporal and spatial constraints overcome, and e-Learning services have gained great popularity to the students who use because those provide various convenience and usefulness. e-Learning studies have been actively performed based on the spread of e-Learning in the various industries. A number of studies suggest the diffusion plan of e-Learning applying the Technology Acceptance Model studies. Those studies focused on the ease of use and usefulness of e-Learning. The explanation about educational contents perspectives, which is the key factor in e-Learning, is very weak. Therefore, this study suggested the strategy for spreading the e-Learning adoption through in terms of e-Learning educational contents and trust perspectives. This research results would provide the strategic implications to boost the e-Learning adoption in the various universities in terms of e-Learning educational contents and trust perspectives.

• The Journal of the Korea Contents Association
• /
• v.14 no.6
• /
• pp.477-490
• /
• 2014

The purpose of this study is to investigate factors influencing continuous usage intention of mobile learning and suggest practical strategies to enhance learners' continuous usage intention of mobile learning. In this study, we hypothesized that system quality, information quality, service quality and personal innovativeness have a positive effect on effort expectancy and performance expectancy, which ultimately have a positive effect on continuous usage intention. In order to examine structural relationship among variables, we surveyed 279 students who took courses at W Cyber University in 2013 fall semester. After collecting data, we examined causal relationship among variables using Structural Equation Modeling. The results of this study are as follows: First, system quality and personal innovativeness significantly affect effort expectancy. Second, information quality, service quality and personal innovativeness significantly affect performance expectancy. Last of all, effort expectancy and performance expectancy significantly affect continuous usage intention of mobile learning.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.712-715
• /
• 2023

딥러닝 기술의 발전은 고품질의 대규모 데이터에 크게 의존한다. 그러나, 데이터의 품질과 일관성을 유지하는 것은 상당한 비용과 시간이 소요된다. 이러한 문제를 해결하기 위해 최근 연구에서 최소한의 비용으로 최대의 성능을 추구하는 액티브 러닝(active learning) 기법이 주목받고 있는데, 액티브 러닝은 모델 관점에서 불확실성(uncertainty)이 높은 데이터들을 샘플링 하는데 중점을 둔다. 하지만, 레이블 생성에 있어서 여전히 많은 시간적, 자원적 비용이 불가피한 점을 고려할 때 보완이 불가피 하다. 본 논문에서는 의사-라벨링(pseudo labeling)을 활용한 준지도학습(semi-supervised learning) 방식과 학습 손실을 동시에 사용하여 모델의 불확실성(uncertainty)을 측정하는 방법론을 제안한다. 제안 방식은 레이블의 신뢰도(confidence)와 학습 손실의 최적화를 통해 비용 효율적인 데이터 레이블 생성 방식을 제안한다. 특히, 레이블 데이터의 품질(quality) 및 일관성(consistency) 측면에서 딥러닝 모델의 정확도 성능을 높임과 동시에 적은 데이터만으로도 효과적인 학습이 가능할 수 있는 메커니즘을 제안한다.

• Journal of vocational education research
• /
• v.37 no.5
• /
• pp.25-53
• /
• 2018

The purpose of this study is to find out the improvement plan through the satisfaction survey of the trainees involved in vocational training fraud preventive education. In order to do this, we conducted a satisfaction survey(4,263 persons) of 5,939 people who participated in the prevention education conducted by group education or e-learning in 2017. Finally we collected 4,237 effective responses data. Descriptive statistics and the regression analysis were conducted. The finding of the study were as follows. First, the education service quality(4.42), satisfaction level(4.44), understanding level(4.44) and help level(4.45) were significantly higher than those of participants in the preventive education 4 and above. Second, e-learning participants' perceived level of education service quality, satisfaction, comprehension, and help was higher in all variables than collective education's. Third, all of the sub-factors of preventive education service quality influenced satisfaction, understanding, and help in collective education and e-learning, respectively. In the collective education, the contents of education had the greatest influence, and in e-learning, the data composition had the greatest influence. Fourth, desirable education contents were cases of fraud training(70.7%), disposition regulations(47.9%), NCS course operation instructions(32.8%) and training management best practices(32.4%). Additional requirements also included the establishment of an in-depth course, the provision of anti-fraud education content for trainees, and screen switching and system stability that can be focused on e-learning. Therefore, this study suggests that first, it is necessary to activate e-learning for prevention education more, reflecting satisfaction of e-learning is higher than that of collective education. Second, it is necessary to diversify the content of preventive education and to provide it more abundantly, because it has the biggest influence in common with the satisfaction, understanding and help level of the preventive education. Third, education content next, the factors that have a relatively big influence on satisfaction are shown as delivery method and education place in the collective education. Therefore, it is necessary to prepare education place considering the assignment of instructor and convenience. Fourth, constructing data next, the factor that have a relatively great influence on understanding and help are found to be operator support, and more active operator support activities are required in e-learning. Fifth, it is required to delivery prevention activity for trainees participating in vocational training. Sixth, it is necessary to analyze the educational need to construct the contents of preventive education more systematically.

• Journal of Korea Entertainment Industry Association
• /
• v.5 no.1
• /
• pp.65-72
• /
• 2011

The major purpose of this study is to investigate the influencing factors toward continuance intention in e-learning services. For this purpose, we introduced Post Acceptance Model(PAM) proposed by Bhattacherjee(2001) as basic analysis framework. Based on the relevant literature reviews, this study posits seven characteristics, that is, contents quality, interactivity, expectation confirmation, perceived ease of use, perceived usefulness, user satisfaction, and continuance intention as key variables to describe the post acceptance behavior in e-learning services. Data have been collected from users who have used e-learning services and the research model and hypotheses were tested through covariance structural model analysis. The results of this study are summarized as follows. First, contents quality, interactivity, and expectation confirmation have positive influence upon perceived usefulness. Second, contents quality, interactivity, expectation confirmation, and perceived ease of use have positive influence upon user satisfaction. Lastly, perceived usefulness have positive effect on the user satisfaction, and perceived usefulness and user satisfaction positively related to continuance intention in e-learning services. The findings have significant implications for e-learning service providers and academic researchers.

• Electronics and Telecommunications Trends
• /
• v.24 no.1
• /
• pp.90-100
• /
• 2009

메인프레임 기반 컴퓨팅에서 PC 기반 컴퓨팅에 이어 제3세대 컴퓨터 환경인 유비쿼터스 컴퓨팅 환경으로의 진화는 현실에 컴퓨터를 탑재하여 언제 어디서나 모든 곳에 존재하는 네트워크 환경을 제공하고 있고, 이러한 유비쿼터스 컴퓨팅과 이를 연동한 네트워크 패러다임은 미래교육 시스템이 나가야 할 새로운 방향을 제시한다. 양방향 의사소통을 기본으로 하는 지식기반사회의 교육패러다임의 변화는 컴퓨터의 역할 패러다임의 변화와 그 맥을 함께 하고 있으며, 이러닝 분야에서도 기존의 단순하고 일방향적인 교육 콘텐츠에서 벗어나 새로운 기술에 기반한 고품질의 양방향적 콘텐츠를 요구하고 있다. 이에 대한 하나의 대안으로 학습자에게 실재감과 몰입감을 촉진하고 마커의 직접적인 조작활동을 통해 양방향 상호작용을 극대화 할 수 있는 혼합현실(mixed reality) 기반 이러닝 시스템의 개발이 시도되고 있다. 본 고에서는 이러한 혼합현실기반 이러닝 기술의 동향에 대해 살펴보고자 한다.

• The Journal of Society for e-Business Studies
• /
• v.26 no.4
• /
• pp.15-36
• /
• 2021

The airline industry faces with significant competition due to the rise of technology innovation and diversified customer needs. Therefore, continuous quality management is essential to gain competitive advantages. For this reason, there have been various studies to measure and manage service quality using customer reviews. However, previous studies have focused on measuring customer satisfaction only, neglecting systematic management between customer expectations and perception based on customer reviews. In response, this study suggests a framework to identify relevant criteria for service quality management, measure the importance, and assess the customer perception based on customer reviews. Machine learning techniques, topic models, and sentiment analysis are used for this study. This study can be used as an important strategic tool for evaluating service quality by identifying important factors for airline customer satisfaction while presenting a framework for identifying each airline's current service level.