• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1071-1081
• /
• 2021

In addition to the current quality control procedures for the weather observation performed by the Korea Meteorological Administration (KMA), this study proposes quality inspection standards for Internet of Things (IoT) urban weather observed data based on machine learning that can be used in smart cities of the future. To this end, in order to confirm whether the standards currently set based on ASOS (Automated Synoptic Observing System) and AWS (Automatic Weather System) are suitable for urban weather, usability was verified based on SKT AWS data installed in Seoul, and a machine learning-based quality control algorithm was finally proposed in consideration of the IoT's own data's features. As for the quality control algorithm, missing value test, value pattern test, sufficient data test, statistical range abnormality test, time value abnormality test, spatial value abnormality test were performed first. After that, physical limit test, stage test, climate range test, and internal consistency test, which are QC for suggested by the KMA, were performed. To verify the proposed algorithm, it was applied to the actual IoT urban weather observed data to the weather station located in Songdo, Incheon. Through this, it is possible to identify defects that IoT devices can have that could not be identified by the existing KMA's QC and a quality control algorithm for IoT weather observation devices to be installed in smart cities of future is proposed.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.4
• /
• pp.55-61
• /
• 2024

Recently, the number of aging concrete structures is steadily increasing. This is because many of these structures are reaching their expected lifespan. Such structures require accurate inspections and persistent maintenance. Otherwise, their original functions and performance may degrade, potentially leading to safety accidents. Therefore, research on objective inspection technologies using deep learning and computer vision is actively being conducted. High-resolution images can accurately observe not only micro cracks but also spalling and exposed rebar, and deep learning enables automated detection. High detection performance in deep learning is only guaranteed with diverse and numerous training datasets. However, surface damage to concrete is not commonly captured in images, resulting in a lack of training data. To overcome this limitation, this study proposed a method for generating concrete surface damage images, including cracks, spalling, and exposed rebar, using stable diffusion. This method synthesizes new damage images by paired text and image data. For this purpose, a training dataset of 678 images was secured, and fine-tuning was performed through low-rank adaptation. The quality of the generated images was compared according to three base models of stable diffusion. As a result, a method to synthesize the most diverse and high-quality concrete damage images was developed. This research is expected to address the issue of data scarcity and contribute to improving the accuracy of deep learning-based damage detection algorithms in the future.

• Electronics and Telecommunications Trends
• /
• v.26 no.1
• /
• pp.36-46
• /
• 2011

급변하는 사회 환경과 기술 변화에 적응하기 위해 평생 교육에 대한 관심이 높아지고 있으며 이러한 욕구를 충족시키기 위한 새로운 개념의 e-러닝 기술에 대한 연구가 활발히 진행중이다. 또한 기존의 단순한 정보 전달 수준을 뛰어 넘어 학습자가 직접 참여하고 체험할 수 있는 고품질의 인터랙티브 e-러닝 콘텐츠에 대한 요구가 증대되고 있다. 본 고에서는 최근 이슈가 되고 있는 증강 현실 학습 기술, 가상현실 학습 기술, 시뮬레이션 학습 기술, 맞춤형 학습 기술 등 e-러닝 요소 기술 개발 현황에 대해 살펴보고 관련 기술 동향을 분석한다. 또한 e-러닝 기술 관련 표준화 동향에 대해서도 살펴본다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.243-250
• /
• 2023

Chest X-ray is radiological examination for xeamining the lungs and haert, and is particularly widely used for diagnosing lung disease. Since the quality of these chest X-rays can affect the doctor's diagnosis, the process of evaluating the quality must necessarily go through. This process can involve the subjectivity of radiologists and is manual, so it takes a lot of time and csot. Therefore, in this paper, based on the chest X-ray quality assessment guidelines used in clinical settings, we propose a tool that automates the five quality assessments of artificial shadow, coverage, patient posture, inspiratory level, and permeability. The proposed tool reduces the time and cost required for quality judgment, and can be further utilized in the pre-processing process of selecting high-quality learning data for the development of a learning model for diagnosing chest lesions.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.5 no.1
• /
• pp.45-51
• /
• 2013

To improve the e-learning education quality in VietHanIT College (Vietnam-Korea Friendship Information Technology College), e-learning acceptance was evaluated based on the well-known Technology Acceptance Model (TAM). Quantitative data of the questionnaire survey were gathered from 158 lecturers and staffs of VietHanIT College and analyzed by using Statistical Package for the Social Sciences (SPSS). While designing the questionnaire various previous studies were considered and hypotheses and models of the study were set up accordingly. As the results, success model of e-learning system was built up and important factors were identified. And most of lectures and staffs in VietHanIT College were aware of the benefits of e-learning system and they were ready to apply e-learning method for their training and teaching.

• Journal of Digital Contents Society
• /
• v.18 no.5
• /
• pp.869-879
• /
• 2017

This study identifies the effects of HTML5 service quality on the use intention of smart learning and present the policy implications through empirical studies. This study select assurance, reliability, tangibles, responsiveness, empathy as independent variables of HTML5 service quality and also select perceived usefulness, degree of perceived ease of use as parameters and select use intention of smart learning as dependent variables. The control variables such as learning devices, service, learning place, use age, use times are adapted. As a result of analysis by applying the structural equation model, it was estimated that the reliability of HTML5 service quality, tangibles affect negatively on perceived ease of use, but reliability, assurance, tangibles, empathy, responsiveness of HTML5 service affect positive impacts on perceived usefulness, and also certainty, empathy, responsiveness was identified as positive impacts on the perceived ease of use. It was proven that perceived ease of use effect positive on the perceived usefulness and also usefulness or ease to use have positive effects on the usage intention of users.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.6
• /
• pp.749-756
• /
• 2021

Thanks to PLC and IoT Sensor, huge amounts of data has been accumulated onto the companies' databases. Machine Learning Algorithms for the predictive model with good performance have been widely utilized in the manufacturing process. We present how to improve the performance of machine learning predictive models. To improve the performance of the predictive model, typical techniques such as increasing the sample size, optimizing the hyper parameters for the algorithm, and selecting a proper machine learning algorithm for the predictive model would be shown. We suggest some new ways to make the model performance much better. With the proposed methods, we can build a better predictive model for predicting and controlling product qualities and save incredibly large amount of quality failure cost.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.19-26
• /
• 2020

Steel production requires high-quality surfaces with minimal defects. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. To meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. In this paper, we proposed a ShuffleDefectNet defect detection system based on deep learning. The proposed defect detection system exceeds state-of-the-art performance for defect detection on the Northeastern University (NEU) dataset obtaining a mean average accuracy of 99.75%. We train the best performing detection with different amounts of training data and observe the performance of detection. We notice that accuracy and speed improve significantly when use the overall architecture of ShuffleDefectNet.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.2
• /
• pp.309-323
• /
• 2007

Recently, E-Learning based on wide-area infrastructure is being spotlighted as the new means to innovate education at school and develop human resources at society and appeared as the main point of digital content industry. In this paper, we analyze the characteristics of base technology of E-Learning software and developed E-Learning software quality evaluation model by analyzing quality characteristics for quality test and evaluation of E-Learning software. To do so, we established the quality evaluation system and developed the evaluation model to evaluate the quality about E-Learning software by introducing related international standard. We think that this will promote development of competitive E-Learning software products.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.63-64
• /
• 2022

마스크 착용은 대화나 통화 등의 의사소통에 불편함을 초래하고 음성의 품질과 명료도를 떨어트린다. 이를 해결하기 위해 음성 향상 기술이 필요하며, 머신러닝 기반의 다양한 음성 향상 방법이 개발되었다. 지도 학습을 위해 마스크 착용 유무에 따라 일대일로 대응된 음성 데이터를 확보하는 것은 매우 어렵고, 따라서 일대일로 대응된 데이터가 필수적이지 않은 비지도 학습이 요구된다. 본 논문에서는 비지도 학습방식을 사용하면서 콘텍스트를 유지하며 특징을 변경할 수 있는 CycleGAN을 이용하여 마스크 착용에 의한 음성 왜곡을 복원 시키는 기술을 제안한다. 스펙트로그램 기반으로 마스크 착용에 의해 왜곡된 음성을 마스크 미착용 음성으로 변환하여 음성의 품질을 향상시켰다. 청취평가를 진행한 결과 품질이 향상된 음원의 선호도가 더 높음을 확인하였으며 스펙트로그램을 통해 3 kHz 이상의 고대역 에너지가 증가하는 것을 확인하였다. 이를 통해 CycleGAN을 이용한 비지도 학습으로 마스크 착용에 의해 왜곡된 음성의 품질을 향상시킬 수 있음을 확인하였다.