• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.561-568
• /
• 2023

Various defects occur in concrete structures due to internal and external environments. If there is a defect, it is important to efficiently identify and maintain it because there is a problem with the structural safety of concrete. However, recent deep learning research has focused on cracks in concrete, and studies on exfoliation and contamination are lacking. In this study, focusing on exfoliation and contamination, which are difficult to label, four models were developed and their performance evaluated through unlabelling method, filtering method, the convergence of transfer learning based k-means clustering. As a result of the analysis, the convergence model classified the defects in the most detail and could increase the efficiency compared to direct labeling. It is hoped that the results of this study will contribute to the development of deep learning models for various types of defects that are difficult to label in the future.

• Journal of the Korean Solar Energy Society
• /
• v.39 no.6
• /
• pp.1-13
• /
• 2019

With the adoption of the Paris Agreement, a new climate regime is intensifying the global interest in reducing greenhouse gas emissions. In the meantime, Korea is preparing to introduce a new renewable energy carbon certification system in order to activate the use of renewable energy and to reduce carbon emissions in the entire life cycle of manufacturing and disposal of renewable energy facilities. Therefore, this study aims to identify the implications for the introduction of the carbon certification system and to establish a theoretical basis for the system design by examining the status of overseas carbon certification, international trade norms and trade disputes. As a result, carbon emissions certification is being implemented in developed countries such as EU, UK, France, USA and Japan, but only France, Germany and EU have adopted carbon certification for renewable energy sector. The analysis of the WTO TBT Agreement and GATT also confirmed the possibility of a violation of the international trade rules of the carbon certification system and derived nine international technical standards related to carbon certification. Finally, by examining the case of trade disputes related to environmental labeling, the minimum requirements to be considered at the institutional design stage were drawn to eliminate the possibility of trade disputes.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.99-104
• /
• 1998

한국어의 자연스러운 음성합성을 위해 280문장에 대하여 남성화자 1명이 발성한 문음성 데이터를 음운 세그먼트, 음운 라벨링, 음운별 품사 태깅하여 음성 코퍼스를 구축하였다. 이 문 음성 코퍼스를 사용하여 음운환경, 품사 뿐만 아니라 구문 구조에 이하여 음운으 lwlthrtlrks이 어떻게 변화하는가에 대하여 xhdrPwjrdfmh 분석하였다. 음운 지속시간을 보다 정교하게 예측하기 위하여, 각 음운의 고유 지속시간의 영향이 배제된 정규화 음운지속시간을 회귀트리를 이용하여 모델화하였다. 평가결과, 기존의 회귀트리를 이용한 음운지속시간 모델에 의한 예측오차는 87%정도가 20ms 이내 이었지만, 정규화 음운 지속시간 모델에 의한 예측 오차는 89% 정도가 20ms 이내로 더욱 정교하게 예측되었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.389-392
• /
• 2010

In this paper, it presents to detect location using structural information of hand from the input color images on Webcam and to recognize hand gestures. In this system, based on the skin color, the image changes a binary number and labels. Within each labeled area, we can find the Maximum Inscribed Circle using Voronoi Diagram. This circle can find the center of hand. And the circle extracts hand region from analyzing the ellipse elements to relate Maximum Inscribed Circle. We use the Maximum Inscribed Circle and the ellipse elements as characteristic of hand gesture recognition. In various environments, we cannot recognize the object that have similar colors like the background colors. But the proposed algorithm has the advantage that can be effectively eliminated about it.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.17-28
• /
• 2023

Potholes that occur on paved roads can have fatal consequences for vehicles traveling at high speeds and may even lead to fatalities. While manual detection of potholes using human labor is commonly used to prevent pothole-related accidents, it is economically and temporally inefficient due to the exposure of workers on the road and the difficulty in predicting potholes in certain categories. Therefore, completely preventing potholes is nearly impossible, and even preventing their formation is limited due to the influence of ground conditions closely related to road environments. Additionally, labeling work guided by experts is required for dataset construction. Thus, in this paper, we utilized the Mean Teacher technique, one of the semi-supervised learning-based knowledge distillation methods, to achieve robust performance in pothole image classification even with limited labeled data. We demonstrated this using performance metrics and GradCAM, showing that when using semi-supervised learning, 15 pre-trained CNN models achieved an average accuracy of 90.41%, with a minimum of 2% and a maximum of 9% performance difference compared to supervised learning.

• Journal of Korean Society for Quality Management
• /
• v.23 no.4
• /
• pp.180-189
• /
• 1995

Today, as globalization continues and international trading blocks are formed, world markets are intensely competitive and abound in product variety, volume, complexity and environmental management. Specifically, green consumer's needs and expectations are changing and diversifying, resulting in a changed global environment for industry. Due to these changes, domestic companies are striving to achieve the Environmental Management System (ISO 14000) certification. This is considered a basis step in meeting the guiding principle and practice of ISO/TC 207/SC 3 resolution. In this paper, we will present three type(I, II, III) of Environmental Labelling programs to build a model for environmental management system by analysing practitioner and stakeholder. After companies establish an ISO 9000 quality system these companies should focus on improve toward their own Environmental Labelling program and continue to build ISO 14000.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1336-1338
• /
• 2022

폐기물 관리는 전 세계적으로 환경, 사회, 경제 문제를 일으키고 있다. 이러한 문제를 예방하고자 폐기물을 효율적으로 관리하기 위해, 인공지능을 통한 연구를 제안하고 있다. 따라서 본 논문에서는 GAN 기반 데이터 증강을 통한 폐기물 객체 인식모델을 제안한다. Open Images Dataset V6와 AI Hub의 공공 데이터 셋을 융합하여 폐기물 품목에 해당하는 이미지들을 정제하고 라벨링한다. 이때, 실제 배출환경에서 발생할 수 있는 장애물로 인한 일부분만 노출된 폐기물, 부분 파손, 눕혀져 배출, 다양한 색상 등의 인식저해요소를 모델 학습에 반영할 수 있도록 일반적인 데이터 증강과 GAN을 통한 데이터 증강을 병합 사용한다. 이후 YOLOv4 기반 폐기물 이미지 인식 모델 학습을 진행하고, 학습된 이미지 인식 모델에 대한 검증 및 평가를 mAP, F1-Score로 진행한다. 이를 통해 향후 스마트폰 애플리케이션과 융합하여 효율적인 폐기물 관리 체계를 구축할 수 있을 것이다.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.856-858
• /
• 2024

VR 기술의 발전은 다양한 분야에서 사용자에게 몰입감 있는 가상 현실 경험을 제공하지만, VR기기 내부에 사용자의 생체 데이터 및 금융정보와 같은 민감한 정보들이 저장되어 새로운 보안 문제를 야기하고 있다. 이에 따라 PIN, 패스워드 등과 같은 기존의 인증 방식이 VR 기기에 적용되고 있지만 이들은 shoulder-surfing attack 공격 취약하며 VR 환경에서 사용하기에 불편한 인터페이스를 가지고 있다. 따라서 본 논문에서는 이상 탐지 모델을 활용하여 외부 추론 공격에 강인하며 VR 환경에 적합한 사용자 행위 기반의 VR기기 사용자 인증 모델을 구현한다. 특정 task를 수행하는 동안 사용자의 행위 데이터를 수집 및 feature 데이터를 추출하고, 정상으로 라벨링 된 사용자의 데이터로 이상 탐지 머신러닝 모델들을 학습 후 정상 데이터와 비정상 데이터를 이용하여 인증 모델의 성능을 평가하였다. OC-SVM이 87.72%의 F1-score로 세 모델 중 가장 높은 성능을 보임을 확인하였으며, 향후 인증 모델 성능 향상을 위한 계획을 제시하였다.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.918-919
• /
• 2024

현재 환경 문제는 인류의 생존을 위협할 정도로 매우 심각하다. 올바른 분리수거는 매립 및 소각하는 폐기물 양을 줄이고 자원을 재활용하여 자원 절약에 기여할 수 있다. 그러나 생활 폐기물의 올바른 분리수거가 이루어지고 있다고 보기 어렵다. 이러한 문제를 해결하기 위해, 폐기물의 이미지를 통해 분리수거 방법을 안내하는 AI 기반 시스템을 개발했다. 본 연구에서는 폐기물 객체를 정확하게 탐지하기 위해 YOLO 기반의 객체 탐지 알고리즘을 사용하였으며, 이미지 인식의 정확도를 높이기 위해 학습 데이터셋으로 직접 라벨링한 커스텀 데이터셋을 활용하였다. 본 연구를 통해 올바른 분리수거 실천률을 향상시키고, 환경 보호와 지속 가능한 사회를 만드는 데 기여할 수 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.8
• /
• pp.4987-4998
• /
• 2014

Recently, the use of nanotechnology in products is constantly expanding, and the problems on human health hazard has emerged as a major issue. A nanomaterials regulatory policy on the products is urgently required. This study analyzed the introduction of regulatory policies of nanomaterials contained in industrial products. In this study, the AHP (Analytic Hierarchy Process) method was applied and three regulatory policies were evaluated to analyze the validity of the introduction of a nanomaterials regulatory policy. To select the optimal regulatory policy, the policy evaluation criteria were set as enforcement (effectiveness), economics, acceptability, and protection. For the regulatory policies, self-regulation, product labelling, and enforced registration were introduced and evaluated as the regulatory policies, and product labelling was selected as the optimal regulatory policy.