• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2013.05a
• /
• pp.249-251
• /
• 2013

The government has applied the Construction New Excellent Technology Endorsement System to enhance national competitiveness and advance domestic construction technology since 1989. Nevertheless, It's application hasn't been expanded to overall construction industry, due to insufficient verification of the cost effectiveness. So, the government has established the standardized cost estimation guideline to verify the cost effectiveness in 2011. This research classified the technology group based on 27 cases of the cost estimation reports to increase understanding of the cost effectiveness of the new excellent technology. It is expected to contribute establishing reasonable and feasible cost estimation standards.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.6
• /
• pp.509-519
• /
• 2007

This paper presents new techniques under development for monitoring the health and vibration of the active components in nuclear power plants, The purpose of this study is to develop an automated system for condition classification of a check valve one of the components being used extensively in a safety system of a nuclear power plant. Acoustic emission testing for a check valve under controlled flow loop conditions was performed to detect and evaluate disc movement for valve failure such as wear and leakage due to foreign object interference in a check valve, It is clearly demonstrated that the evaluation of different types of failure types such as disc wear and check valve leakage were successful by systematically analyzing the characteristics of various AE parameters, It is also shown that the leak size can be determined with an artificial neural network.

• Journal of Information Technology Services
• /
• v.7 no.4
• /
• pp.179-198
• /
• 2008

It is widely known that usability is a critical quality attribute of IT systems. Many studies have developed various methods for finding out usability problems. Usability professionals have emphasized that usability should be integrated into the development life cycle in order to maximize the usability of systems with minimal cost. To achieve this, it is essential to classify usability problems systematically and connect them into the activities of designing user interfaces and tasks. However, there is a lack of framework or method for these two problems and thus remains a challengeable research issue. As a beginning study, this paper proposes a conceptual framework for addressing the two issues. We firstly summarize usability-related studies so far, including usability factors and evaluation methods. Secondly, we review seven approaches to identifying and classifying usability problems. Based on this review and opinions of usability engineers in real industry as well as the review results, this paper proposes a framework comprising three viewpoints, from which more sound classification scheme of usability problems can be inductively developed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.33-34
• /
• 2019

대부분의 나라에서는 어선의 위치발신장치를 이용하여 어선 조업상황을 모니터링 한다. 우리나라도 어선의 위치발신장치를 이용하여 어선 조업량, 불법조업 유무를 판별한다. 현재까지는 어선의 불법조업 유무 판별은 어선의 위치정보 기반으로 이루어 졌으나, 허가받지 않는 어구를 사용하는 불법조업에 대한 판별은 불가능 하였다. 이에 본 논문에서는 어선 항적과 조업면허 데이터를 이용하여 데이터 기반의 어선 조업 판별모델을 개발하고자 한다. 이를 위해 어선 항적데이터를 시계열 단위로 전처리하여 학습 이미지들을 생성하고, 해당 어선의 조업면허 정보를 레이블로 하여 학습 데이터를 제안하는 딥러닝 모델에 적용한다. 제안하는 방법의 검증을 위해 1년 동안 제주 주변해역에서 조업하는 어선의 선박자동식별장치의 항적데이터를 수집하여 실험을 하였다. 실험 결과 제안한 방법의 분류정확도는 71.5%를 얻었다.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1167-1174
• /
• 2022

Cast austenitic stainless steels (CASSs) are widely used as structural materials in the nuclear industry. The main drawback of CASSs is the reduction in fracture toughness due to long-term exposure to operating environment. Even though ultrasonic non-destructive testing has been conducted in major nuclear components and pipes, the detection of cracks is difficult due to the scattering and attenuation of ultrasonic waves by the coarse grains and the inhomogeneity of CASS materials. In this study, the ultrasonic signals measured in thermally aged CASS were discriminated for the first time with the simple ultrasonic technique (UT) and machine learning (ML) models. Several different ML models, specifically the K-nearest neighbors (KNN), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) models, were used to classify the ultrasonic signals as thermal aging condition of CASS specimens. We identified that the ML models can predict the category of ultrasonic signals effectively according to the aging condition.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.1383-1387
• /
• 2009

As information technologies in construction field get developed, various studies and projects are in progress for improvement of construction industry. Meanwhile, web-basis online system for building materials is tending upward. However, most of the informations about classification system for building materials and specifications are not systematic yet. Most field staffs have some troubles in making full use of the material information, repeating inefficient works from constructional design to the maintenance of it. This study designed auto-categorization system classified by materials, multi-search engines, auto-converting/creating electronic catalog as well as RFID search support to provide standardized building materials information.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.43-44
• /
• 2022

기존 자연어 처리 모델은 문맥 단위 단어 임베딩을 처리하지 못하는 한계점을 가지고 있는 한편 최근 BERT 기반 사전학습 모델들은 문장 단위 임베딩이 가능하고 사전학습을 통해 학습 효율이 비약적으로 개선되었다는 특징이 있다. 본 논문에서는 사전학습 언어 모델들을 이용하여 음식점, 배달전문점 등 음식 업종에서 발생한 고객 발화 의도를 분류하고 모델별 성능을 비교하여 최적의 모델을 제안하고자 한다. 연구결과, 사전학습 모델의 한국어 코퍼스와 Vocab 사이즈가 클수록 고객의 발화 의도를 잘 예측하였다. 한편, 본 연구에서 발화자의 의도를 크게 문의와 요청으로 구분하여 진행하였는데, 문의와 요청의 큰 차이점인 '물음표'를 제거한 후 성능을 비교해본 결과, 물음표가 존재할 때 발화자 의도 예측에 좋은 성능을 보였다. 이를 통해 음식 업종에서 발화자의 의도를 예측하는 시스템을 개발하고 챗봇 시스템 등에 활용한다면, 발화자의 의도에 적합한 서비스를 정확하게 적시에 제공할 수 있을 것으로 기대한다.

• The Journal of Fisheries Business Administration
• /
• v.53 no.4
• /
• pp.51-67
• /
• 2022

The Korean tariff rate for fishery products is a single tax rate of 10% for live fish and frozen seafood, and 20% for all others. Since FTAs have been concluded with several countries, the tariffs is not an appropriate means to protect domestic fishery producers. The differential tariff rate according to the scientific name (genus) of the fishery products, which was implemented 30 years ago to protect fishery products produced in the Korean coastal waters has lost its original purpose. It seems that future fishery trade policy should focus on IUU prevention, hygiene and safety of consumers rather than protecting fishery producers through customs tariffs. This paper suggest that a paradigm shift in the fishery producers protection policies such as direct financial support from the state, protection and development of fishery resources, and support for fostering the 6th industry rather than indirect protection through tariffs.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.714-716
• /
• 2020

We propose a unique client-driven music genre classification solution, that can identify the music genre using a deep convolutional neural network operating on the time-domain signal. The proposed method uses the client device (Jetson TX2) computational resources to identify the music genre. We use the industry famous GTZAN genre collection dataset to get reliable benchmarking performance. HTTP live streaming (HLS) client and server sides are designed locally to validate the effectiveness of the proposed method. HTTP persistent broadcast connection is adapted to reduce corresponding responses and network bandwidth. The proposed model can identify the genre of music files with 97% accuracy. Due to simplicity and it can support a wide range of client hardware.

• Biomolecules & Therapeutics
• /
• v.30 no.2
• /
• pp.179-183
• /
• 2022

Traditionally, pathologists microscopically examine tissue sections to detect pathological lesions; the many slides that must be evaluated impose severe work burdens. Also, diagnostic accuracy varies by pathologist training and experience; better diagnostic tools are required. Given the rapid development of computer vision, automated deep learning is now used to classify microscopic images, including medical images. Here, we used a Inception-v3 deep learning model to detect mouse lung metastatic tumors via whole slide imaging (WSI); we cropped the images to 151 by 151 pixels. The images were divided into training (53.8%) and test (46.2%) sets (21,017 and 18,016 images, respectively). When images from lung tissue containing tumor tissues were evaluated, the model accuracy was 98.76%. When images from normal lung tissue were evaluated, the model accuracy ("no tumor") was 99.87%. Thus, the deep learning model distinguished metastatic lesions from normal lung tissue. Our approach will allow the rapid and accurate analysis of various tissues.