• 방사선산업학회지
• /
• 제17권1호
• /
• pp.11-17
• /
• 2023

Waste generated during the dismantling of nuclear power plants is not only diverse in types such as metal, concrete, soil, but also in a large amount, requiring systematic and efficient management. It is very important to quickly and accurately measure radioactive contamination of wastes generated simultaneously at the decommissioning site, classify them by level, and make decisions so that they can be disposed of in accordance with related laws and regulations. In this paper, for the technical and economic aspects of recycling of radioactive metal waste generated during the dismantling of nuclear power plants, we propose a management system that can measure the radioactive contamination by shape of metal waste at the decommissioning site and automatically classify it according to the presence or absence of contamination. Accordingly, a system for collecting information on metal samples such as weight measurement and shape acquisition of metal waste, measurement of radioactive contamination and identification of nuclides, and an automatic classification system according to radioactivity measurement results were described.

• 한국컴퓨터정보학회논문지
• /
• 제28권4호
• /
• pp.53-63
• /
• 2023

과학기술 문헌을 활용한 계량정보분석에서 학과정보의 활용은 매우 유용하다. 본 논문에서는 국내 과학기술 분야 학술지 논문에 출현하는 대학기관 소속 저자의 학과정보 선별, 데이터 정제와 학과유형 분류 처리 과정을 통해 학과정보 데이터셋을 구축하고 학습데이터와 검증데이터로 이용하여 딥러닝 기반의 자동분류 모델을 구현하였다. 또한 학과정보 데이터셋과 국내 학술지 저자소속 정보를 활용하여 컴퓨터 분야의 공저 구성 현황과 네트워크를 분석하였다. 연구결과, 자동분류 모델은 한글 학과정보 기준 98.6% 정확률을 보였으며 컴퓨터 분야 연구자들의 공저 패턴과 기관유형, 지역, 기관, 학과유형 측면별 공저 네트워크의 속성과 중심성이 자세히 파악되고 맵으로 시각화되었다.

• 전기전자학회논문지
• /
• 제18권4호
• /
• pp.536-543
• /
• 2014

Terrain classification is still a challenging issue in image processing, especially with high resolution satellite images. The well-known obstacles include low accuracy in the detection of targets, especially for the case of man-made structures, such as buildings and roads. In this paper, we present an efficient approach to classify and detect building footprints, foliage, grass and road from high resolution grayscale satellite images. Our contribution is to build a strong classifier using AdaBoost based on a combination of co-occurrence and Haar-like features. We expect that the inclusion of Harr-like feature improves the classification performance of the man-made structures, since Haar-like feature is extracted from corner features and rectangle features. Also, the AdaBoost algorithm selects only critical features and generates an extremely efficient classifier. Experimental result indicates that the classification accuracy of AdaBoost classifier is much higher than that of the conventional classifier using back propagation algorithm. Also, the inclusion of Harr-like feature significantly improves the classification accuracy. The accuracy of the proposed method is 98.4% for the target detection and 92.8% for the classification on high resolution satellite images.

• 한국산업정보학회논문지
• /
• 제13권5호
• /
• pp.22-28
• /
• 2008

본 논문에서는 전자정부 시스템의 대 국민 사용성과 효율성을 증진시키기 위한 의미기반 문서 분류 방법(CoWDC)을 제시한다. 기존 의미기반 문서분류 방법에서 많은 양의 키워드들의 계층적 컨셉들을 이용하는 것을 지양하고 사용자들이 사용하는 키워드들 간의 관계를 중심으로 문서를 분류한다. 즉, 문서의 컨텍스트(context)에 근거하여 깊고 정확한 의미를 키워드 간 관계를 분석하여 적은 양의 정보로 효율적인 문서분류를 하게 된다. 이를 위해 제안한 CoWDC(Concept Wright Document Classification) 시스템은 기존의 시소러스/온톨로지의 의존도를 줄이고 키워드 관계, 관계의 경중 고려, 상하위 개념으로 변환 등을 통한 실험과 평가가 이루어졌다. 전자정부 시스템의 구조 및 특징 분석을 통해 CoWDC 실험 결과는 대국민 서비스 향상을 위해 매우 필요함을 인지하고 이를 접목하기 위한 기술적, 정책적 제언을 제시하였다. CoWDC를 통해 의미기반 검색기술의 우수함을 입증하였고 이는 전자정부 시스템의 지식베이스 구축, 운영체제의 운용, 시소러스의 구성 등의 과정에서 체계적으로 통합 운영되어야 한다.

• 대한안전경영과학회지
• /
• 제16권1호
• /
• pp.213-220
• /
• 2014

This study suggests new approach to identify core technologies through patent analysis. Specially, the approach applied data mining technique and multi-criteria decision making method to the co-classification information of registered patents. First, technological interrelationship matrices of intensity, relatedness, and cross-impact perspectives are constructed with support, lift and confidence values calculated by conducting an association rule mining on the co-classification information of patent data. Second, the analytic network process is applied to the constructed technological interrelationship matrices in order to produce the importance values of technologies from each perspective. Finally, data envelopment analysis is employed to the derived importance values in order to identify priorities of technologies, putting three perspectives together. It is expected that suggested approach could help technology planners to formulate strategy and policy for technological innovation.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 춘계 학술발표회
• /
• pp.999-1008
• /
• 2009

A series of sedimentary rocks which are formed in the Tertiary are distributed around Samcheok(Samcheok-Pukpyoung basin), Younghae(Younghae basin), Pohang(Pohang basin), Gyeongju(Yangnam basin), Ulsan(Ulsan basin), Jeju(Seogyuipo formation) in the southern region of the Korean Peninsula. This study concerned with geological, geophysical, geotechnical properties of the unconsolidated rocks in the Pohang area. A consolidated rocks are classified as hard rock - soft rock - weathered rock - residual soil follows in degree of weathering. But unconsolidated rocks has soil properties as well as rock's at the same time. The results of field excursion, boring, borehole-logging, rock testing, geophysical survey, laboratory test are soft rock range, but the durability of the rock until the residual soil from the weathered rock. We accomplished the rock mass classification of the unconsolidated rocks.

• 한국컴퓨터정보학회논문지
• /
• 제21권5호
• /
• pp.79-89
• /
• 2016

In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.

• 대한공간정보학회지
• /
• 제22권3호
• /
• pp.155-160
• /
• 2014

본 논문에서는 각기 다른 3가지 해상도로 촬영된 항공 초분광영상을 이용하여 건물, 도로, 산림 등 8가지 분류군에 대해 토지피복분류를 실시하고 정확도를 비교하는 연구를 수행하였다. 연구는 24밴드(0.5m 공간해상도), 48밴드(1.0m 공간해상도), 96밴드(1.5m 공간해상도)로 각각 1000m, 2000m, 3000m고도에서 촬영된 초분광영상을 이용하여 8가지 클래스에 대해 토지피복분류를 수행하였다. 그 결과 2000m고도에서 촬영된 48밴드 초분광영상을 이용하여 분류한 영상이 가장 높은 분류정확도를 보였고, 24밴드, 96밴드 순으로 분류정확도가 높게 나타났다. 초분광영상 활용에 있어서 1m 공간해상도에 48개밴드를 사용하여 토지피복분류를 수행함에 있어 적합함을 확인하였고 항공 초분광영상을 활용한 주제도 제작과 관련하여 정확도와 실용성 면에서 공간정보 품질이 개선될 것으로 기대한다.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1998년도 추계학술발표회요약집
• /
• pp.125-125
• /
• 1998

• 대한원격탐사학회지
• /
• 제25권3호
• /
• pp.255-261
• /
• 2009

A new polarimetric SAR image classification technique based on the degree of polarization (DoP) and the co-polarized phase-difference (CPD) is presented in this paper. Since the DoP and the CPD of a scattered wave provide information on the randomness of the scattering and the type of scattering mechanisms, at first, the statistics of the DoP and CPD are examined with measured polarimetric SAR image data. Then, a DoP-CPD diagram with appropriate boundaries between six different classes is developed based on the SAR image. The classification technique is verified using the JPL AirSAR and ALOS PALSAR polarimetric data. The technique may have capability to classify an SAR image into six major classes; a bare surface, a village, a crown-layer short vegetation canopy, a trunk-layer short vegetation canopy, a crown-layer forest, and a trunk-dominated forest.