• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2003년도 봄 학술발표회 논문집
• /
• pp.281-288
• /
• 2003

In karst formation area, the tunnel support system is an important factor for the tunnel safety during operation. This paper presents the simplified tunnel support systems to be adopt in karst formation. For the tunnel planned in the project area, karst features and the expected scenarios in the tunnel area were developed based on the results of the geological and geotechnical assessment. In order to provide specific supporting system and construction details for a wide range of possible karst features, the generalized typical support systems are developed according to the classification of karst features. In addition, the initial support systems and construction sequence for each karst feature are also presented in this paper.

• 한국산학기술학회논문지
• /
• 제9권6호
• /
• pp.1889-1893
• /
• 2008

본 논문은 영상 분류 문제를 위한 support vector machines (SVMs)의 적용을 통한 분류의 성능을 다루고 있다. 본 연구에서는 영상 분류 문제에서 자연영상을 대상으로 색상, 질감, 형상 특징벡터를 추출하고, 각각의 특징벡터와 이들을 결합한 특징벡터를 사용하여 역전파 신경망과 SVM 기반의 방법을 적용하여 영상 분류의 정확성을 비교한다. 실험결과는 각각의 특징벡터중에는 색상 특징벡터값을 이용한 영상 분류가 그리고 각각의 특징벡터보다는 이들을 결합한 특징벡터를 이용한 영상 분류가 보다 우수함을 보여준다. 그리고 알고리즘간의 비교에서는 정확성과 일반화성능 측면에서 역전파 신경망보다 SVMs이 우수함을 보였다.

• KIEAE Journal
• /
• 제9권2호
• /
• pp.27-36
• /
• 2009

Due to rapid advances in science and technology and peoples life value, multi-dimensional functionality of the house has been possible and demanded. Among them, intellectual function and health support function appeared prominent and the former can support the later. The purpose of this study was to delineate health support planning features for smart home. Thirty six planning elements were extracted for initial pool for survey to find out what consumers demanded. Two hundred and nine data were collected through the web-survey. Important planning features were identified in relation to three different health dimensions that is physical/physiological, psychological, and social health. Generally consumers' responses were positive for all features. Major health friendly features highly demanded by consumers were found gas detect system, security system, and a call alarm system. The result of this study is expected to be used as a basic reference to develop strategies for smart home and to grasp current housing culture.

• 정보처리학회논문지B
• /
• 제12B권3호
• /
• pp.365-368
• /
• 2005

본 연구에서는 지지 벡터 기계(Support Vector Machines)를 이용하여 한국어 대화의 화행을 분석하는 방법을 제안한다. 우리는 발화의 어휘 및 품사와 이진 품사 쌍을 문장 자질로 사용하고 이전 발화의 문맥을 문맥 발화로 사용한다. 카이 제곱 통계량을 이용해 적절한 자질을 선택하고 선택된 자질로 지지 벡터 기계를 학습하였다. 학습된 지지 벡터 기계 분류기를 이용하여 각 발화의 화행을 분석하였다. 호텔 예약 영역의 말뭉치에 대해 제안된 시스템을 이용하여 실험한 결과 약 $90.54\%$의 정확률을 얻었다.

• Journal of Information Processing Systems
• /
• 제9권3호
• /
• pp.395-404
• /
• 2013

In order to classify a web page as being benign or malicious, we designed 14 basic and 16 extended features. The basic features that we implemented were selected to represent the essential characteristics of a web page. The system heuristically combines two basic features into one extended feature in order to effectively distinguish benign and malicious pages. The support vector machine can be trained to successfully classify pages by using these features. Because more and more malicious web pages are appearing, and they change so rapidly, classifiers that are trained by old data may misclassify some new pages. To overcome this problem, we selected an adaptive support vector machine (aSVM) as a classifier. The aSVM can learn training data and can quickly learn additional training data based on the support vectors it obtained during its previous learning session. Experimental results verified that the aSVM can classify malicious web pages adaptively.

• 대한기계학회논문집A
• /
• 제34권11호
• /
• pp.1681-1689
• /
• 2010

Support Vector Machine(SVM)을 이용한 회전기계 진단 연구가 많이 수행되어 왔으나 결함 분류성능은 입력 특징과 더불어 다중 분류 방법, 이진분류기, 커널함수 등에 따라 다르다. SVM 을 이용한 대부분의 기존 연구들은 한번 입력 특징들을 선정하면 결함 분류시 동일한 특징데이터를 이용한다. 본 논문에서는 회전기계의 다양한 결함조건에서 측정한 진동신호로부터 추출한 통계적 특징들을 이용하여 각각의 결함을 분류하기 위한 최적 특징들을 선정한 후, 해당 결함상태를 분류하기 위한 SVM 학습과 분류에 각각 이용하였다. 실험자료를 이용한 검증 결과, 제안한 단계 분류 방법이 상대적으로 적은 학습시간으로 단일 다중 분류 방법과 유사한 분류 성능을 얻을 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.153-172
• /
• 2022

In this study, the authors intend to analyze factors contributing to research performance using Backpropagation Neural Network and Support Vector Machine. The analyzing factors contributing to lecturer research performance start from defining the features. The next stage is to collect datasets based on defining features. Then transform the raw dataset into data ready to be processed. After the data is transformed, the next stage is the selection of features. Before the selection of features, the target feature is determined, namely research performance. The selection of features consists of Chi-Square selection (U), and Pearson correlation coefficient (CM). The selection of features produces eight factors contributing to lecturer research performance are Scientific Papers (U: 154.38, CM: 0.79), Number of Citation (U: 95.86, CM: 0.70), Conference (U: 68.67, CM: 0.57), Grade (U: 10.13, CM: 0.29), Grant (U: 35.40, CM: 0.36), IPR (U: 19.81, CM: 0.27), Qualification (U: 2.57, CM: 0.26), and Grant Awardee (U: 2.66, CM: 0.26). To analyze the factors, two data mining classifiers were involved, Backpropagation Neural Networks (BPNN) and Support Vector Machine (SVM). Evaluation of the data mining classifier with an accuracy score for BPNN of 95 percent, and SVM of 92 percent. The essence of this analysis is not to find the highest accuracy score, but rather whether the factors can pass the test phase with the expected results. The findings of this study reveal the factors that have a significant impact on research performance and vice versa.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

• 인지과학
• /
• 제19권4호
• /
• pp.499-517
• /
• 2008

본 논문에서는 한국어 감정 분류에 기반이 되는 감정 자질 추출의 효과적인 추출 방법을 제안하고 평가하여, 그 유용성을 보인다. 한국어 감정 자질 추출은 감정을 지닌 대표적인 어휘로부터 시작하여 확장할 수 있으며, 이와 같이 추출된 감정 자질들은 문서의 감정을 분류하는데 중요한 역할을 한다. 문서 감정 분류에 핵심이 되는 감정 자질의 추출을 위해서는 영어 단어 시소러스 유의어 정보를 이용하여 자질들을 확장하고, 영한사전을 이용하여 확장된 자질들을 번역하여 감정 자질들을 추출하였다. 추출된 한국어 감정 자질들을 평가하기 위하여, 이진 분류 기법인 지지 벡터 기계(Support Vector Machine)를 사용해서 한국어 감정 자질로 표현된 입력문서의 감정을 분류하였다. 실험 결과, 추출된 감정 자질을 사용한 경우가 일반적인 정보 검색에서 사용하는 내용어(Content Word) 기반의 자질을 사용한 경우보다 약 14.1%의 성능 향상을 보였다.

• International Journal of Contents
• /
• 제2권4호
• /
• pp.1-7
• /
• 2006

The goal of Ambient Intelligence (AmI) is to build a smart environment for users where they are supported in some of their activities by many interaction mechanisms. The diversity of AmI characteristics requires special support from Operating Systems (OSes). In this paper, in order to support a conscious choice of an operating system for any specific AmI application, features requested by AmI systems were characterized and defined considering various applications. Then, characteristics of existing Operating Systems have been investigated in the context of AmI application support to relate their key characteristics to the typical requirements of AmI systems. Qualitative mapping table between AmI characteristics and as features has been proposed with an illustration of how to use it. As no as completely covers the range of characteristics required by AmI systems, challenging issues are summarized for the development of a new as and a product line of OSes.