http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Prior Model of Structural SVMs for Domain Adaptation
이창기,Myung-Gil Jang 한국전자통신연구원 2011 ETRI Journal Vol.33 No.5
In this paper, we study the problem of domain adaptation for structural support vector machines (SVMs). We consider a number of domain adaptation approaches for structural SVMs and evaluate them on named entity recognition, part-of-speech tagging, and sentiment classification problems. Finally, we show that a prior model for structural SVMs outperforms other domain adaptation approaches in most cases. Moreover, the training time for this prior model is reduced compared to other domain adaptation methods with improvements in performance.
A Modified Fixed-Threshold SMO for 1-Slack Structural SVMs
이창기,Myung-Gil Jang 한국전자통신연구원 2010 ETRI Journal Vol.32 No.1
In this paper, we describe a modified fixed-threshold sequential minimal optimization (FSMO) for 1-slack structural support vector machine (SVM) problems. Because the modified FSMO uses the fact that the formulation of 1-slack structural SVMs has no bias, it breaks down the quadratic programming (QP) problems of 1-slack structural SVMs into a series of smallest QP problems, each involving only one variable. For various test sets, the modified FSMO is as accurate as existing structural SVM implementations (n-slack and 1-slack SVM-struct) but is faster on large data sets.
Fast Training of Structured SVM Using Fixed-Threshold Sequential Minimal Optimization
이창기,Myung-Gil Jang 한국전자통신연구원 2009 ETRI Journal Vol.31 No.2
In this paper, we describe a fixed-threshold sequential minimal optimization (FSMO) for structured SVM problems. FSMO is conceptually simple, easy to implement, and faster than the standard support vector machine (SVM) training algorithms for structured SVM problems. Because FSMO uses the fact that the formulation of structured SVM has no bias (that is, the threshold b is fixed at zero), FSMO breaks down the quadratic programming (QP) problems of structured SVM into a series of smallest QP problems, each involving only one variable. By involving only one variable, FSMO is advantageous in that each QP sub-problem does not need subset selection. For the various test sets, FSMO is as accurate as an existing structured SVM implementation (SVM-Struct) but is much faster on large data sets. The training time of FSMO empirically scales between O(n) and O(n1.2), while SVM-Struct scales between O(n1.5) and O(n1.8).
Dependency Structure Applied to Language Modeling for Information Retrieval
이창기,장명길,이근배 한국전자통신연구원 2006 ETRI Journal Vol.28 No.3
In this paper, we propose a new language model, namely, a dependency structure language model, for information retrieval to compensate for the weaknesses of unigram and bigram language models. The dependency structure language model is based on the first-order dependency model and the dependency parse tree generated by a linguistic parser. So, long-distance dependencies can be naturally captured by the dependency structure language model. We carried out extensive experiments to verify the proposed model, where the dependency structure model gives a better performance than recently proposed language models and the Okapi BM25 method, and the dependency structure is more effective than unigram and bigram in language modeling for information retrieval.
이창기,임형규,Lee, Chang-Ki,Im, Hyung-Kyu 한국전자통신학회 2012 한국전자통신학회 논문지 Vol.7 No.6
The parking management system can increase driver's convenience with detailed parking information service in the parking lot. At the same time, parking management system consumes non-negligible electrical energy with large amount of sensors, displays and control modules. With the increase in the demand for green and sustainable building design all over the world, it becomes a meaningful issue for parking management system to reduce operating power. This paper presents the preliminary design and estimated results of a parking management system which is optimized to reduce the power consumption mainly on detectors and displays. The system design is based on pre-developed wireless parking detectors, Park Tile and Park Disk. The system has a number of parking space detectors, vehicle count detectors, information displays, guidance terminals and other control units. We have performed system architecture design, communication network design, parking information service scenario planning, battery life regulation and at last operating power estimation. The estimated operating power was 0.93KW per parking-slot, which is 20% of traditional systems. The estimated annual maintenance cost was 18% of traditional systems. 주차관리 시스템은 주차장에서 주차 정보를 제공하여 운전자에게 주차의 편리성을 제공한다. 동시에 다수의 센서, 디스플레이와 제어모듈을 이용하여 아주 소량의 전기 에너지 만을 소모한다. 친환경 빌딩 설계의 요구가 점차 증가함에 따라 주차관리 시스템의 운용 전력 감축 문제가 이슈화 되고 있다. 본 논문에서는 주차관리 시스템의 감지기와 디스플레이 장치의 설계와 소비 전력 감축의 결과를 제시한다. 이 시스템은 무선 Park Tile 과 Park Disk를 사용하여 전력소비를 감축 시키고, 여러 개의 주차 공간 감지기와 자동차 카운터, 정보 디스플레이 장치, 안내 터미널과 제어장치로 구성되어 있다. 그리고 시스템구조 설계와 통신망 설계, 주차 정보 서비스 시나리오 계획, 배터리 수명 제어, 운영전력 평가 등이 수행되었다. 주차장당 운영전력은 0.93KW로 평가 되었으며, 이는 기존 시스템의 20%정도 이고 매년 유지비는 기존 시스템에 비해 18%에 해당된다.