• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.470-480
• /
• 2006

The longer the input sentences, the worse the parsing results. To improve the parsing performance, many methods about long sentence segmentation have been reserarched. As an isolating language, Chinese sentence has fewer cues for sentence segmentation. However, the average frequency of comma usage in Chinese is higher than that of other languages. The syntactic information that the comma conveys can play an important role in long sentence segmentation of Chinese languages. This paper proposes a method for classifying commas in Chinese sentences according to the context where the comma occurs. Then, sentences are segmented using the classification result. The experimental results show that the accuracy of the comma classification reaches 87.1%, and with our segmentation model, the dependency parsing accuracy of our parser is improved by 5.6%.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.936-947
• /
• 2005

In dependency parsing of long sentences with fewer subjects than predicates, it is difficult to recognize which predicate governs which subject. To handle such syntactic ambiguity between subjects and predicates, this paper proposes an 'S-clause' segmentation method, where an S(ubject)-clause is defined as a group of words containing several predicates and their common subject. We propose an automatic S -clause segmentation method using decision trees. The S-clause information was shown to be very effective in analyzing long sentences, with an improved parsing performance of 5 percent. In addition, the performance in detecting the governor of subjects was improved by $32\%$.

• Annual Conference on Human and Language Technology
• /
• 2003.10d
• /
• pp.261-266
• /
• 2003

문장이 길면 구문분석의 정확률이 크게 낮아진다. 따라서 장문을 분할하여 분석하면 구문분석의 복잡도를 크게 줄일 수 있어 정확률 향상에 크게 기여할 수 있다. 특히, 중국어는 고립어로서, 교착어나 융합어와 비교할 때 자연어처리에 도움을 줄 수 있는 굴절이나 어미정보가 없어 구문분석에 어려움이 더욱 많다. 반면, 중국어 문자에서는 쉼표를 비교적 많이 사용하고 있고 또한 쉼표의 쓰임이 정확하므로 구문 분석에 도움을 줄 수 있다. 본 논문에서는 쉼표가 많이 쓰이고 있는 중국어 문장에서 해당 쉼표위치 문장 분할가능여부를 Support Vector Machine을 이용 판단하여 정확률 88.61%의 높은 분할 성능을 보였다.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1998.05a
• /
• pp.99-105
• /
• 1998

육각형구조에서 중성자 확산방정식의 해를 구하기 위해 육각형을 3개의 사각형으로 분할하여 노달해를 구하는 방법을 개발하였다. 이 방법은 기존의 사각형 노달기법의 기본적인 틀을 그대로 이용할 수 있기 때문에 육각형을 직접 푸는 방법에 비해 간단하며, 향후 노드의 세분화 및 다군 확산방정식에 적용하기 쉬운 장점을 가지고 있다. 이러한 사각형분할에 의한 육각형 노달해를 구하는 방법을 2차원 IAEA 벤치마크 계산을 통해 검증해 본 결과, 정확성이 잘 유지되고 있음을 알 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.3A
• /
• pp.443-450
• /
• 2000

Although designing a virtual topology for all-optical WDM wide-area networks has been extensively studied and several algorithms have been proposed, these algorithms assumed error-free communication between two nodes. However, noises from optical amplifiers and optical cross-connects can degraded the signal, resulting in a nonzero bit-error rate. In this paper, we investigate the effect of physical limitations on the virtual topology design. We show that for side-area all-optical networks where transmission distance is fairly long, virtual topology design algorithm that can determine the locations of opto-electronic(OE) and electro-optic(EO) conversions to set up a connection request with a high BER in a multihop manner.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.561-563
• /
• 2000

최근 인터넷에 대한 수요의 증가로 인해 데이터 트래픽이 음성 트래픽을 초과하는 단계로 이르고 있으며 또한 이동통신 가입자의 급증으로 인한 트래픽도 상당한 것으로 알려져 있다. 이렇게 폭증하는 망에 대한 요구를 수용하기 위해서는 단순히 광섬유를 추가로 설치하기 보다는 기존의 광섬유를 최대한 활용할 수 있어야 한다. 이를 위해 WDM 방식 광통신 시스템이 각광받고 있다. 본 연구에서는 우리나라의 실정에 적합한 트래픽을 모델링하기 위한 Pl(Population- Information factor) 트래픽 모델링 기법을 제시하며 이에 기초하여 도출된 트래픽 값으로 WBM을 수용하는 전력통신망 모델을 설계한다. 전력통신망 설계와 특성 분석을 위하여 Visual C로 시뮬레이션 툴을 개발하였으며, 본 결과는 향후 WDM을 수용한 전광전송망을 구축할 때 활용될 수 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.169-174
• /
• 2008

Recently, biometric systems are of interest for the reliable security system. Iris recognition technology is one of the biometric system with the highest reliability. Various iris recognition methods have been proposed for automatic personal identification and verification. These methods require accurate iris segmentation for successful processing because the iris is a small part of an acquired image. The iris boundaries have been parametrically modeled and subsequently detected by circles or parabolic arcs. Since the iris boundaries have a wide range of edge contrast and irregular border shapes, the assumption that they can be fit to circles or parabolic arcs is not always valid. In some cases, the shape of a dilated pupil is slightly different from a constricted one. This is especially true when the pupil has an irregular shape. This is why this research is important. This paper addresses how to accurately detect iris boundaries for improved iris recognition, which is robust to noises.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.8
• /
• pp.2061-2074
• /
• 1998

In pattern recognition and image analysis upplications, a graph is a useful tool for complex obect representation and recognition. However it takes much time to pair proper nodes between the prototype graph and an input data graph. Futhermore it is difficult to decide whether the two graphs in a class are the same hecause real images are degradd in general by noise and other distortions. In this paper we propose a matching algorithm using a matrix. The matrix is suiable for simple and easily understood representation and enables the ordering and matching process to be convenient due to its predefined matrix manipulation. The nodes which constitute a gaph are ordered in the matrix by their geometrical positions and this makes it possible to save much comparison time for finding proper node pairs. for the classification, we defined a distance measure thatreflects the symbo's structural aspect that is the sum of the mode distance and the relation distance; the fornet is from the parameters describing the node shapes, the latter from the relations with othes node in the matrix. We also introduced a subdivision operation to compensate node merging which is mainly due t the prepreocessing error. The proposed method is applied to the recognition of musteal symbols and the result is given. The result shows that almost all, except heavily degraded symbols are recognized, and the recognition rate is approximately 95 percent.