• 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 Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.109-113
• /
• 2002

In this paper, we propose a new intrusion detection algorithm based on clustering: Kernel-ART, which is composed of the on-line clustering algorithm, ART (adaptive resonance theory), combining with mercer-kernel and concept vector. Kernel-ART is not only satisfying all desirable characteristics in the context of clustering-based 105 but also alleviating drawbacks associated with the supervised learning IDS. It is able to detect various types of intrusions in real-time by means of generating clusters incrementally.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.459-461
• /
• 1992

This paper presents the new method to recognize the 2D patterns dynamically by rotating the input patterns according to the difference vector. Generally neural network with many patterns leads to various recognition ratio. The dynamic management of input patterns means that we can move pixels to desired locations controlled by the difference vector. We divide dual neural network model into two parts at learning phase, respectively. And then we combine them to construct the total network. Our model has some good results such that it has less number of patterns and reduced learning time. At present, we only discuss the four way movement of input patterns. The research for the complex movement will be fulfilled later.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.9
• /
• pp.1363-1368
• /
• 2015

Recently, computer form were smaller than before because of computing technique's development and many wearable device are formed. So, computer's cognition of human emotion has importantly considered, thus researches on analyzing the state of emotion are increasing. Human voice includes many information of human emotion. This paper proposes a discriminative feature vector selection for emotion classification based on speech. For this, we extract some feature vectors like Pitch, MFCC, LPC, LPCC from voice signals are divided into four emotion parts on happy, normal, sad, angry and compare a separability of the extracted feature vectors using Bhattacharyya distance. So more effective feature vectors are recommended for emotion classification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.12
• /
• pp.4624-4642
• /
• 2014

Image compression is a popular research issue that focuses on the problems of reducing the size of multimedia files. Vector Quantization (VQ) is a well-known lossy compression method which can significantly reduce the size of a digital image while maintaining acceptable visual quality. A locally adaptive scheme (LAS) was proposed to improve the compression rate of VQ in 1997. However, a LAS needs extra indicators to indicate the sources, consequently the compression rate of LAS will be affected. In this paper, we propose a novel method to eliminate the LAS indicators and so improve the compression rate. The proposed method uses the concept of data hiding to conceal the indicators, thus further improving the compression rate of LAS. From experimental results, it is clearly demonstrated that the proposed method can actually eliminate the extra indicators while successfully improving the compression rate of the LAS.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.133-138
• /
• 2008

In this paper, we propose a novel anchor shot detection system, named to MASD (Multi-phase Anchor Shot Detection), which is a core step of the preprocessing process for the news video analysis. The proposed system is composed of four modules and operates sequentially: 1) skin color detection module for reducing the candidate face regions; 2) face detection module for finding the key-frames with a facial data; 3) vector representation module for the key-frame images using a non-negative matrix factorization; 4) one class SVM module for determining the anchor shots using a support vector data description. Besides the qualitative analysis, our experiments validate that the proposed system shows not only the comparable accuracy to the recently developed methods, but also more faster detection rate than those of others.

• Proceedings of the KIEE Conference
• /
• 2000.07b
• /
• pp.1053-1055
• /
• 2000

This paper describes a new approach to estimating permanent magnet synchronous motor(PMSM) speed and position from measured terminal voltages and currents for speed-sensorless vector control. The proposed system is based on observing the instantaneous reactive power of the motor. The described technique is very simple and robust to variations of motor parameters. The new approach is not dependent upon the value of the stator resistance. Also, MRAS schemes are chosen for determining the adaptive law for the speed and the position estimator. The effectiveness is verified by simulation.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.01a
• /
• pp.19-20
• /
• 2016

본 논문에서는 서포트 벡터 머신 (SVM)의 분류 성능에 영향을 주는 인수인 C와 ${\sigma}$ 값을 적응적으로 최적화할 수 있는 적응적 자가튜닝 SVM을 이용한 베어링의 상태 진단 방법을 제안한다. SVM의 각 인수의 변화에 따른 베어링 상태 진단의 성능 변화 패턴을 분석하여 적합한 인수를 적응적으로 찾을 수 있는 방법을 제안하고, 제안한 방법의 우수성을 검증하기 위해 실제 베어링 신호를 이용하여 기존방법인 격자탐색과의 성능을 비교하였다.

• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.37-41
• /
• 2011

본 논문에서는 최근 많은 관심을 받고 있는 Opinion Mining으로서 사용자들의 자연어 형태의 영화평 문장을 분석하여 자동으로 평점을 예측하는 시스템을 제안한다. 제안 시스템은 영화평 분석에 적합한 어휘 자질, 감정 자질, 가치 자질 및 기타 자질들을 추출하고, 10점 척도의 영화평의 평점을 10개의 범주로 가정하여, 커널모델인 다중 범주 Support Vector Machine (SVM) 모델을 이용하여 높은 성능으로 영화평의 평점을 범주 분류한다.

• Journal of Power Electronics
• /
• v.10 no.2
• /
• pp.146-154
• /
• 2010

In this paper two dual output current-type inverters are proposed. These inverters have been called a current source nines-witch inverter and a current-type z-source nine-switch inverter by the authors. The proposed inverters have two independent current source outputs. Compared to two independent current source inverters, the proposed converters are implemented with fewer semiconductor switches. Space vector modulation (SVM) is proposed for these converters. Simulation results show the validity and performance of the proposed inverters.