• Journal of KIISE:Software and Applications
• /
• v.32 no.5
• /
• pp.385-395
• /
• 2005

Long sentence analysis has been a critical problem in machine translation because of high complexity. The methods of intra-sentence segmentation have been proposed to reduce parsing complexity. This paper presents the intra-sentence segmentation method based on maximum entropy probability model to increase the coverage and accuracy of the segmentation. We construct the rules for choosing candidate segmentation positions by a teaming method using the lexical context of the words tagged as segmentation position. We also generate the model that gives probability value to each candidate segmentation positions. The lexical contexts are extracted from the corpus tagged with segmentation positions and are incorporated into the probability model. We construct training data using the sentences from Wall Street Journal and experiment the intra-sentence segmentation on the sentences from four different domains. The experiments show about $88\%$ accuracy and about $98\%$ coverage of the segmentation. Also, the proposed method results in parsing efficiency improvement by 4.8 times in speed and 3.6 times in space.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.93-100
• /
• 2009

In this paper, we propose a Difference Image Entropy based gaze direction recognition system. The Difference Image Entropy is computed by histogram levels using the acquired difference image of current image and reference images or average images that have peak positions from $-255{\sim}+255$ to prevent information omission. There are two methods about the Difference Image Entropy based gaze direction. 1) The first method is to compute the Difference Image Entropy between an input image and average images of 45 images in each location of gaze, and to recognize the directions of user's gaze. 2) The second method is to compute the Difference Image Entropy between an input image and each 45 reference images, and to recognize the directions of user's gaze. The reference image is created by average image of 45 images in each location of gaze after receiving images of 4 directions. In order to evaluate the performance of the proposed system, we conduct comparison experiment with PCA based gaze direction system. The directions of recognition left-top, right-top, left-bottom, right-bottom, and we make an experiment on that, as changing the part of recognition about 45 reference images or average image. The experimental result shows that the recognition rate of Difference Image Entropy is 97.00% and PCA is 95.50%, so the recognition rate of Difference Image Entropy based system is 1.50% higher than PCA based system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.334-340
• /
• 2002

This paper proposes a self-organizing fuzzy modeling which can create a new hyperplane-shaped cluster by applying multiple regression to input/output data with relatively large fuzzy entropy, add the new cluster to fuzzy rule base and adjust parameters of the fuzzy model in repetition. Tn the coarse tuning, weighted recursive least squared algorithm and fuzzy C-regression model clustering are used and in the fine tuning, gradient descent algorithm is used to adjust parameters of the fuzzy model precisely And learning rates are optimized by utilizing meiosis-genetic algorithm. To check the effectiveness and feasibility of the suggested algorithm, four representative examples for system identification are examined and the performance of the identified fuzzy model is demonstrated in comparison with that of the conventional fuzzy models.

• The Journal of Korean Association of Computer Education
• /
• v.10 no.3
• /
• pp.67-73
• /
• 2007

In this paper, we review essential constituents of a dialogue interface system and propose practical methods to implement the each constituent. The implemented system consists of a discourse manager, an intention analyzer, a named entity recognizer, a SQL query generator, and a response generator. In the progress of implementation, the intention analyzer uses a maximum entropy model based on statistics because the domain dependency of the intention analyzer is comparatively low. The others use a simple pattern matching method because they needs high domain portability. In the experiments in a schedule arrangement domain, the implemented system showed the precision of 88.1% in intention analysis and the success rate of 83,4% in SQL query generation.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.06a
• /
• pp.177-180
• /
• 2001

본 논문에서는 신경망을 이용한 내용 기반 이미지 분류 방법을 제안한다. 분류 대상이미지는 인터넷상의 다양한 이미지들 중 오브젝트 이미지이대 웹 에이전트를 통하여 획득하고 정규화 과정을 거친다. 획득한 이미지를 분류하기 위한 특징은 웨이블릿 변란 후 추출된 질감 특징이다. 추출된 질감 특징을 이용하여 학습패턴을 생성하고 신경망을 학습한다. 그리고 구성된 신경망 분류기로 이미지를 분류한다. 본 연구에서는 다양한 질감 특징들 중에서 대비(contrast), 에너지(energy), 엔트로피(entropy)를 이용하여 특징을 추출한다. 실험에 사용한 데이터는 30종류에 대하여 각각 10개씩, 300개의 이미지들을 학습 데이터, 테스트 데이터로 사용하여 구성된 분류기의 인식률을 실험하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.245-251
• /
• 2002

본 논문에서는 상대적으로 큰 퍼지 엔트로피를 갖는 입력-출력 데이터 집단에 다중 회귀 분석을 적용하여 다차원 평면 클러스터를 생성하고, 이 클러스터를 새로운 퍼지 모델의 규칙으로 추가한 후 퍼지 모델 파라미터의 개략 동조와 정밀 동조를 수행하는 자기구성 퍼지 모델링을 제안한다. Weighted recursive least squared 알고리즘과 fuzzy C-regression model 클러스터링에 의해 퍼지 모델의 파라미터를 개략적으로 동조한 후 gradient descent 알고리즘에 의해 파라미터를 정밀 동조하면서 감수분열 유전 알고리즘을 이용하여 최적의 학습률을 탐색한다. 그리고 자기 구성 퍼지 모델링 기법을 이용하여 Box-Jenkins의 가스로 데이터, 다변수비선형 정적 함수의 데이터와 하수 처리 활성오니 공정의 모델링을 수행하고, 기존의 방법에 의한 모델링 결과와 비교하여 그 성능을 입증한다.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.24 no.9
• /
• pp.671-678
• /
• 2012

The objective of this study is to analyze theoretically the performance of an open air-cycle refrigeration system in which environmental concerns increase. The pressure ratio of the external compressor and efficiencies of the components that compose of the system are selected as important parameters. As the pressure ratio of the external compressor increases, the pressure ratio of the ACM compressor is determined high, the refrigerating temperature and capacity increase, the COP decreases, and the total entropy production rate increases. The effect of heat exchanger effectiveness and turbine efficiency on the performance are greater than that of the ACM compressor efficiency. Also the performance of the air-cycle refrigeration system with two heat exchangers has been enhanced like high COP and low total entropy production rate, compared to the system with one heat exchanger.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.26 no.11
• /
• pp.504-511
• /
• 2014

The objective of this study is to theoretically analyze the performance of an open wet air-cycle refrigeration system, which nowadays is increasingly generating environmental concern. The temperature and relative humidity of the outside air are selected as the most important parameters. As the temperature and relative humidity of the outside air increase, the pressure ratio of the ACM compressor is determined to be nearly constant, the air temperature at the exit of the system increases, and the amount of condensed water, the cooling capacity, the COP, and the total entropy production rate increase overall. The effects of the effectiveness of the heat exchanger and the efficiency of the turbine on the performance are greater than that of the efficiency of the ACM compressor. Also, the performance of the wet air-cycle refrigeration system with two heat exchangers is enhanced, with a high COP and low total entropy production rate, compared to the system with a single heat exchanger.

• Journal of the Korea Convergence Society
• /
• v.8 no.5
• /
• pp.13-17
• /
• 2017

Existing Speech feature extracting method in speech Signal, there are incorrect recognition rates due to incorrect speech which is not clear threshold value. In this article, the modeling method for improving speech recognition performance that combines the feature extraction for speech and silence characteristics normalized to the non-speech. The proposed method is minimized the noise affect, and speech recognition model are convergence of speech signal feature extraction to each speech frame and the silence feature normalization. Also, this method create the original speech signal with energy spectrum similar to entropy, therefore speech noise effects are to receive less of the noise. the performance values are improved in signal to noise ration by the silence feature normalization. We fixed speech and non speech classification standard value in cepstrum For th Performance analysis of the method presented in this paper is showed by comparing the results with CHMM HMM, the recognition rate was improved 2.7%p in the speech dependent and advanced 0.7%p in the speech independent.

• Broadcasting and Media Magazine
• /
• v.16 no.4
• /
• pp.59-71
• /
• 2011

오디오와 음성 압축 기술적 근간은 서로 다르지만, 최근의 모바일 멀티미디어 기기 시장의 컨버전스 현상에 따라 압축하고자 하는 신호가 혼용되고 있으며, 비슷한 목표 전송률과 음질로 수렴하고 있다. 현재는 동일 기기에서 서로 다른 압축 기술을 적용하고 있으나, 음성과 음악이 동시에 서비스 되는 멀티미디어 기기에서는 단일 압축 방식으로 처리하고자 하는 이슈가 부각되고 있다. 특히, 스마트 폰 및 음악 콘텐츠 포탈 서비스의 대중화를 고려할 때, 음성 및 음악 신호 모두를 효율적으로 압축하는 음악 및 음성 신호의 융합 압축 기술이 더욱 필요해 보인다. 본 고에서는 MPEG 오디오 그룹에서 가장 최근 진행한 Unified Speech and Audio Coding(USAC)의 탄생 배경 및 표준화 현황을 소개한다. USAC는 64kbps 이하에서 기술적으로 최고 성능을 지닌 AMR-WB+ 및 HE-AAC v2보다도 우월한 음질을 보이며, 높은 비트율에서도 동등한 음질을 보장한다. 이런 우수한 음질에 기여한 USAC의 스위칭 구조와 더불어 기술적으로 향상된 주요 모듈인 파라미터 기반 스테레오 및 고주파 압축, 그리고 엔트로피 코딩 방식에 대해서 살펴 본다. 향후, 다양한 오디오 신호를 효율적으로 압축하는 USAC는 디지털 라디오, 모바일 TV, 그리고 오디오 북과 같은 사용자 시나리오에서 사용될 확률이 높아 보인다. 또한, USAC는 배경 잡음이나 배경 음악이 있는 경우에도 성능이 우수하기 때문에 YouTube 및 podcast 등과 같이 사용자가 콘텐츠를 생성할 때도 유용하게 사용 될 수 있다.