• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.394-396
• /
• 2006

기존 질의기반의 문서요약은 질의와 문서간의 사전 학습으로 요약의 질을 높이거나, 문서의 고유 구조(inherent structure)를 반영하여 요약의 정확도를 높이기 위하여 문서를 그래프로 변환한다. 본 논문은 비음수 행렬 인수분해 (NMF, Non-negative Matrix Factorization)를 이용하여 질의 기반의 문서를 요약하는 새로운 방법을 제안하였다. 제안된 방법은 질의와 문서간에 사전학습이 필요 없다. 또한 문서를 그래프로 변형시키는 복잡한 처리 없이 NMF에 의해 얻어진 의미 특징(semantic feature)과 의미 변수(semantic variable)로 문서의 고유 구조를 반영하여 요약의 정확도를 높일 수 있다. 마지막으로 단순한 방법으로 문장을 쉽게 요약 할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.427-430
• /
• 2008

본 논문은 비음수 행렬 인수분해(NMF, non-negative matrix factorization)와 NMF 군집방법을 이용하여 다중문서를 요약하는 새로운 방법을 제안하였다. 본 논문에서 NMF에 의해 계산된 의미 특징(semantic feature)은 문서의 고유 구조(inherent structure)를 반영하여 문장을 추출함으로써 요약의 질을 높일 수 있고, 의미 변수(semantic variable)를 이용한 문장의 군집은 문장 간의 유사성과 다양성 고려하여서 쉽게 과잉정보를 제거하여 문장을 요약할 수 있는 장점을 갖는다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.418-420
• /
• 2015

본 논문은 베이지안 비음수 행렬 인수분해 (Bayesian nonnegative matrix factorization, BNMF) 기반의 음성 강화 기법에서 음성과 잡음 성분의 latent source 수에 따른 강화성능에 대해 서술한다. BNMF 기반의 음성 강화 기법은 입력 신호를 서브 신호들의 합으로 분해한 후, 잡음 성분을 제거하는 방식으로 그 성능이 기존의 NMF 기반의 방법들보다 우수한 것으로 알려져 있다. 그러나 많은 계산량과 latent source 의 수에 따라 성능의 차이가 있다는 단점이 있다. 이러한 단점을 개선하기 위해 본 논문에서는 BNMF 기반의 음성 강화 기법에서 최적의 latent source 개수를 찾기 위한 실험을 진행하였다. 실험은 잡음의 종류, 음성의 종류, 음성과 잡음의 latent source 의 개수, 그리고 SNR 을 바꿔가며 진행하였고, 성능 평가 방법으로 PESQ (perceptual evaluation of speech quality) 를 이용하였다. 실험 결과, 음성의 latent source 개수는 성능에 영향을 주지 않지만, 잡음의 latent source 개수는 많을수록 성능이 좋은 것으로 확인되었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.8
• /
• pp.851-858
• /
• 2016

This paper presents a new statistical voice activity detection (VAD) based on the probabilistic interpretation of nonnegative matrix factorization (NMF). The objective function of the NMF using Kullback-Leibler divergence coincides with the negative log likelihood function of the data if the distribution of the data given the basis and encoding matrices is modeled as Poisson distributions. Based on this probabilistic NMF, the VAD is constructed using the likelihood ratio test assuming that speech and noise follow Poisson distributions. Experimental results show that the proposed approach outperformed the conventional Gaussian model-based and NMF-based methods at 0-15 dB signal-to-noise ratio simulation conditions.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.391-393
• /
• 2006

인터넷의 급속한 확산과 대량 정보의 이동은 문서의 요약을 더욱 필요로 하고 있다. 본 논문은 비음수 행렬 인수분해로(NMF, non-negative matrix factorization) 얻어진 비음수 의미 가변 행렬(NSVM, non-negative semantic variable matrix)을 이용하여 자동으로 포괄적 문서요약 하는 새로운 방범을 제안하였다. 제안된 방법은 인간의 인식 과정과 유사한 비음수 제약을 사용한다. 이 결과 잠재의미색인에 비해 더욱 의미 있는 문장을 선택하여 문서를 요약할 수 있다. 또한, 비지도 학습에 의한 문서요약으로 사전 전문가에 의한 학습문장이 필요 없으며, 적은 계산비용을 통하여 쉽게 문장을 추출할 수 있는 장점을 갖는다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.3B
• /
• pp.293-303
• /
• 2011

An efficient diagonalized approximate factorization algorithm (DAF) is developed for the solution of three-dimensional incompressible viscous flows. The pressure-based, artificial compressibility (AC) method is used for calculating steady incompressible Navier-Stokes equations. The AC form of the governing equations is discretized in space using a second-order-accurate finite volume method. The present DAF method is applied to derive a second-order accurate splitting of the discrete system of equations. The primary objective of this study is to investigate the computational efficiency of the present DAF method. The solutions of the DAF method are evaluated relative to those of well-known four-stage Runge-Kutta (RK4) method for fully developed and developing laminar flows in curved square ducts and a laminar flow in a cavity. While converged solutions obtained by DAF and RK4 methods on the same computational meshes are essentially identical because of employing the same discrete schemes in space, both algorithms shows significant discrepancy in the computing efficiency. The results reveal that the DAF method requires substantially at least two times less computational time than RK4 to solve all applied flow fields. The increase in computational efficiency of the DAF methods is achieved with no increase in computational resources and coding complexity.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.4
• /
• pp.619-627
• /
• 2015

This paper presents a speech enhancement method using non-negative matrix factorization (NMF). In the training phase, each basis matrix of source signal is obtained from a proper database, and these basis matrices are utilized for the source separation. In this case, the performance of speech enhancement relies heavily on the basis matrix. The proposed method for which speech basis matrix is made a high reconstruction error for noise signal shows a better performance than the standard NMF which basis matrix is trained independently. For comparison, we propose another method, and evaluate one of previous method. In the experiment result, the performance is evaluated by perceptual evaluation speech quality and signal to distortion ratio, and the proposed method outperformed the other methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.12
• /
• pp.88-93
• /
• 2016

This paper presents a method of constructing the highly performance switching circuit(HPSC) over finite fields. The proposed method is as following. First of all, we extract the input/output relationship of linear characteristics for the given digital switching functions, Next, we convert the input/output relationship to Directed Cyclic Graph using basic gates adder and coefficient multiplier that are defined by mathematical properties in finite fields. Also, we propose the new factorization method for matrix characteristics equation that represent the relationship of the input/output characteristics. The proposed method have properties of generalization and regularity. Also, the proposed method is possible to any prime number multiplication expression.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2201-2206
• /
• 2008

This paper presents a method of constructing the Linear Digital Switching Function(LDSF) over finite fields. The proposed method is as following. First of all, we extract the input/output relationship of linear characteristics for the given digital switching functions, Next, we convert the input/output relationship to Directed Cyclic Graph(DCG) using basic gates adder and coefficient multiplier that are defined by mathematical properties in finite fields. Also, we propose the new factorization method for matrix characteristics equation that represent the relationship of the input/output characteristics. The proposed method have properties of generalization and regularity. Also, the proposed method is possible to any prime number multiplication expression.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.99-106
• /
• 2016

In this paper, we will discuss about correction method of missing data on noisy observation matrix and uncertainty analysis for the potential noise. In situations without missing data in an observation matrix, this solution is known to be accurately induced by SVD (Singular Value Decomposition). However, usually the several entries of observation matrix have not been observed and other entries have been perturbed by the influence of noise. In this case, it is difficult to find the solution as well as cause the 3D reconstruction error. Therefore, in order to minimize the 3D reconstruction error, above all things, it is necessary to correct reliably the missing data under noise distribution and to give a quantitative evaluation for the corrected results. This paper focuses on a method for correcting missing data using geometrical properties between 2D projected object and 3D reconstructed shape and for estimating a noise level of the observation matrix using ranks of SVD in order to quantitatively evaluate the performance of the correction algorithm.