• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.725-734
• /
• 2003

In this paper, we propose the text summarization method using PCA (Principal Component Analysis) and SVD (Singular Value Decomposition). The proposed method presents a summary by extracting significant sentences based on the distances between thematic words and sentences. To extract thematic words, we use both word frequency and co-occurence information that result from performing PCA. To extract significant sentences, we exploit Euclidean distances between thematic word vectors and sentence vectors that result from carrying out SVD. Experimental results using newspaper articles show that the proposed method is superior to the method using either word frequency or only PCA.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.4
• /
• pp.752-757
• /
• 2006

In the case of the requirement of high speed transmission, OFDM is a powerful technique employed in communications systems suffering from frequency selective fading. In this paper, we apply an optimal adaptive bitloading algorithm technique. The BER performance of the fixed-rate SISO and adaptive SISO is simulated. Specially, we can decompose the MIMO channel into the SISO channel by making use of the singular value decomposition(SVD) assuming channel knowledge in a multipath environment. As a results of simulation, we confirmed that the BER enhancement of MIMO-OFDM system with the bitloadins algorithm was superior to the SISO-OFDM system.

• Korean Journal of Optics and Photonics
• /
• v.6 no.3
• /
• pp.178-187
• /
• 1995

The method that determines the appropriate damping factor is studied for a lens design. When suitable damping factor is applied to the additive damped least-squares (DLS) method, the convergence and the stability of the optimization process are examined in a triplet-type photographic lens design. We calculate eigenvalues of the product of the Jacobian matrix of error functions by using the singular value decomposition (SVD) method. We adopt the median of eigenvalues as an appropriate damping factor. The convergence and the stability of the optimization process are improved by choosing the adequate damping factor for the optimization of a photographic lens. It is known that the numerical inaccuracy in the calculation of normal equation is overcome by using the orthogonal transformations of the Jacobian matrix. Therefore, a combination of the method for setting a proper damping factor and the orthogonal transformations of the Jacobian matrix is good for application to the design of an aspheric lens with high-order terms. terms.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2013.10a
• /
• pp.130-132
• /
• 2013

This paper presents an improvement for calculating method of astronomical vessel position with circle of equal altitude equation based on using a virtual object in sun and two stars observation. In addition, to enhance the accuracy of ship position achieved from solving linear matrix system, and surmount the disadvantages on rank deficient matrices situation, the authors used singular value decomposition (SVD) in least square method instead of normal equation and QR decomposition, so, the solution of matrix system will be available in all situation. As proposal algorithm, astronomical ship position will give more accuracy than previous methods.

• ETRI Journal
• /
• v.41 no.1
• /
• pp.109-116
• /
• 2019

This paper explores new techniques that are based on a hidden-layer linear transformation for fast speaker adaptation used in deep neural networks (DNNs). Conventional methods using affine transformations are ineffective because they require a relatively large number of parameters to perform. Meanwhile, methods that employ singular-value decomposition (SVD) are utilized because they are effective at reducing adaptive parameters. However, a matrix decomposition is computationally expensive when using online services. We propose the use of an extended diagonal linear transformation method to minimize adaptation parameters without SVD to increase the performance level for tasks that require smaller degrees of adaptation. In Korean large vocabulary continuous speech recognition (LVCSR) tasks, the proposed method shows significant improvements with error-reduction rates of 8.4% and 17.1% in five and 50 conversational sentence adaptations, respectively. Compared with the adaptation methods using SVD, there is an increased recognition performance with fewer parameters.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.729-739
• /
• 2015

An algorithm for fault detection and classification method for wide-area protection in Korean transmission systems is proposed. The modeling of 345-kV and 765-kV Korean power system transmission networks using the Electro Magnetic Transient Program - Restructured Version (EMTP-RV) is presented and the algorithm for fault detection and classification in transmission lines is developed. The proposed algorithm uses the Wavelet Transform (WT) and Singular Value Decomposition (SVD). The Singular value of Approximation coefficient (SA) and part Sum of Detail coefficient (SD) are introduced. The characteristics of the SA and SD at the fault conditions are analyzed and used in the algorithm for fault detection and classification. The validation of the proposed algorithm is verified by various simulation results.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.3
• /
• pp.234-239
• /
• 2015

Non-Negative Matrix Factorization (NMF) is a method for updating dictionary and gain in alternating manner. Due to ease of implementation and intuitive interpretation, NMF is widely used to detect and separate overlapping sound events. However, NMF that utilizes non-negativity constraints generates parts-based representation and this distinct property leads to a dictionary containing fragmented acoustic events. As a result, the presence of shared basis results in performance degradation in both separation and detection tasks of overlapping sound events. In this paper, we propose a new method that utilizes K-Singular Value Decomposition (K-SVD) based dictionary to address and mitigate the part-based representation issue during the dictionary learning step. Subsequently, we calculate the gain using NMF in sound event detection step. We evaluate and confirm that overlapping sound event detection performance of the proposed method is better than the conventional method that utilizes NMF based dictionary.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.26-33
• /
• 2014

For wireless communication systems of (and beyond) LTE-Advanced, multiple-input multiple-output (MIMO) with an increased number of antennas will be utilized for system throughput improvement. When using such an increased number of antenna, an excessive amount of overhead in channel state information (CSI) feedback can be a serious problem. In this paper, we propose methods which reduce the CSI feedback overhead, particularly including application strategies for multi-rank transmission targeted for two or more reception antennas. To reduce the information which is instantaneously transmitted from the reception node to the transmission node, we present a beamforming method utilizing singular value decomposition (SVD) based on channel estimation of partitioned antenna arrays. Since the SVDs for partial matrices of the channel may lose the characteristics of the original unpartitioned matrix, we explain an appropriate scheme to cope with this problem.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.279-286
• /
• 2006

One of the widely used methods for product recommendation in Internet storefronts is matching product features against target customer profiles. When using this method, it's very important to choose a suitable subset of features for recommendation efficiency and performance, which, however, has not been rigorously researched so far. In this paper, we utilize a dataset collected from a virtual shopping experiment in a Korean Internet book shopping mall to compare several popular methods from other disciplines for selecting features for product recommendation: the vector-space model, TFIDF(Term Frequency-Inverse Document Frequency), the mutual information method, and the singular value decomposition(SVD). The application of SVD showed the best performance in the analysis results.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.143-146
• /
• 2009

There are some image hash methods, in the paper four image hash methods have been compared: FJLT (Fast Johnson- Lindenstrauss Transform), SVD (Singular Value Decomposition), NMF (Non-Negative Matrix Factorization), FP (Feature Point). From the compared result, FJLT method can't be used in the online. the search time is very slow because of the KNN algorithm. So FJLT method has been improved in the paper.