• Journal of Integrative Natural Science
• /
• v.7 no.2
• /
• pp.138-144
• /
• 2014

Fisher information matrix plays an important role in statistical inference of unknown parameters. Especially, it is used in objective Bayesian inference where we calculate the posterior distribution using a noninformative prior distribution, and also in an example of metric functions in geometry. To estimate parameters in a distribution, we can use the Fisher information matrix. The more the number of parameters increases, the more its matrix form gets complicated. In this paper, by using Mathematica programs we derive the Fisher information matrix for 4-parameter generalized gamma distribution which is used in reliability theory.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.3-10
• /
• 2014

In this paper we review the typical Toeplitz matrices and block circulant matrices, and propose the a circulant Hadamard matrix which is consisted of +1 and -1, but its structure is different from typical Hadamard matrix. The proposed circulant Hadamard matrix decreases computational complexities to $Nlog_2N$ additions through high speed algorithm compare to original one. This matrix is able to be applied to Massive MIMO channel estimation, FIR filter design, amd signal processing.

• Journal of information and communication convergence engineering
• /
• v.6 no.1
• /
• pp.105-109
• /
• 2008

A robust optimal control system design algorithm in active suspension equipment adopting linear matrix inequalities control system design theory is presented. The validity of the linear matrix inequalities robust control system design in active suspension system through the numerical examples is also investigated.

• Transactions of the Society of Information Storage Systems
• /
• v.3 no.3
• /
• pp.126-128
• /
• 2007

일반적으로 주어진 하나의 H matrix 로 다수의 코드율을 가지는 코드화가 가능하다. 하지만 Low Density Parity Check(LDPC) 코드의 H matrix는 H matrix 내의 1의 개수와 위치에 따라 그 성능이 달라짐으로 해서 하나의 H matrix로 다수의 코드율을 대응하기 위한 설계 방법이 요구된다. H matrix 의 성능은 일반적으로 girth나 minimum distance에 의해 좌우되고 H matrix의 1의 위치에 따라 달라진다. 본 논문에서는 H matrix의 girth 와 minimum distance에 입각한 다수 개의 코드율이 대응 가능한 LDPC code의 H matrix 설계 방법을 제시하고자 한다. 이렇게 함으로써 하나의 H matrix로 다수의 코드율에 따른 각각의 성능을 일정 수준 이상 유지하는 multi-rate LDPC code가 가능하다.

• ETRI Journal
• /
• v.39 no.1
• /
• pp.21-29
• /
• 2017

This paper addresses the problem of unsupervised speech separation based on robust non-negative matrix factorization (RNMF) with ${\beta}$-divergence, when neither speech nor noise training data is available beforehand. We propose a robust version of non-negative matrix factorization, inspired by the recently developed sparse and low-rank decomposition, in which the data matrix is decomposed into the sum of a low-rank matrix and a sparse matrix. Efficient multiplicative update rules to minimize the ${\beta}$-divergence-based cost function are derived. A convolutional extension of the proposed algorithm is also proposed, which considers the time dependency of the non-negative noise bases. Experimental speech separation results show that the proposed convolutional RNMF successfully separates the repeating time-varying spectral structures from the magnitude spectrum of the mixture, and does so without any prior training.

• Annual Conference of KIPS
• /
• 2003.11b
• /
• pp.1033-1036
• /
• 2003

최근 인터넷의 급격한 발전의 결과로서 전산 시스템의 대규모화와 복잡화가 증가함에 따라 시스템의 전문적인 관리를 위한 솔루션에 대한 요구가 증가하고 있다. 서비스를 수행중인 시스템에 있어서 성능 관리는 전산 자원의 가동 성능을 유지하고 향상시키는 일련을 작업을 의미하며 모니터링, 진단, 제어의 사이클로 관리자와 상호작용을 수행한다. 본 논문에서는 차세대 인터넷 서버의 관리를 위한 시스템 관리 솔루션인 MATRlx (MATRIx's Advanced Technology of Resource Information extraction / eXploitation / eXploration / eXchange) 시스템을 소개하며 MATRIx 시스템의 성능 관리 블록인 MATRIx-PFMB의 설계 및 구현에 대한 이슈들을 다룬다. MATRIx-PFMB(PerFormance Management Block)는 관리 서버와 에어젼트 및 관리자 콘솔로 구성되며 능동적인 시스템 관리를 위한 진단 도구 및 제어 기능을 제공하고 기능 확장의 용이성을 제공하기 위한 프레임워크 구조를 갖는다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.2
• /
• pp.372-379
• /
• 2015

The latest video compression standard (such as H.264/AVC and HEVC) utilizes quarter-pel accuracy motion estimation in order to retain detailed motion information. Many sub-pixel motion estimation algorithms used in the spatial domain usually encounters increment of computational complexity due to embedded interpolation algorithm. In this paper, an approach to measure sub-pixel accuracy motion estimation in frequency domain using shifting matrix is proposed. Complexity can be reduced utilizing shifting matrix algorithm in frequency domain and simulation results demonstrate not only higher PSNR but lower bit rates than spatial domain algorithms.

• Journal of information and communication convergence engineering
• /
• v.3 no.4
• /
• pp.172-175
• /
• 2005

In this paper, a new method to get the optimum channel capacity of a Multiple-Input Multiple­Output (MIMO) system is presented. The proposed method exploits the diagonal structure of channel matrix to maximize the channel capacity. The diagonal format of the channel matrix is formed by multiplying the transmitted signal with the pre-compensated channel PCC) matrix. Numerical simulations show that the proposed method exploiting the diagonal structure of channel matrix could significantly increase the system capacity compared with the system without applying the diagonal structure of channel matrix.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.317-319
• /
• 2002

In this paper, a new method to get the optimum channel capacity of a Multiple-Input Multiple-Output (MIMO) system is presented. The proposed method exploits the diagonal structure o f channel matrix in order to maximize the channel capacity. The diagonal format of the channel matrix is formed by multiplying the transmitted signal with the precompensated channel (PCC) matrix. Numerical simulations show that the proposed method exploiting the diagonal structure of channel matrix could significantly increase the system capacity compared with the system without applying the diagonal structure of channel matrix.