Earticle

A real-time digital holographic display is the core technology for the next-generation 3DTV. Holographic display requires a considerably large amount of calculation. If generating a large number of digital holograms is intended, the amount of calculation and the time required increase exponentially. This is a significant obstacle in a real-time hologram service. This paper proposes an algorithm that increases the speed of generating a Fresnel hologram by using a recursive addition operation covering the entire coordinate array of a digital hologram. The 3D object designed to calculate the digital hologram uses a depth-map image produced by computer graphics. The proposed algorithm is a technique that performs the computer-generated holography (CGH) operation with only recursive addition of all of the hologram's coordinates by analyzing the regularity between the 3D object and the digital hologram coordinates. The experimental results show that the proposed algorithm increases the operation speed by 70% over the technique using the conventional CGH equation and by more than 30% over the previously proposed recursive technique.

메모리 기반 추론에서 기억공간의 효율적인 사용과 분류성능의 향상을 위하여, 재귀 분할 평균 기법을 제안하였다. 이 알고리즘은 패턴공간을 구성하는 각 초월 평면이 동일한 클래스소속으로 패턴으로 구성될 때까지 재귀적으로 분할한 후, 초월 평면별로 소속된 패턴들의 평균값을 계산하여 대표패턴을 추출한다. 또한 각 특징과 클래스간의 상호정보를 특징의 가중치로 사용하여 분류 성능의 향상을 시도하였다. 제안된 알고리즘은 k-NN(k-Nearest Neighbors) 분류기에서 필요로 하는 메모리 공간의 30~90%만을 사용하며, 분류에 있어서도 k-NN과 유사한 인식 성능을 보이고 있다. 또한 저장된 패턴 개수의 감소로 인하여, 실제 분류에 소요되는 시간에 있어서도 k-NN보다 월등히 우수한 성능을 보이고 있다.

We proposed the RPA (Recursive Partition Averaging) method in order to improve the storage requirement and classification rate of the Memory Based Reasoning. This algorithm recursively partitions the pattern space until each hyperrectangle contains only those patterns of the same class, then it computes the average values of patterns in each hyperrectangle to extract a representative. Also we have used the mutual information between the features and classes as weights for features to improve the classification performance. The proposed algorithm used 30~90% of memory space that is needed in the k-NN (k-Nearest Neighbors) classifier, and showed a comparable classification performance to the k-NN. Also, by reducing the number of stored patterns, it showed an excellent result in terms of classification time when we compare it to the k-NN.

재귀원형군은 마이크로 프로세스의 모델로서 활발하게 연구되고 있으며 특히 슈퍼컴퓨팅 분야에서 많은 관심을 불러 일으키고 있다. 본 논문에서는 재귀원형군에서 메시지의 경로 설정을 연구하는데 이는 네트워크의 성능 평가에 중요한 기준이 된다. 재귀원형군에서 출발 노드에서 목적 노드까지 m개의 패킷을 m개의 경로를 따라서 동시에 전송하고자 한다. 이 때 i번째의 패킷은 i번째의 경로를 따라서 전송된다. $(o{\leq}i{\leq}m-1)$. 모든 패킷들이 목적 노드에 신속하고 안전하게 도달하기 위해서 i번째의 경로는 disjoint해야 한다. 이들 경로들을 설계하기 위해서 Hamiltonian Circuit Latin Square(HCLS)를 재귀원형군에 적용시켜서 $O(n^2)$ 병렬 경로 알고리즘을 제안한다.

Recursive circulant graph has recently developed as a new model of multiprocessors, and drawn considerable attention to supercomputing, In this paper, we investigate the routing of a message i recursive circulant, that is a key to the performance of this network. On recursive circulant network, we would like to transmit m packets from a source node to a destination node simultaneously along paths, where the ith packet will traverse along the ith path $(o{\leq}i{\leq}m-1)$. In oder for all packets to arrive at the destination node quickly and securely, the ith path must be node-disjoint from all other paths. For construction of these paths, employing the Hamiltonian Circuit Latin Square(HCLS), a special class of $(n{\times}n)$ matrices, we present $O(n^2)$ parallel routing algorithm on recursive circulant network.

Writing a program with the recursive method is a simple and effective way of program design, making the logic of the program concise and clear. This paper will focus on the analytical program, writing method of the recursive algorithm, as well as the optimization of recursive program. Formula method or mathematical induction can be applied for writing of the recursive algorithm more simply. Meanwhile, either of them could provide the method of tail recursive to deal with the problem lies in recursive algorithm that massive time and space of the system are occupied.

An extremely crucial step in the diagnosis of cancers is to select a small number of informative genes for accurate classification. This issue has become a hot focus in the data mining of gene expression profiles. Especially for data with a large number of cancer types, many conventional classification methods show very poor performance. Here, we proposed a new approach for gene selection and multi-cancer classification based on step-by-step improvement of classification performance (SSiCP). The SSiCP gene selection algorithms were evaluated over the NCI60 and GCM benchmark datasets, with accuracy of 96.6% and 95.5% in 10-fold cross-validation, respectively. Furthermore, the SSiCP outperformed recently published algorithms when applied to another two multi-cancer data sets. Computational evidence indicated that SSiCP can avoid overfitting effectively. Compared with various gene selection algorithms, the implementation of SSiCP is simple and many of the selected genes by SSiCP are shown to be closely related to cancers.

The Recursive Least Squares (RLS) algorithm is renowned for its rapid convergence but in some scenarios it fails to show swiftness required by several applications. Such failure may result due to different limiting conditions. Gain vector plays an essential role in the performance of RLS algorithm. This paper proposes a modification in Gain vector that results in RLS algorithm performing much better in perspective of convergence, without adding significant complexity. Simulation results are presented which prove the authenticity of the finding, and comparison with conventional RLS algorithm is presented.

In this paper, a recursive formulation for generating the equations of motion of spatial mechanical systems is presented. The rigid bodies are replaced by a dynamically equivalent constrained system of particles which avoids introducing any rotational coordinates. For the open-chain system, the equations of motion are generated recursively along the serial chains using the concepts of linear and angular momenta Closed-chain systems are transformed to open-chain systems by cutting suitable kinematic joints and introducing cut-joint constraints. The formulation is used to carry out the dynamic analysis of multi-link five-point suspension. The results of the simulation demonstrate the generality and simplicity of the proposed dynamic formulation.

Circulant and multiblock circulant matrices have many important applications, and therefore their inverses are of considerable interest. A simple recursive algorithm is presented to compute the inverse of a multiblock circulant matrix. The algorithm only uses complex variables, roots of unity and normal matrix/vector operations.

In existing identification methods for on-orbit spacecraft, such as eigensystem realization algorithm (ERA) and subspace method identification (SMI), singular value decomposition (SVD) is used frequently to estimate the modal parameters. However, these identification methods are often used to process the linear time-invariant system, and there is a lower computation efficiency using the SVD when the system order of spacecraft is high. In this study, to improve the computational efficiency in identifying time-varying modal parameters of large spacecraft, a faster recursive algorithm called fast approximated power iteration (FAPI) is employed. This approach avoids the SVD and can be provided as an alternative spacecraft identification method, and the latest modal parameters obtained can be applied for updating the controller parameters timely (e.g. the self-adaptive control problem). In numerical simulations, two large flexible spacecraft models, the Engineering Test Satellite-VIII (ETS-VIII) and Soil Moisture Active/Passive (SMAP) satellite, are established. The identification results show that this recursive algorithm can obtain the time-varying modal parameters, and the computation time is reduced significantly.

The problem of recursive filtering far linear discrete-time systems with uncertainties is considered. A new suboptimal filtering algorithm is herein proposed. It is based on the fusion formula, which represents an optimal mean-square linear combination of local Kalman estimates with weights depending on cross-covariances between local filtering errors. In contrast to the optimal weights, the suboptimal weights do not depend on current measurements, and thus the proposed algorithm can easily be implemented in real-time. High accuracy and efficiency of the suboptimal filtering algorithm are demonstrated on the following examples: damper harmonic oscillator motion and vehicle motion constrained to a plane.

Maximum likelihood estimates (MLEs) for recursive models of categorical variables are discussed under an EM framework. Since MLEs by EM often depend on the choice of the initial values for MLEs, we explore reasonable rules for selecting the initial values for EM. Simulation results strongly support the proposed rules.

최근 악성코드와 정상 바이너리를 분류하기 위해 기계학습을 이용하는 기술이 다양하게 연구되고 있다. 효과적인 기계학습을 위해서는 악성코드와 정상 바이너리를 식별하기 위한 Feature를 잘 추출하는 것이 무엇보다 중요하다. 본 논문에서는 재귀적인 방법을 이용하여 기계학습에 활용하기 위한 Feature 추출 방법인 RFA(Recursive Feature Addition) 제안한다. 제안하는 방법은 기계학습의 성능을 극대화 하기 위해 개별 Feature를 대상으로 재귀적인 방법을 사용하여 최종 Feature Set을 선정한다. 세부적으로는 매 단계마다 개별 Feature 중 최고성능을 내는 Feature를 추출하여, 추출한 Feature를 결합하는 방법을 사용한다. 제안하는 방법을 활용하여 Decision tree, SVM, Random forest, KNN등의 기계학습 알고리즘에 적용한 결과 단계가 지속될수록 기계학습의 성능이 향상되는 것을 검증하였다.

Recently, various technologies that use machine learning to classify malicious code have been studied. In order to enhance the effectiveness of machine learning, it is most important to extract properties to identify malicious codes and normal binaries. In this paper, we propose a feature extraction method for use in machine learning using recursive methods. The proposed method selects the final feature using recursive methods for individual features to maximize the performance of machine learning. In detail, we use the method of extracting the best performing features among individual feature at each stage, and then combining the extracted features. We extract features with the proposed method and apply them to machine learning algorithms such as Decision Tree, SVM, Random Forest, and KNN, to validate that machine learning performance improves as the steps continue.

Abstract-Using the recursive generalized eigendecomposition method, we develop a recursive form solution to the data least squares (DLS) problem, in which the error is assumed to lie in the data matrix only. Simulations demonstrate that DLS outperforms ordinary least square for certain types of deconvolution problems.

We present a recursive total least squares (RTLS) algorithm for multilayer feedforward neural networks. So far, recursive least squares (RLS) has been successfully applied to training multilayer feedforward neural networks. But, when input data contain additive noise, the results from RLS could be biased. Such biased results can be avoided by using the recursive total least squares (RTLS) algorithm. The RTLS algorithm described in this paper gives better performance than RLS algorithm over a wide range of SNRs and involves approximately the same computational complexity of $O(N^{2})$.

The WK-recursive network proposed by Vecchia and Sanges[1] is widely used in the design and implementation of local area networks and parallel processing architectures. It provides a high degree of regularity and scalability, which conform well to a design and realization of distributed systems involving a large number of computing elements. In this paper, the routing of a message is investigated on the WK-recursive network, which is key to the performance of this network. We present an efficient shortest path algorithm on the WK-recursive network, which is simpler than Chen and Duh[2] in terms of design complexity.

In this paper, we propose a fast implementation of Bilateral filter for tone mapping algorithm. Bilateral filter is able to preserve detail while at the same time prevent halo-ing artifacts because of improper scale selection by ensuring image smoothed that not only depend on pixel closeness, but also similarity. We accelerate Bilateral filter by using a piecewise linear approximation and recursive Gaussian filter as its domain filter. Recursive Gaussian filter is scale independent filter that combines low cost 1D filter which makes this filter much faster than conventional convolution filter and filtering in frequency domain. The experiment results show that proposed method is simpler and faster than previous method without mortgaging the quality.

We present a recursive total least squares (RTLS) algorithm for adaptive system identification. So far, recursive least squares (RLS) has been successfully applied in solving adaptive system identification problem. But, when input data contain additive noise, the results from RLS could be biased. Such biased results can be avoided by using the recursive total least squares (RTLS) algorithm. The RTLS algorithm described in this paper gives better performance than RLS algorithm over a wide range of SNRs and involves approximately the same computational complexity of O(N²).

This paper is on realization of the speed-sensorless vector control of an induction motor using the RLS(Recursive Least Square) algorithm. The speed estimator is including the RLS algorithm and a rotor flux observer. The RLS algorithm has speed and rotor time constant as parameter vectors and rotor flux observer is designed to have robustness to stator resistance variation and through the IP(Integral and Proportional) speed controller stable performance is obtained for estimating rotor speed. Finally the total algorithm are realized in induction motor drive system and its effectiveness is verified.

A generalized recursive circulant network(GR) is widely used in the design and implementation of local area networks and parallel processing architectures. In this paper, we investigate the routing of a message on this network, that is a key to the performance of this network. We would like to transmit maximum number of packets from a source node to a destination node simultaneously along paths on this network, where the i^th packet traverses along the i^th path. In order for all packets to arrive at the destination node securely, the i^th path must be node-disjoint from all other paths. For construction of these paths, employing the Hamiltonian Circuit Latin Square(HCLS), a special class of (n x n) matrices, we present O(n²) parallel routing algorithm on generalized recursive circulant networks.