• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.4
• /
• pp.723-730
• /
• 2015

In this paper, a location tracking compensation algorithm based on the Least-Squares Method ($LCA_{LSM}$) was proposed to improve the autonomous tracking efficiency for the docent robot in exhibition hall, and the performance of the $LCA_{LSM}$ is analyzed by several practical experiments. The proposed $LCA_{LSM}$ compensates the collected location coordinates for the robot using the Least-Squares Method (LSM) in order to reduce the cumulated errors that occur in the Encoder/Giro sensor (E/G) and to enhance the measured tracking accuracy rates in the autonomous tracking of the robot in exhibition hall. By experiments, it was confirmed that the average error reduction rates of the $LCA_{LSM}$ are higher as 4.85% than that of the $LCA_{KF}$ in Scenario 1 (S1) and Scenario 2 (S2), respectively on the location tracking. In addition, it was also confirmed that the standard deviation in the measured errors of the $LCA_{LSM}$ are much more low and constant compared to that of the E/G sensor and the $LCA_{KF}$ in S1 and S2 respectively. Finally, we see that the suggested $LCA_{LSM}$ can execute more the stabilized location tracking than the E/G sensors and the $LCA_{KF}$ on the straight lines of S1 and S2 for the docent robot.

• Journal of Astronomy and Space Sciences
• /
• v.26 no.1
• /
• pp.75-88
• /
• 2009

The main purpose of the current research is to introduce the alternative algorithm of the non-recursive batch filter based on the unscented transformation in which the linearization process is unnecessary. The presented algorithm is applied to the orbit determination of a low earth orbiting satellite and compared its results with those of the well-known Bayesian batch least squares estimation and the iterative UKF smoother (IUKS). The system dynamic equations consist of the Earth's geo-potential, the atmospheric drag, solar radiation pressure and the lunar/solar gravitational perturbations. The range, azimuth and elevation angles of the satellite measured from ground stations are used for orbit determination. The characteristics of the non recursive unscented batch filter are analyzed for various aspects, including accuracy of the determined orbit, sensitivity to the initial uncertainty, measurement noise and stability performance in a realistic dynamic system and measurement model. As a result, under large non-linear conditions, the presented non-recursive batch filter yields more accurate results than the other batch filters about 5% for initial uncertainty test and 12% for measurement noise test. Moreover, the presented filter exhibits better convergence reliability than the Bayesian least squares. Hence, it is concluded that the non-recursive batch filter based on the unscented transformation is effectively applicable for highly nonlinear batch estimation problems.

• Journal of Digital Convergence
• /
• v.12 no.4
• /
• pp.277-283
• /
• 2014

Fuzzy modeling is generally using the given data and the fuzzy rules are established by the input variables and the space division by selecting the input variable and dividing the input space for each input variables. The premise part of the fuzzy rule is presented by selection of the input variables, the number of space division and membership functions and in this paper the consequent part of the fuzzy rule is identified by polynomial functions in the form of linear inference and modified quadratic. Parameter identification in the premise part devides input space Min-Max method using the minimum and maximum values of input data set and C-Means clustering algorithm forming input data into the hard clusters. The identification of the consequence parameters, namely polynomial coefficients, of each rule are carried out by the standard least square method. In this paper, membership function of the premise part is dividing input space by using trapezoid-type membership function and by using gas furnace process which is widely used in nonlinear process we evaluate the performance.

• The Journal of the Acoustical Society of Korea
• /
• v.7 no.4
• /
• pp.98-109
• /
• 1988

This paper introduces an adaptive nonlinear filtering algorithm that uses the sequential regression(SER) method to update the second order Volterra filter coefficients in a recursive way. Conventionally, the SER method has been used to invert large matrices which result from direct application of Wiener filter theory to the Volterra filter. However, the algorithm proposed in this paper uses the SER approach to update the least squares solution which is derived for Gaussian input signals. In such an algorithm, the size of the matrix to be inverted is smaller than that of conventional approaches, and hence the proposed method is computationally simpler than conventional nonlinear system identification techniques. Simulation results are presented to demonstrate the performance of the proposed algorithm.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.4
• /
• pp.224-231
• /
• 2012

In this paper, we introduce a fuzzy inference systems based on fuzzy c-means clustering algorithm for fuzzy modeling of nonlinear process. Typically, the generation of fuzzy rules for nonlinear processes have the problem that the number of fuzzy rules exponentially increases. To solve this problem, the fuzzy rules of fuzzy model are generated by partitioning the input space in the scatter form using FCM clustering algorithm. The premise parameters of the fuzzy rules are determined by membership matrix by means of FCM clustering algorithm. The consequence part of the rules is expressed in the form of polynomial functions and the coefficient parameters of each rule are determined by the standard least-squares method. And lastly, we evaluate the performance and the nonlinear characteristics using the data widely used in nonlinear process.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.8 no.1
• /
• pp.81-87
• /
• 2008

This study is about the back analysis to optimize the uncertain parameters of geotechnical properties used in stability analysis of cut and cover tunnel. The Simplex algorithm, Powell algorithm, Rosenbrock algorithm, and Levenberg-Marquardt algorithm are applied for artificial problems of ground excavation. Furthermore, results are compared in the matter of the reliability of optimal solutions with a certain accuracy and the computation speed for evaluations of variables. As shown in results of numerical analysis, all of four algorithms are converged to exact solution satisfying the allowable criteria. And Levenberg-Marquardt's and Rosenbrock's algorithms are identified to be the more efficient methods in the evaluations of functions. After the back analysis for Poisson ratio and Young's modulus for cut and cover tunnel has been performed, design parameters have been correctly estimated and computation time has been improved while the number of measure points is increased.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1995.04a
• /
• pp.147-152
• /
• 1995

실험에 의한 모우드 해석 방법들은 1980년대부터 활발히 연구되어 많은 새로운 방법들이 개발되어 발표되었다. 그러나 개발된 대부분의 방법들은 측정된 데이타를 일괄처리하는 밸치(또는 off-line) 방법들이다. 최근에는 시간에 따라서 변하는 구조물의 동특성을 규명하는 분야에 모우드 해석 방법이 응용되어 사용되고 있다. 이러한 응용분야에서는 모우드 변수들의 변화되는 값을 새로운 데이타가 샘플링 될 때마다 그 값들을 수정하면서 추정할 수 있는 회귀적인(recursive 또는 on-line) 방법을 사용하여야 한다. Davies와 Hammond[1]는 회귀적 선형 자승법(Recursive Least Squares : RLS)을 이용하여 모우드 변수를 구하고 이를 벧치방법인 Instrumental Variable 방법과 Fourier 방법의 결과와 비교하였다. 그러나, 그 결과에서 보여준것처럼 RLS 방법은 잡음 대 시호비가 낮을 때에만 모우드 변수 값들을 정확하게 추정할 수 있었다. Sundararajan과 Montgomrey[2]는 회귀적 선형 최소자승 격자필터(lattice filter)를 이용하여 구조물의 차수(order)와 고유진동형, 그리고 진폭을 결정한 후 이를 토대로 회귀적 gradient형태의 방정식 오차 규명 방법(equation-error identification algorithm)에 의하여 모우드 변수들을 추정하였다. 이 방법은 2차원 격자구조물의 모우드 변수 추정에 사용되었으며, 또한 적응모우드제어에도 성공적으로 이용되었다. 그러나, 이 방법도 잡음 대 신호비가 낮은 환경에서만 사용할 수 있다는 단점이 있다. 위에서 언급한 방법들은 모두 RLS 방법을 기초로 하여 개발되었으나, RLS 방법은 전형적인 결정적(deterministic)방법으로서 잡음이 섞인 데이타를 처리하기에는 부적절한 방법임이 널리 알려진 사실이다[3]. 최근에 Ben Mrad와 Fassois[4]는 신호에 잡음이 존재하여도 이를 잘 처리할 수 있는 확률적(stochastic) 방법을 개발하여 기존의 결정적 방법들과 그 결과를 비교하였다. 그러나, 개발된 방법은 응답 신호에 백색잡음(white noise)이 섞이는 특수한 경우에만 사용할 수 있게 만들어져서 이 방법의 실질적인 적용에는 어려움이 있다. 본 연구에서는 기존의 방법들의 단점을 극복할 수 있는 새로운 회귀적 모우드 변수 규명 방법을 개발하였다. 이는 Fassois와 Lee가 ARMAX모델의 계수를 효율적으로 추정하기 위하여 개발한 뱉치방법인 Suboptimum Maximum Likelihood 방법[5]를 기초로 하여 개발하였다. 개발된 방법의 장점은 응답 신호에 유색잡음이 존재하여도 모우드 변수들을 항상 정확하게 구할 수 있으며, 또한 알고리즘의 안정성이 보장된 것이다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.11
• /
• pp.5379-5388
• /
• 2012

In fuzzy modeling for nonlinear process, the fuzzy rules are typically formed by selection of the input variables, the number of space division and membership functions. The Generation of fuzzy rules for nonlinear processes have the problem that the number of fuzzy rules exponentially increases. To solve this problem, complex nonlinear process can be modeled by generating the fuzzy rules by means of fuzzy division of input space. Therefore, in this paper, rules of non-fuzzy inference systems are generated by partitioning the input space in the scatter form using HCM clustering algorithm. The premise parameters of the rules are determined by membership matrix by means of HCM clustering algorithm. The consequence part of the rules is represented in the form of polynomial functions and the consequence parameters of each rule are identified by the standard least-squares method. And lastly, we evaluate the performance and the nonlinear characteristics using the data widely used in nonlinear process. Through this experiment, we showed that high-dimensional nonlinear systems can be modeled by a very small number of rules.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.1
• /
• pp.55-65
• /
• 1995

Existing multiple-row downdating algorithms have adopted a CFD(Cholesky Factor Downdating) that recursively downdates one row at a time. The CFD based algorithm requires 5/2p $n^{2}$ flops(floating point operations) downdating a p$\times$n observation matrix $Z^{T}$ . On the other hands, a HCFD(Hybrid CFD) based algorithm we propose in this paper, requires p $n^{2}$＋6/5 $n^{3}$ flops v hen p$\geq$n. Such a HCFD based algorithm factorizes $Z^{T}$ at first, such that $Z^{T}$ = $Q_{z}$ RT/Z, and then applies the CFD onto the upper triangular matrix Rt/z, so that the total number of floating point operations for downdating $Z^{T}$ would be significantly reduced compared with that of the CFD based algorithm. Benchmark tests on the Sun SPARC/2 and the Tolerant System also show that performance of the HCFD based algorithm is superior to that of the CFD based algorithm, especially when the number of rows of the observation matrix is large.rge.

• Proceedings of KOSOMES biannual meeting
• /
• 2005.11a
• /
• pp.197-202
• /
• 2005

Generally, a semiconductor chip measured with a few micro units is captured by line scan camera for higher inspection accuracy. However, the faulty inspection requires an exact boundary detection algorithm because it is very sensitive to scan speed and lighting conditions. In this paper we propose boundary detection using subpixel edge detection method in order to increase the accuracy of bump faulty detection on chips. The bump edge is detected by first derivative to four directions from bump center point and the exact edge positions are searched by the subpixel method. Also, the exact bump boundary to calculate the actual bump size is computed by LSM(Least Squares Method) to minimize errors since the bump size is varied such as bump protrusion, bump bridge, and bump discoloration. Experimental results exhibit that the proposed algorithm shows large improvement comparable to the other conventional boundary detection algorithms.