• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.193-200
• /
• 2011

This paper proposes a low-cost visual analyzer algorithm of human body motion for real-time applications such as human-computer interfacing, virtual reality applications in medicine and telemonitoring of patients. To reduce cost of its use, we design the algorithm to use a single camera. To make the proposed system to be used more conveniently, we avoid from using optical markers. To make the proposed algorithm be convenient for real-time applications, we design it to have a closed-form with high accuracy. To design a closed-form algorithm, we propose an idea that formulates motion of a human body joint as a 2D universal joint model instead of a common 3D spherical joint model, without any kins of approximation. To make the closed-form algorithm has high accuracy, we formulates the estimation process to be an optimization problem. Thus-desined algorithm is applied to each joint of the human body one after another. Through experiments we show that human body motion capturing can be performed in an efficient and robust manner by using our algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.487-496
• /
• 2000

In this paper, the Multi-FNN(Fuzzy-Neural Networks) model is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNN is based on Yamakawa's FNN and uses simplified inference as fuzzy inference method and error back propagation algorithm as learning rules. We use a HCM clustering and Genetic Algorithms(GAs) to identify both the structure and the parameters of a Multi-FNN model. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNN according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNN model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. A aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. The aggregate performance index stands for an aggregate objective function with a weighting factor to consider a mutual balance and dependency between approximation and predictive abilities. According to the selection and adjustment of a weighting factor of this aggregate abjective function which depends on the number of data and a certain degree of nonlinearity, we show that it is available and effective to design an optimal Multi-FNN model. To evaluate the performance of the proposed model, we use the time series data for gas furnace and the numerical data of nonlinear function.

• Journal of the Korean Data and Information Science Society
• /
• v.8 no.2
• /
• pp.163-171
• /
• 1997

Function approximation from a set of input-output pairs has numerous applications in scientific and engineering areas. Multilayer feedforward neural networks have been proposed as a good approximator of nonlinear function. The back propagation(BP) algorithm allows multilayer feedforward neural networks to learn input-output mappings from training samples. It iteratively adjusts the network parameters(weights) to minimize the sum of squared approximation errors using a gradient descent technique. However, the mapping acquired through the BP algorithm may be corrupt when errorneous training data we employed. When errorneous traning data are employed, the learned mapping can oscillate badly between data points. In this paper we propose a robust BP learning algorithm that is resistant to the errorneous data and is capable of rejecting gross errors during the approximation process, that is stable under small noise perturbation and robust against gross errors.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.6
• /
• pp.543-556
• /
• 2009

Recently, NAND flash memory is being used as the swap device of virtual memory as well as the file storage of mobile systems. Since temporal locality is dominant in page references of virtual memory, LRU and its approximated CLOCK algorithms are widely used. However, cost of a write operation in flash memory is much larger than that of a read operation, and thus a page replacement algorithm should consider this factor. This paper analyzes virtual memory read/write reference patterns individually, and observes the ranking inversion problem of temporal locality in write references which is not observed in read references. With this observation, we present a new page replacement algorithm considering write frequency as well as temporal locality in estimating write reference behaviors. This new algorithm dynamically allocates memory space to read/write operations based on their reference patterns and I/O costs. Though the algorithm has no external parameter to tune, it supports optimized implementations for virtual memory systems, and also performs 20-66% better than CLOCK, CAR, and CFLRU algorithms.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.5
• /
• pp.489-495
• /
• 2014

A micro-genetic algorithm (MGA) is one of the improved forms of a genetic algorithm. It is used to reduce the number of iterations and the computing resources required by using small populations. The efficiency of MGAs has been proved through many problems, especially problems with 3-5 design variables. This study proposes an optimization algorithm based on the sequential design of experiments (SDOE) and an MGA. In a previous study, the authors used the SDOE technique to reduce trial-and-error in the conventional approximate optimization method by using the statistical design of experiments (DOE) and response surface method (RSM) systematically. The proposed algorithm has been applied to various mathematical examples and a structural problem.

• Journal of Broadcast Engineering
• /
• v.12 no.3
• /
• pp.278-288
• /
• 2007

We propose the fast full search algorithm that reduces the computational load of the block matching algorithm which is used for a motion estimation in the video coding. Since the conventional spiral search method starts searching at the center of the search window and then moves search point to estimate the motion vector pixel by pixel, it is good for the slow motion picture. However we proposed the efficient motion estimation method which is good for the fast and slow motion picture. Firstly, when finding the initial threshold value, we use the expanded predictor that can approximately calculate minimum threshold value. The proposed algorithm estimates the motion in the new search order after partitioning the search window and adapt the directional search order in the re-divided search window. At the result, we can check that the proposed algorithm reduces the computational load 94% in average compared to the conventional spiral full search algorithm without any loss of image quality.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.2
• /
• pp.94-104
• /
• 2002

As a part of scientific data visualization automatic generation algorithms for a contour map have been investigated mainly on data which are defined at every lattice point. But in actual situation like weather data measurement. it is impossible to get data defined at every lattice point This is because the exact value on every lattice point can not be obtained due to characteristics in sampling devices or sampling methods. In order to define data on every lattice point where data were not sampled an interpolation method. was applied to the sample data to assign approximate values for some lattice type data but by using the non-lattice type of sample data sets. A triangle data link was defined by using non lattice points directly based on actually sample data set, not by using the pre-processed rectangle lattice points. The suggested algorithm generates a contour map a contour map only by using sample data set which are much smaller than old one without data interpolation and there is no skew on data any more since it does not need any interpolation to get the values of the defined lattice points.

• Journal of the Korea Society for Simulation
• /
• v.29 no.3
• /
• pp.41-48
• /
• 2020

In this paper, a dynamic prediction algorithm using the cumulative distribution function for traffic volume is presented as a new method for predicting highway traffic rate more accurately, where an approximation function of the cumulative distribution function is obtained through numerical methods such as natural cubic spline interpolation and Levenberg-Marquardt method. This algorithm is a new structure of random number generation algorithm using the cumulative distribution function used in financial mathematics to be suitable for predicting traffic flow. It can be confirmed that if the highway traffic rate is simulated with this algorithm, the result is very similar to the actual traffic volume. Therefore, this algorithm is a new one that can be used in a variety of areas that require traffic forecasting as well as highways.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.388-390
• /
• 2012

본 논문에서는 $L_1$ 메트릭을 사용하는 평면상에 주어진 자료점의 집합 P로부터 질의점의 집합 Q에 대해 skyline이 되는 점들을 계산하는 문제를 다룬다. $L_1$ 거리는 도로망이 잘 발달된 도시 내의 이동 시간을 근사화해 주는 것으로 알려져 있다. 이 문제에서 각각의 질의점은 수직 또는 수평 방향으로 단위속도로 움직인다고 가정한다. 본 논문에서는 시간 0에서 $t_1$ 사이에 움직이는 질의점들에 대해서 skyline의 변화를 모두 계산하는 알고리즘을 제시한다. 또한 이 알고리즘이 O(${\mid}P{\mid}^2{\mid}Q{\mid}$) 시간에 모든 skyline을 계산 가능함을 보인다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2000.11a
• /
• pp.135-140
• /
• 2000

베이지안 신경망 모형(Bayesian Neural Networks Models)에서 주어진 입력값(input)은 블랙 박스(Black-Box)와 같은 신경망 구조의 각 층(layer)을 거쳐서 출력값(output)으로 계산된다. 새로운 입력 데이터에 대한 예측값은 사후분포(posterior distribution)의 기대값(mean)에 의해 계산된다. 주어진 사전분포(prior distribution)와 학습데이터에 의한 가능도함수(likelihood functions)를 통해 계산되어진 사후분포는 매우 복잡한 구조를 갖게 됨으로서 기대값의 적분계산에 대한 어려움이 발생한다. 이때 확률적 추정에 의한 근사 방법인 몬테칼로 적분을 이용한다. 이러한 방법으로서 Hybrid Monte Carlo 알고리즘은 우수한 결과를 제공하여준다(Neal 1996). 본 논문에서는 Hybrid Monte Carlo 알고리즘과 기존에 많이 사용되고 있는 Gibbs sampling, Metropolis algorithm, 그리고 Slice Sampling등의 몬테칼로 방법들을 비교한다.