• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1245-1255
• /
• 2017

The online learning is a process of obtaining the solution for a given objective function where the data is accumulated in real time or in batch units. The stochastic gradient descent method is one of the most widely used for the online learning. This method is not only easy to implement, but also has good properties of the solution under the assumption that the generating model of data is homogeneous. However, the stochastic gradient method could severely mislead the online-learning when the homogeneity is actually violated. We assume that there are two heterogeneous generating models in the observation, and propose the a new stochastic gradient method that mitigate the problem of the heterogeneous models. We introduce a robust mini-batch optimization method using statistical tests and investigate the convergence radius of the solution in the proposed method. Moreover, the theoretical results are confirmed by the numerical simulations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.3
• /
• pp.2172-2177
• /
• 2015

The DF-MZEP-CME (decision feedback - maximum zero-error probability for constant modulus errors) algorithm that makes the probability for constant modulus error (CME) close to zero and employs decision feedback (DF) structures shows more improved performance in channel distortion compensation. However the DF-MZEP-CME algorithm has a computational complexity proportional to a sample size for probability estimation and this property plays a role of an obstacle in practical implementation. In this paper, the gradient of DF-MZEP-CME is proposed to be estimated recursively and shown to solve the computational problem by making the algorithm independent of the sample size. For a sample size N, the conventional method has 10N multiplications but the proposed has only 20 regardless of N. Also the recursive gradient estimation for weight update is kept in continuity from the initial state to the steady state without any error propagation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.3C
• /
• pp.278-286
• /
• 2007

In this paper, an efficient algorithm is proposed for the interpolation of interlaced images. First of all, by efficiently estimating the directional spatial correlations of neighboring pixels, increased interpolation accuracy can be achieved. And then using the gradient vector which was obtained by Sobel operation, enables to consider the fine directional edges and make it possible to estimate the accurate direction of edges. In other words, it is possible to interpolate the interlaced images with considering the characteristics of images. In addition, by altering the conventional edge detector for the purpose of a easy De-interlacing and multiplying the optimal translation coefficients to each of the gradient vectors, an efficient interpolation for images can be achieved. Comparing with the conventional De-interlacing algorithms, proposed algorithm not only reduced the complexity but also estimated the accurate edge direction and the proposed scheme have been clearly verified that it enhances the objective and subjective image quality by the extensive simulations for various images.

• Atmosphere
• /
• v.27 no.2
• /
• pp.119-131
• /
• 2017

We present and discuss the Tropopause Folding Turbulence Detection (TFTD) algorithm for the Korean Communication, Ocean, Meteorological Satellite (COMS) which is originally developed for the Tropopause Folding Turbulence Product (TFTP) from the Geostationary Operational Environmental Satellite (GOES)-R. The TFTD algorithm assumes that the tropopause folding is linked to the Clear Air Turbulence (CAT), and thereby the tropopause folding areas are detected from the rapid spatial gradients of the upper tropospheric specific humidity. The Layer Averaged Specific Humidity (LASH) is used to represent the upper tropospheric specific humidity calculated using COMS $6.7{\mu}m$ water vapor channel and ERA-interim reanalysis temperature at 300, 400, and 500 hPa. The comparison of LASH with the numerical model specific humidity shows a strong negative correlation of 80% or more. We apply the single threshold, which is determined from sensitivity analysis, for cloud-clearing to overcome strong gradient of LASH at the edge of clouds. The tropopause break lines are detected from the location of strong LASH-gradient using the Canny edge detection based on the image processing technique. The tropopause folding area is defined by expanding the break lines by 2-degree positive gradient direction. The validations of COMS TFTD is performed with Pilot Reports (PIREPs) filtered out Convective Induced Turbulence (CIT) from Dec 2013 to Nov 2014 over the South Korea. The score test shows 0.49 PODy (Probability of Detection 'Yes') and 0.64 PODn (Probability of Detection 'No'). Low POD results from various kinds of CAT reported from PIREPs and the characteristics of high sensitivity in edge detection algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.5
• /
• pp.3132-3138
• /
• 2014

In many communication systems, intersymbol interference, DC and impulsive noise are hard-to-solve problems. For the purpose of cancelling such interferences, the concept of lagged cross-correlation of probability has been used for blind equalization. However, this algorithm has a large burden of computation. In this paper, a recursive method of the algorithm based on the lagged probability correlation is proposed. The summation operation in the calculation of gradient of the cost is transformed into a recursive gradient calculation. The recursive method shows to reduce the high computational complexity of the algorithm from O(NM) to O(M) for M symbols and N block data having advantages in implementation while keeping the robustness against those interferences. From the results of the simulation, the proposed method yields the same learning performance with reduced computation complexity.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.4
• /
• pp.21-34
• /
• 2023

Federated Learning is divided into synchronous federated learning and asynchronous federated learning. Asynchronous federated learning has a time advantage over synchronous federated learning, but asynchronous federated learning still has some challenges to obtain better performance. In particular, preventing performance degradation in non-IID training datasets, selecting appropriate clients, and managing stale gradient information are important for improving model performance. In this paper, we deal with K-asynchronous federated learning by using non-IID datasets. In addition, unlike traditional method using static K, we proposed an algorithm that adaptively adjusts K and we can reduce the learning time. Additionally, the we show that model performance is improved by using stale gradient handling method. Finally, we use a method of judging model performance to obtain strong model stability. Experiment results show that overall algorithm can obtain advantages of reducing training time, improving model accuracy, and improving model stability.

• Korean Journal of Mathematics
• /
• v.6 no.1
• /
• pp.27-46
• /
• 1998

We are concerned with an optimal control problem governed by a Poisson equation in which body force acts like a control parameter. The cost functional to be optimized is taken to represent the error from the desired observation and the cost due to the control. We recast the problem into the mixed formulation to take advantage of the minimax principle for the duality method. The existence of a saddle point for the Lagrangian shall be shown and the optimality system will be derived therein. Finally, to attain an optimal control, we combine the optimality system with an operational technique. By achieving the gradient of the cost functional, a convergent algorithm based on the projected gradient method is established.

• Transactions on Control, Automation and Systems Engineering
• /
• v.1 no.1
• /
• pp.8-15
• /
• 1999

One of the main reason advocating redundant manipulators' superiority in application is that they can afford to optimize a dexterity measure, for example the manipulability measure. However, to obtain the gradient of the manipulability is not an easy task in case of general manipulator with high degrees of redundancy. This article proposes a method to compute the gradient of the manipulability, based on recursive algorithm to compute the Jacobian and its derivative using Denavit-Hartenberg parameters only. To characterize the null motion of redundant manipulators, the null space matrix using square minors of the Jacobian is also proposed. With these capabilities, the inverse kinematics of a redundant manipulator system can be done automatically. The result is easily extended to dual manipulator system using the relative kinematics.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.525-528
• /
• 1999

Abstract - In this paper, a segmentation method for brain Magnetic Resonance(MR) image using region clustering technique with statistical distribution of gradient image and fuzzy rules is described. The brain MRI consists of gray matter and white matter, cerebrospinal fluid. But due to noise, overlap, vagueness, and various parameters, segmentation of MR image is a very difficult task. We use gradient information rather than intensity directly from the MR images and find appropriate thresholds for region classification using gradient approximation, rayleigh distribution function, region clustering, and merging techniques. And then, we propose the adaptive fuzzy rules in order to extract anatomical structures and diseases from brain MR image data. The experimental results shows that the proposed segmentation algorithm given better performance than traditional segmentation techniques.

• Smart Structures and Systems
• /
• v.18 no.5
• /
• pp.839-864
• /
• 2016

This paper presents an efficient method for updating the structural finite element model. Model updating is performed through minimizing the difference between the recorded acceleration of a real damaged structure and a hypothetical damaged one. This is performed by updating physical parameters (module of elasticity in this study) in each step using iterative process of modified nonlinear conjugate gradient (M-NCG) and modified Broyden-Fletcher-Goldfarb-Shanno algorithm (M-BFGS) separately. These algorithms are based on sensitivity analysis and provide a solution for nonlinear damage detection problem. Three illustrative test examples are considered to assess the performance of the proposed method. Finally, it is demonstrated that the proposed method is satisfactory for detecting the location and ratio of structural damage in presence of noise.