• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.627-632
• /
• 2021

ITL (information-theoretic learning) has been applied successfully to adaptive signal processing and machine learning applications, but there are difficulties in deciding the kernel size, which has a great impact on the system performance. The correntropy algorithm, one of the ITL methods, has superior properties of impulsive-noise robustness and channel-distortion compensation. On the other hand, it is also sensitive to the kernel sizes that can lead to system instability. In this paper, considering the sensitivity of the kernel size cubed in the denominator of the cost function slope, a new adaptive kernel estimation method using the rate of change in error power in respect to the kernel size variation is proposed for the correntropy algorithm. In a distortion-compensation experiment for impulsive-noise and multipath-distorted channel, the performance of the proposed kernel-adjusted correntropy algorithm was examined. The proposed method shows a two times faster convergence speed than the conventional algorithm with a fixed kernel size. In addition, the proposed algorithm converged appropriately for kernel sizes ranging from 2.0 to 6.0. Hence, the proposed method has a wide acceptable margin of initial kernel sizes.

• Journal of the Korean Society of Radiology
• /
• v.11 no.6
• /
• pp.443-451
• /
• 2017

The purpose of this study was to comparison of measure signal to noise ratio (SNR) according to change of kernel size from region of interest (ROI) of heart shadow in chest image. We examined images of chest image of 100 patients in a University-affiliated hospital, Seoul, Korea. Chest images of each patient were calculated by using ImageJ. We have analysis socio-demographical variables, SNR according to images, 95% confidence according to SNR of difference in a mean of SNR. Differences of SNR among change of equalization were tested by SPSS Statistics21 ANOVA test for there was statistical significance 95%(p<0.05). In SNR results, with the quality of distributions in the order of kernel size 9*9 image, kernel size 7*7 image and original chest image, kernel size 3*3 image (p<0.001). In conclusion, this study would be that quantitative evaluation of heart shadow on chest image can be used as an adjunct to the kernel size chest image.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.561-566
• /
• 2021

The optimum kernel size for error-distribution estimation with given error samples cannot be used in the weight adjustment of minimum Euclidean distance between error distributions (MED) algorithms. In this paper, a new adaptive kernel estimation method for convergence enhancement of MED algorithms is proposed. The proposed method uses the average rate of change in error power with respect to a small interval of the kernel width for weight adjustment of the MED learning algorithm. The proposed kernel adjustment method is applied to experiments in communication channel compensation, and performance improvement is demonstrated. Unlike the conventional method yielding a very small kernel calculated through optimum estimation of error distribution, the proposed method converges to an appropriate kernel size for weight adjustment of the MED algorithm. The experimental results confirm that the proposed kernel estimation method for MED can be considered a method that can solve the sensitivity problem from choosing an appropriate kernel size for the MED algorithm.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.40 no.6
• /
• pp.365-372
• /
• 2016

Using the computational fluid dynamics (CFD) technique, we simulated the fluid flow in a Taylor reactor considering the aggregation and breakage of particles. We calculated the population balance equation (PBE) to determine the particle-size distribution by implementing the quadrature method-of-moment (QMOM). It was used that six moments for an initial moments, the sum of Brownian kernel and turbulent kernel for aggregation kernel, and power-law kernel for breakage kernel. We predicted the final mean particle size when the particle had various initial volume fraction values. The result showed that the mean particle size and initial growth rate increased as the initial volume fraction of the particle increased.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.987-994
• /
• 2020

In this paper, we studied the effect of kernel size of CNN layer on performance in acoustic noise attenuators. This system uses a deep learning algorithm using a neural network adaptive prediction filter instead of using the existing adaptive filter. Speech is estimated from a single input speech signal containing noise using a 100-neuron, 16-filter CNN filter and an error back propagation algorithm. This is to use the quasi-periodic property in the voiced sound section of the voice signal. In this study, a simulation program using Tensorflow and Keras libraries was written and a simulation was performed to verify the performance of the noise attenuator for the kernel size. As a result of the simulation, when the kernel size is about 16, the MSE and MAE values are the smallest, and when the size is smaller or larger than 16, the MSE and MAE values increase. It can be seen that in the case of an speech signal, the features can be best captured when the kernel size is about 16.

• Progress in Medical Physics
• /
• v.15 no.2
• /
• pp.100-104
• /
• 2004

The detector size effect due to the spatial response of detectors is a critical source of inaccuracy in clinical dosimetry that has been the subject of numerous studies. Conventionally, the detector response kernel contains all the information about the influence that the detector size has on the measured beam profile. Various analytical models for this kernel have been proposed and studied in theoretical and experimental works. Herein, a method to simply determine the detector response kernel using the Monte Carlo simulation and convolution theory has been proposed. Based on this numerical method, the detector response kernel for a Farmer type ion chamber embedded in a water phantom has been obtained. The obtained kernel shows characteristics of both the pre-existing parabolic model proposed by Sibata et al. and the Gaussian model used by Garcia-Vicente et al. From this kernel and deconvolution technique, the detector size effect can be removed from measurements for 6MV, 10${\times}$10 $\textrm{cm}^2$ and 0.5${\times}$10 $\textrm{cm}^2$photon beams. The deconvolved beam profiles are in good agreements with the measurements performed by the film and pin-point ion chamber, with the exception of in the tail legion.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.714-720
• /
• 2021

The ITL (information theoretic learning) based on the kernel density estimation method that has successfully been applied to machine learning and signal processing applications has a drawback of severe sensitiveness in choosing proper kernel sizes. For the maximization of correntropy criterion (MCC) as one of the ITL-type criteria, several methods of adapting the remaining kernel size ( ) after removing the term have been studied. In this paper, it is shown that the main cause of sensitivity in choosing the kernel size derives from the term and that the adaptive adjustment of in the remaining terms leads to approach the absolute value of error, which prevents the weight adjustment from continuing. Thus, it is proposed that choosing an appropriate constant as the kernel size for the remaining terms is more effective. In addition, the experiment results when compared to the conventional algorithm show that the proposed method enhances learning performance by about 2dB of steady state MSE with the same convergence rate. In an experiment for channel models, the proposed method enhances performance by 4 dB so that the proposed method is more suitable for more complex or inferior conditions.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.137-141
• /
• 2009

We study on selecting the kernel weighting function in smoothing moment conditions for dependent processes. For hypothesis testing in Generalized Method of Moments or Generalized Empirical Likelihood context, we find that smoothing moment conditions by Bartlett kernel delivers smallest size distortions based on empirical Edgeworth expansions of the long-run variance estimator.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2004.11a
• /
• pp.36-38
• /
• 2004

The detector size effect due to the spatial response of defectors is one critical source of inaccuracy in clinical dosimetry and has been a subject of numerous studies. Conventionally, the detector response kernel contains all of the influence that the detector size has on the measured beam profile. Various analytic models for this kernel have been proposed and studied in theoretical and experimental works. Here, we use a method to determine detector response kernel simply by using Monte Carlo simulation and convolution theory. Based on this numerical method and DOSIMETER, an EGS4 Monte Carlo code, the detector response for a Farmer type ion chamber embedded in water phantom is obtained. There exists characteristic difference in the simulated chamber readings between one with carbon graphite wall and the other with Acrylic wail. Using the obtained response and the convolution theory, we are planning to derive the detector response kernel numerically and remove detector size effect from measurements for 6MV, 10${\times}$l0cm2 and 0.5${\times}$10 cm2 photon beam.

• Journal of the Korean Statistical Society
• /
• v.33 no.1
• /
• pp.59-78
• /
• 2004

A regression function in generalized linear model may have a discontinuity/change point at unknown location. In order to estimate the location of the discontinuity point and its jump size, the strategy is to use a nonparametric approach based on one-sided kernel weighted local-likelihood functions. Weak convergences of the proposed estimators are established. The finite-sample performances of the proposed estimators with practical aspects are illustrated by simulated examples.