• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.101-110
• /
• 2022

Histopathological analysis of biopsy specimens is still used for diagnosis and classifying the brain tumors today. The available procedures are intrusive, time consuming, and inclined to human error. To overcome these disadvantages, need of implementing a fully automated deep learning-based model to classify brain tumor into multiple classes. The proposed CNN model with an accuracy of 92.98 % for categorizing tumors into five classes such as normal tumor, glioma tumor, meningioma tumor, pituitary tumor, and metastatic tumor. Using the grid search optimization approach, all of the critical hyper parameters of suggested CNN framework were instantly assigned. Alex Net, Inception v3, Res Net -50, VGG -16, and Google - Net are all examples of cutting-edge CNN models that are compared to the suggested CNN model. Using huge, publicly available clinical datasets, satisfactory classification results were produced. Physicians and radiologists can use the suggested CNN model to confirm their first screening for brain tumor Multi-classification.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.1
• /
• pp.155-162
• /
• 2010

In this paper we propose a doubly penalized kernel method which estimates both the mean function and the variance function simultaneously by kernel machines for heteroscedastic autoregressive data. We also present the model selection method which employs the cross validation techniques for choosing the hyper-parameters which aect the performance of proposed method. Simulated examples are provided to indicate the usefulness of proposed method for the estimation of mean and variance functions.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.4
• /
• pp.765-775
• /
• 2010

For the accelerated failure time (AFT) model a lot of effort has been devoted to develop effective estimation methods. AFT model assumes a linear relationship between the logarithm of event time and covariates. In this paper we propose a semiparametric support vector machine to consider situations where the functional form of the effect of one or more covariates is unknown. The proposed estimating equation can be computed by a quadratic programming and a linear equation. We study the effect of several covariates on a censored response variable with an unknown probability distribution. We also provide a generalized approximate cross-validation method for choosing the hyper-parameters which affect the performance of the proposed approach. The proposed method is evaluated through simulations using the artificial example.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.2
• /
• pp.391-399
• /
• 2013

Partially linear regression is capable of providing more complete description of the linear and nonlinear relationships among random variables. In support vector regression (SVR) the hyper-parameters are known to affect the performance of regression. In this paper we propose an iterative reweighted least squares (IRWLS) procedure to solve the quadratic problem of partially linear support vector regression with a modified loss function, which enables us to use the generalized approximate cross validation function to select the hyper-parameters. Experimental results are then presented which illustrate the performance of the partially linear SVR using IRWLS procedure.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.925-931
• /
• 2009

In this paper we propose a variance function estimation method for replicated data based on averages of squared residuals obtained from estimated mean function by the least squares support vector machine. Newton-Raphson method is used to obtain associated parameter vector for the variance function estimation. Furthermore, the cross validation functions are introduced to select the hyper-parameters which affect the performance of the proposed estimation method. Experimental results are then presented which illustrate the performance of the proposed procedure.

• Communications for Statistical Applications and Methods
• /
• v.16 no.2
• /
• pp.383-388
• /
• 2009

In this paper we propose a variance function estimation method based on kernel trick for replicated data or data consisted of sample variances. Newton-Raphson method is used to obtain associated parameter vector. Furthermore, the generalized approximate cross validation function is introduced to select the hyper-parameters which affect the performance of the proposed variance function estimation method. Experimental results are then presented which illustrate the performance of the proposed procedure.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.379-382
• /
• 1997

We present a hybrid self-tuning method using hyper elliptic Gaussian membership function. The proposed method applies a GA to identify the structure and the parameters of a fuzzy inference system. The parameters obtained by a GA, however, are near optimal solutions. So we solve this problem through a backpropagation-type gradient method. It is called GA hybrid self-tuning method in this paper. We provide a numerical example to evaluate the advantage and effectiveness of the proposed approach and compare with the conventional method.

• Nuclear Engineering and Technology
• /
• v.48 no.3
• /
• pp.778-784
• /
• 2016

HyperGam-U was recently developed to determine uranium enrichment based on ${\gamma}$- and X-ray spectroscopy analysis. The $XK_{\alpha}$ region of the uranium spectrum contains 13 peaks for $^{235}U$ and $^{238}U$ and is used mainly for analysis. To describe the X-ray peaks, a Lorentzian broadened shape function was used, and methods were developed to reduce the number of fitting parameters for decomposing the strongly overlapping peaks using channel-energy, energy-width, and energy-efficiency calibration functions. For validation, eight certified reference material uranium samples covering uranium enrichments from 1% to 99% were measured using a high-resolution planar high-purity germanium detector and analyzed using the HyperGam-U code. When corrections for the attenuation and true coincidence summing were performed for the detection geometry in this experiment, the goodness of fit was improved by a few percent. The enrichment bias in this study did not exceed 2% compared with the certified values for all measured samples.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.47-55
• /
• 2020

In this paper, we propose one stage multi-scale face detector based Fully Convolution Network using anchor free method. Recently almost all state-of-the-art face detectors which predict location of faces using anchor-based methods rely on pre-defined anchor boxes. However this face detectors need to hyper-parameters and additional computation in training. The key idea of the proposed method is to eliminate hyper-parameters and additional computation using anchor free method. To do this, we apply two ideas. First, by eliminating the pre-defined set of anchor boxes, we avoid the additional computation and hyper-parameters related to anchor boxes. Second, our detector predicts location of faces using multi-feature maps to reduce foreground/background imbalance issue. Through Quantitative evaluation, the performance of the proposed method is evaluated and analyzed. Experimental results on the FDDB dataset demonstrate the effective of our proposed method.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.709-715
• /
• 2023

In this study, the performance evaluation of image quality for noise reduction was implemented using the U-net deep learning architecture in computed tomography (CT) images. In order to generate input data, the Gaussian noise was applied to ground truth (GT) data, and datasets were consisted of 8:1:1 ratio of train, validation, and test sets among 1300 CT images. The Adagrad, Adam, and AdamW were used as optimizer function, and 10, 50 and 100 times for number of epochs were applied. In addition, learning rates of 0.01, 0.001, and 0.0001 were applied using the U-net deep learning model to compare the output image quality. To analyze the quantitative values, the peak signal to noise ratio (PSNR) and coefficient of variation (COV) were calculated. Based on the results, deep learning model was useful for noise reduction. We suggested that optimized hyper parameters for noise reduction in CT images were AdamW optimizer function, 100 times number of epochs and 0.0001 learning rates.