• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.14-20
• /
• 2018

The purpose of training a convolutional neural network (CNN) is to obtain weight factors that give high classification accuracies. The initial values of hyper-parameters affect the training results, and it is important to train a CNN with a suitable hyper-parameter set of a learning rate, a batch size, the initialization of weight factors, and an optimizer. We investigate the effects of a single hyper-parameter while others are fixed in order to obtain a hyper-parameter set that gives higher classification accuracies and requires shorter training time using a proposed VGG-like CNN for training since the VGG is widely used. The CNN is trained for four datasets of CIFAR10, CIFAR100, GTSRB and DSDL-DB. The effects of the normalization and the data transformation for datasets are also investigated, and a training scheme using merged datasets is proposed.

• Journal of Korean Neurosurgical Society
• /
• v.67 no.1
• /
• pp.50-59
• /
• 2024

Objective : This study aimed to conduct a bibliometric analysis on pelvic parameter related research over the last 30 years, analyzing trends, hotspots, and influential works within this field. Methods : A comprehensive Web of Science database search was performed. The search yielded 3249 results, focusing on articles and reviews published from 1992 to 2022 in English. Data was analyzed using CiteSpace and VOSviewer for keyword, authorship, and citation burst analysis, co-citation analysis, and clustering. Results : The number of publications and citations related to pelvic parameters has increased exponentially over the last 30 years. The USA leads in publication count with 1003 articles. Top publishing journals include the European Spine Journal, Spine, and Journal of Neurosurgery: Spine, with significant contributions by Schwab, Lafage V, and Protoptaltis. The most influential articles were identified using centrality and sigma values, indicating their role as key articles within the field. Research hotspots included spinal deformity, total hip arthroplasty, and sagittal alignment. Conclusion : Interest in pelvic parameter related research has grown significantly over the last three decades, indicating its relevance in modern orthopedics. The most influential works within this field have contributed to our understanding of spinal deformity, pelvic incidence, and their relation to total hip arthroplasty. This study provides a comprehensive overview of the trends and influential research in the field of pelvic parameters.

• Journal of Practical Engineering Education
• /
• v.13 no.2
• /
• pp.233-242
• /
• 2021

In this paper, as a liberal arts course for non-majors, we proposed a supervised learning artificial neural network parameter optimization method and a basic education method for activation function to design a basic artificial neural network subject curriculum. For this, a method of finding a parameter optimization solution in a spreadsheet without programming was applied. Through this training method, you can focus on the basic principles of artificial neural network operation and implementation. And, it is possible to increase the interest and educational effect of non-majors through the visualized data of the spreadsheet. The proposed contents consisted of artificial neurons with sigmoid and ReLU activation functions, supervised learning data generation, supervised learning artificial neural network configuration and parameter optimization, supervised learning artificial neural network implementation and performance analysis using spreadsheets, and education satisfaction analysis. In this paper, considering the optimization of negative parameters for the sigmoid neural network and the ReLU neuron artificial neural network, we propose a training method for the four performance analysis results on the parameter optimization of the artificial neural network, and conduct a training satisfaction analysis.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.18 no.1
• /
• pp.26-30
• /
• 2007

This practice parameter for non-pharmacological treatment for attention-deficit hyperactivity disorder (ADHD) review the domestic and international literature on the psychosocial treatment of children and adolescents with ADHD. This parameter include the parental training & education, cognitive behavior therapy(group or individual), social skill training, family therapy, play therapy (individual psychotherapy) and non-traditional therapy (art therapy, herbal therapy et al). Among them, there is some proven evidence only in parental training & education and cognitive behavior therapy. So, this parameter describes some details only in the field of parental training & education and cognitive behavior therapy. The efficacy or effectiveness, especially, cost-effectiveness of specific psychosocial treatment method for ADHD cannot be fairly assessed due to the scarcity of controlled clinical data. Based on the clinical expert consensus and limited evidence, we cautiously suggest the practice recommendations about the non-pharmacological psychosocial treatment fur children and adolescents with ADHD.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.2
• /
• pp.54.2-54.2
• /
• 2016

We present a machine learning approach to estimating stellar atmospheric parameters, effective temperature (Teff), surface gravity (log g), and metallicity ([Fe/H]) for stars observed during the course of the Sloan Digital Sky Survey (SDSS). For training a neural network, we randomly sampled the SDSS data with stellar parameters available from SEGUE Stellar Parameter Pipeline (SSPP) to cover the parameter space as wide as possible. We selected stars that are not included in the training sample as validation sample to determine the accuracy and precision of each parameter. We also divided the training and validation samples into four groups that cover signal-to-noise ratio (S/N) of 10-20, 20-30, 30-50, and over 50 to assess the effect of S/N on the parameter estimation. We find from the comparison of the network-driven parameters with the SSPP ones the range of the uncertainties of 73~123 K in Teff, 0.18~0.42 dex in log g, and 0.12~0.25 dex in [Fe/H], respectively, depending on the S/N range adopted. We conclude that these precisions are high enough to study the chemical and kinematic properties of the Galactic disk and halo stars, and we will attempt to apply this technique to Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), which plans to obtain about 8 million stellar spectra, in order to estimate stellar parameters.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.173-176
• /
• 2001

This paper proposes training algorithms of neuro-fuzzy systems. First, we introduce a structure training algorithm, which produces the necessary number of hidden nodes from training data. From this algorithm, initial fuzzy rules are also obtained. Second, the parameter training algorithm using evolution strategy is introduced. In order to show their usefulness, we apply our neuro-fuzzy system to a nonlinear system identification problem. It was found from experiments that proposed training algorithms works well.

• Journal of information and communication convergence engineering
• /
• v.8 no.3
• /
• pp.267-272
• /
• 2010

For the last decade, recurrent neural networks (RNNs) have been commonly applied to communications channel equalization. The major problems of gradient-based learning techniques, employed to train recurrent neural networks are slow convergence rates and long training sequences. In high-speed communications system, short training symbols and fast convergence speed are essentially required. In this paper, the derivative-free Kalman filter, so called the unscented Kalman filter (UKF), for training a fully connected RNN is presented in a state-space formulation of the system. The main features of the proposed recurrent neural equalizer are fast convergence speed and good performance using relatively short training symbols without the derivative computation. Through experiments of nonlinear channel equalization, the performance of the RNN with a derivative-free Kalman filter is evaluated.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.195-200
• /
• 2004

In this paper we propose effective speech recognizer through two recognition experiments. In general, SVM is classification method which classify two class set by finding voluntary nonlinear boundary in vector space and possesses high classification performance under few training data number. In this paper we compare recognition performance of HMM and SVM at training data number and investigate recognition performance of each feature parameter while changing feature space of MFCC using Independent Component Analysis(ICA) and Principal Component Analysis(PCA). As a result of experiment, recognition performance of SVM is better than 1:.um under few training data number, and feature parameter by ICA showed the highest recognition performance because of superior linear classification.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.492-495
• /
• 2003

Fuzzy Min-Max Neural Network(FMMNN) is a powerful classifier, It has, however, some problems. Learning result depends on the presentation order of input data and the training parameter that limits the size of hyperbox. The latter problem affects the result seriously. In this paper, the new approach to alleviate that without loss of on-line learning ability is proposed. The committee machine is used to achieve the multi-resolution FMMNN. Each expert is a FMMNN with fixed training parameter. The advantages of small and large training parameters are used at the same time. The parameters are selected by performance and independence measures. The Decision of each expert is guided by the gating network. Therefore the regional and parametric divide and conquer scheme are used. Simulation shows that the proposed method has better classification performance.

• Journal of the Korean Geophysical Society
• /
• v.4 no.3
• /
• pp.175-182
• /
• 2001

We consider the problem of determining smoothing parameters of Gibbs priors for Bayesian methods used in the medical imaging application of emission tomographic reconstruction. We address a simple smoothing prior (membrane) whose global hyperparameter (the smoothing parameter) controls the bias/variance tradeoff of the solution. We base our maximum-likelihood (ML) estimates of hyperparameters on observed training data, and argue the motivation for this approach. Good results are obtained with a simple ML estimate of the smoothing parameter for the membrane prior.