• 전기전자학회논문지
• /
• 제22권1호
• /
• 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
• /
• 제67권1호
• /
• 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.

• 실천공학교육논문지
• /
• 제13권2호
• /
• pp.233-242
• /
• 2021

본 논문에서는 비전공자들을 위한 교양과정으로, 기초 인공신경망 과목 커리큘럼을 설계하기 위해, 지도학습 인공신경망 매개변수 최적화 방법과 활성화함수에 대한 기초 교육 방법을 제안하였다. 이를 위해, 프로그래밍 없이, 매개 변수 최적화 해를 스프레드시트로 찾는 방법을 적용하였다. 본 교육 방법을 통해, 인공신경망 동작 및 구현의 기초 원리 교육에 집중할 수 있다. 그리고, 스프레드시트의 시각화된 데이터를 통해 비전공자들의 관심과 교육 효과를 높일 수 있다. 제안한 내용은 인공뉴런과 Sigmoid, ReLU 활성화 함수, 지도학습데이터의 생성, 지도학습 인공신경망 구성과 매개변수 최적화, 스프레드시트를 이용한 지도학습 인공신경망 구현 및 성능 분석 그리고 교육 만족도 분석으로 구성되었다. 본 논문에서는 Sigmoid 뉴런 인공신경망과 ReLU 뉴런 인공신경망에 대해 음수허용 매개변수 최적화를 고려하여, 인공신경망 매개변수 최적화에 대한 네가지 성능분석결과를 교육하는 방법을 제안하고 교육 만족도 분석을 실시하였다.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제18권1호
• /
• 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.

• 천문학회보
• /
• 제41권2호
• /
• 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.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(3)
• /
• 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
• /
• 제8권3호
• /
• 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.

• 대한전자공학회논문지SP
• /
• 제41권3호
• /
• pp.195-200
• /
• 2004

본 논문은 두 가지 비교 실험을 통하여 효과적 음성인식 시스템을 제안한다. 분별적 이진 패턴 분류기인 SVM(Support Vector Machines)은 특징 공간에서 비선형 경계를 찾아 분류하는 방법으로 적은 학습 데이터에서도 좋은 분류 성능을 나타낸다고 알려져 있다. 본 논문에서는 학습데이터 수에 따른 HMM(Hidden Markov Model)과 SVM의 인식 성능을 비교하고, 최적의 특징 파라메터를 선택하기 위해 SVM을 이용하여 주성분해석과 독립성분분석을 적용하여 MFCC(Mel Frequency Cepstrum Coefficient)의 특징 공간을 변화시키면서 각각의 인식 성능을 비교 검토하였다. 실험 결과 SVM은 HMM에 비해 적은 학습데이터에서도 높은 인식 성능을 보여주었고, 독립성분분석에 의한 특징 파라메터가 특징 공간상에서의 높은 선형 분별성에 의해 다른 특징 파라메터보다 인식 성능에서 우수함을 확인 할 수 있었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• 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.

• 지구물리
• /
• 제4권3호
• /
• pp.175-182
• /
• 2001

본 논문에서는 의료영상의 응용분야로서 방출전산화단증 영상에 사용되는 베이지안 방법을 위한 Gibbs 사전정보의 평활 파라미터를 결정하는 문제를 다룬다. 특히, 광역 하이퍼파라미터(평활 파라미터)가 해외 편향과 분산의 균형을 조절하는 단순 평활사전정보(일명 멤브레인)를 연구 대상으로 한다. 본 논문에서 사용된 방법은 관측된 훈련데이터에 MI. 방법을 적용한 하이퍼파라미터 추정법에 기반을 두며, 이러한 접근방법에 대한 동기에 대하여도 논한다. 멤브레인 사전정보를 위한 평활 파라미터의 경우 단순한 ML 추정법을 적용하여도 파라미터가 쉽게 추정될 수 있음을 보인다.