• Proceedings of the Korea Association of Information Systems Conference
• /
• 2002.11a
• /
• pp.289-312
• /
• 2002

This study suggests the Link weight analysis approach to choose input variables and an integrated model to make more accurate bankruptcy prediction model. the Link weight analysis approach is a method to choose input variables to analyze each input node's link weight which is the absolute value of link weight between an input nodes and a hidden layer. There are the weak-linked neurons elimination method, the strong-linked neurons selection method in the link weight analysis approach. The Integrated Model is a combined type adapting Bagging method that uses the average value of the four models, the optimal weak-linked-neurons elimination method, optimal strong-linked neurons selection method, decision-making tree model, and MDA. As a result, the methods suggested in this study - the optimal strong-linked neurons selection method, the optimal weak-linked neurons elimination method, and the integrated model - show much higher accuracy than MDA and decision making tree model. Especially the integrated model shows much higher accuracy than MDA and decision making tree model and shows slightly higher accuracy than the optimal weak-linked neurons elimination method and the optimal strong-linked neurons selection method.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.321-323
• /
• 1998

이 논문에서는 크기가 큰 III-Conditioned Matrices 정방행렬의 좌측 또는 우측 역행렬 계산시 계산상의 정확도를 향상시키는 알고리듬에 대하여 기술한다. 이 알고리듬은 대상 행렬의 행벡터들을 Input으로 하고 해당 Input 벡터가 몇번째 행 벡터인지를 나타내는 단위 벡터를 Target 벡터로 하며 초기 Weight 값으로 Pivoting을 겸한 Gauss소거법을 적용하여 얻은 역행렬을 사용하는 Single Layer 인공신경망에 적용하는 역전파 알고리듬과 흡사한 것이다. 각각의 Input 행 벡터에 대하여 역행렬의 열 벡터들이 점진적으로 직교가 되거나 평행이 되도록 근접시키므로써 모든 Input 행 벡터들이 열벡터들에 비교적 균일하게 직교 또는 평행이 되도록 학습시키는 알고리듬이다.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.3
• /
• pp.90-101
• /
• 2000

In this paper, we propose a controller for differentially steered wheeled mobile robots. The controller uses input-output linearization algorithm and artificial neural network to stabilize the dynamic model and compensate uncertainties. The proposed neural network part has 6 inputs, 1 hidden layer, 2 torque outputs and features fast online learning and good performance on structure error learning basis. Simulation results show that the proposed controller perform precisely tracking of reference path and is robust to uncertainties.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.42.2-42
• /
• 2002

We discuss a neural network solver for the inverse optimization problem. The problem is that find functional relations between input and output data, which are include defects. Finding the relations, predictions of the defect parts are also required. The part of finding the defects in the input data is an inverse problem . We consider the meanings to solve the problem on the neural network system at first. Next, we consider the network structure of the system, the learning scheme of the network, and at last, examine the precision on the numerical calculations. In the paper, we proposed the high-precision learning method for plural three-layer neural network system that is series-connect...

• Journal of Biomedical Engineering Research
• /
• v.10 no.3
• /
• pp.343-350
• /
• 1989

A new algorithm classifying ECG Arrhythmia signals using Back-propagation network is proposed. The base-line of ECG signal is detected by high pass filter and probability density function then input data are normalized for learning and classifying. In addition, ECG data are scanned to classify Arrhythmia signal which is hard to find R-wave. A two-layer perceptron with one hidden layer along with error back-propagation learning rule is utilized as an artificial neural network. The proposed algorithm shows outstanding performance under circumstances of amplitude variation, baseline wander and noise contamination.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.338-341
• /
• 2003

TIn this study, by formulating input layer, category later, and output layer from data, and in using TAM(Topographic Attentive Mapping) network that created fuzzy rule, it categorized into companies went bankrupt with finances in the black figures, and in the red figures.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.72-72
• /
• 2000

This paper presents a methodology combining sliding mode control and fuzzy control to tune the boundary layer and input gain according to the system state. The equivalent control is designed such that the nominal system exhibits desirable dynamics, The robust control with fuzzy self-tuning is then developed to guarantee the reaching condition and reduce chattering phenomenon in the presence of parameter and disturbance uncertainties.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.341-344
• /
• 2002

음성은 화자들의 특징을 가지고 있다. 이 논문에서는 신경망에 기초한 Incremental Learning을 이용하여 화자인식시스템을 소개한다. 컴퓨터를 통하여 녹음된 문장들은 FFT를 거치면서 Frequency 영역으로 바뀌고, 모음들의 특징을 가지고 있는 Formant를 이용하여 모음들을 추출한다. 추출된 모음들은 LPC처리를 통하여 화자의 특성을 가지고 있는 Coefficient값들을 얻는다. LPCC과정과 Vector Quantization을 통해 10개의 특징 점들은 학습을 위한 Input으로 들어가고 화자 수에 따라 증가되는 Hidden Layer와 Output Layer들을 가지고 있는 신경망을 통해 화자인식을 수행한다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.109-118
• /
• 2023

Data-based analysis methods have become used more for estimating or predicting housing prices, and neural network models and decision trees in the field of big data are also widely used more and more. Neural network models are often evaluated to be superior to existing statistical models in terms of estimation or prediction accuracy. However, there is ambiguity in determining the input feature of the input layer of the neural network model, that is, the type and number of input features, and decision trees are sometimes used to overcome these disadvantages. In this paper, we evaluate the existing methods of using decision trees and propose the method of using decision trees to prioritize input feature selection in neural network models. This can be a complementary or combined analysis method of the neural network model and decision tree, and the validity was confirmed by applying the proposed method to house price estimation. Through several comparisons, it has been summarized that the selection of appropriate input characteristics according to priority can increase the estimation power of the model.

• Nuclear Engineering and Technology
• /
• v.34 no.6
• /
• pp.553-565
• /
• 2002

In this paper, the robust control scheme with the improved control performance within the boundary layer is proposed. In the control scheme, the robust controller based on the traditional variable structure control method is modified to have the adaptation within the boundary layer. From this controller, the width of the boundary layer where the robust control input is smoothened out can be given by an appropriate value. But the improved control performance within the boundary layer can be achieved without the so-called control chattering because the role of adaptive control is to compensate for the uncovered portions of the robust control occurred from the continuous approximation within the boundary layer Simulation tests for circular navigation of an underwater wall-ranging robot developed for inspection of wall surfaces in the research reactor, TRIGA MARK III, confirm the performance improvement. Notational Conventions Vectors are written in boldface roman lower-case letters, e.g., x and y. Matrices are written in upper-case roman letters, e.g., G and B. And ∥.∥ means the Euclidean norm.