• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.335-338
• /
• 2017

Currently Artificial Inteligence and Deep Learning are social issues, and These technologies are applied to various fields. A good method among the various algorithms in Artificial Inteligence is Convolutional Neural Network. Convolutional Neural Network is a form that adds convolution layers that extracts features by convolution operation on a general neural network method. If you use Convolutional Neural Network as small amount of data, or if the structure of layers is not complicated, you don't have to pay attention to speed. But the learning time is long as the size of the learning data is large and the structure of layers is complicated. So, GPU-based parallel processing is a lot. In this paper, we developed Convolutional Neural Network using CUDA and Learning speed is faster and more efficient than the method using the CPU.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.113-119
• /
• 2022

In software fault prediction, a multi classification model that predicts the fault severity category of a module can be much more useful than a binary classification model that simply predicts the presence or absence of faults. A small number of severity-based fault prediction models have been proposed, but no classifier using deep learning techniques has been proposed. In this paper, we construct MLP models with 3 or 5 hidden layers, and they have a structure with a fixed or variable number of hidden layer nodes. As a result of the model evaluation experiment, MLP-based deep learning models shows significantly better performance in both Accuracy and AUC than MLPs, which showed the best performance among models that did not use deep learning. In particular, the model structure with 3 hidden layers, 32 batch size, and 64 nodes shows the best performance.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.49-52
• /
• 1998

Neural Network has good performance in pattern classification, control and many other fields by learning ability. However, there is effective rule or systematic approach to determine optimal structure. In this paper, we propose a new method to find optimal structure of feed-forward multi-layer neural network as a kind of pruning method. That eliminating redundant elements of neural network. To find redundant elements we analysis error and weight changing with Rough Set Theory, in condition of executing back-propagation leaning algorithm.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.3
• /
• pp.159-165
• /
• 2021

This study introduces a topology optimization method for the simultaneous design of macro-scale structural configuration and unit structure variation to ensure effective heat conduction. Shape changes in the unit structure depending on its location within the macro-scale structure result in micro- as well as macro-scale design and enable better performance than using isotropic unit structures. They result in functionally graded composite structures combining both configurations. The representative volume element (RVE) method is applied to obtain various thermal conductivity properties of the multi-material based unit structure according to its shape change. Based on the RVE analysis results, the material properties of the unit structure having a certain shape can be derived using machine learning. Macro-scale topology optimization is performed using the traditional solid isotropic material with penalization method, while the unit structures composing the macro-structure can have various shapes to improve the heat conduction performance according to the simultaneous optimization process. Numerical examples of the thermal compliance minimization issue are provided to verify the effectiveness of the proposed method.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.378-388
• /
• 2000

In this paper, we propose Fuzzy Polynomial Neural Networks(FPNN) based on Polynomial Neural Networks(PNN) and Fuzzy Neural Networks(FNN) for model identification of complex and nonlinear systems. The proposed FPNN is generated from the mutually combined structure of both FNN and PNN. The one and the other are considered as the premise part and consequence part of FPNN structure respectively. As the consequence part of FPNN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. FPNN is available effectively for multi-input variables and high-order polynomial according to the combination of FNN with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. As the premise part of FPNN, FNN uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. And we use two kinds of FNN structure according to the division method of fuzzy space of input variables. One is basic FNN structure and uses fuzzy input space divided by each separated input variable, the other is modified FNN structure and uses fuzzy input space divided by mutually combined input variables. In order to evaluate the performance of proposed models, we use the nonlinear function and traffic route choice process. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously. And also performance index related to the approximation and prediction capabilities of model is evaluated and discussed.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.555-562
• /
• 2016

Semantic Role Labeling (SRL) is to determine the semantic relation of a predicate and its argu-ments in a sentence. But Korean semantic role labeling has faced on difficulty due to its different language structure compared to English, which makes it very hard to use appropriate approaches developed so far. That means that methods proposed so far could not show a satisfied perfor-mance, compared to English and Chinese. To complement these problems, we focus on suffix information analysis, such as josa (case suffix) and eomi (verbal ending) analysis. Korean lan-guage is one of the agglutinative languages, such as Japanese, which have well defined suffix structure in their words. The agglutinative languages could have free word order due to its de-veloped suffix structure. Also arguments with a single morpheme are then labeled with statistics. In addition, machine learning algorithms such as Support Vector Machine (SVM) and Condi-tional Random Fields (CRF) are used to model SRL problem on arguments that are not labeled at the suffix analysis phase. The proposed method is intended to reduce the range of argument instances to which machine learning approaches should be applied, resulting in uncertain and inaccurate role labeling. In experiments, we use 15,224 arguments and we are able to obtain approximately 83.24% f1-score, increased about 4.85% points compared to the state-of-the-art Korean SRL research.

• Journal of The Korean Association For Science Education
• /
• v.27 no.4
• /
• pp.346-353
• /
• 2007

In order to be efficient in teaching, a teacher should understand the current learner's level through diagnostic evaluation. This study has examined the major issues arising from the noble diagnostic assessment tool based on the theory of knowledge space. The knowledge state analysis method is actualizing the theory of knowledge space for practical use. The knowledge state analysis method is very advantageous when a certain group or individual student's knowledge structure is analyzed especially for strong hierarchical subjects such as mathematics, physics, chemistry, etc. Students' knowledge state helps design an efficient teaching plan by referring their hierarchical knowledge structure. The knowledge state analysis method can be enhanced by computer due to fast data processing. In addition, each student's knowledge can be improved effectively through individualistic feedback depending on individualized knowledge structure. In this study, we have developed a diagnostic assessment test for measuring student's learning outcome which is unattainable from the conventional examination. The diagnostic assessment test was administered to middle school students and analyzed by the knowledge state analysis method. The analyzed results show that students' knowledge structure after learning found to be more structured and well-defined than the knowledge structure before the learning.

• Journal of The Korean Association For Science Education
• /
• v.22 no.4
• /
• pp.796-805
• /
• 2002

This study examined the knowledge structure constructed by children before formal instruction, and successive changes in the structural complexity of knowledge during and after the learning of 'Structure and Function of Plant' unit. It also investigated how those changes were affected by children's learning modes. The researchers made the 5th graders draw the first draft of their concept map to see the pre-existing knowledge structure concerned with the unit and four more concept maps after completing every fourth lesson. And to see how long their knowledge structures were preserved, the researchers made children draw additional concept maps in 3 days, 3 months, and 7 months after completing the unit. Children drew their current concept maps on the basis of the previous one while learning the unit and without the previous one after completing the unit. Each concept map drawn by children showed the degree of their current understanding on the structures and functions of plants. The results revealed that only two levels of hierarchy and five relationships among the components of the first concept map(relationship, hierarchy, cross link and example) were proven to be valid in terms of conceptual relevance. Growth in the structural complexity of knowledge took place progressively throughout the unit and the effects of learning mode on the growth were favorably reflected in concept map scores of meaningful learners over time(relationship, cross link, example: p<.01, hierarchy: p<.05). Although there were some differences on the concept map scores between two types of learners, they commonly showed that knowledge restructuring had occurred apparently in the early periods from the 1st to the 6th lesson and had not occurred at all in the last period of the unit. The frequency of tuning was higher in rote learners than in meaningful learners throughout the unit, but the frequency of accretion was reverse. Concept map scores of rote learners constructed in the course of learning of the unit decreased little by little gradually in all the categories after completing the unit. However, the average total map score of meaningful learners increased a little more in 7 months than in 3 months after completing the unit. Therefore it can be inferred that meaningful learners construct more stable and well-differentiated knowledge structures than the rote learners.

• Journal of Educational Research in Mathematics
• /
• v.8 no.1
• /
• pp.327-350
• /
• 1998

The purpose of this study is to examine the applicability of educational games to open mathematic learning and consideration to the position of educational games in mathmatical education as powerful technology. For these purposes, previous literatures about games are reviewed. The concept of simulation games are defined and explore the characteristics of games includings game structure and process. And some typical educational games - Israel games, ORDA - are introduced. The main focus of the deliberation and survey of previous literatures is educational games as meaningful learning medium of mathematics and other subjuct matters. Especially educational games take a meaningful role for an implication of applicability of games especially for higher order thinking skills like problem solving, decision making, and creativity. To realize this alternative learning method of mathematics, first of all the attituce of teachers are have to change and accumulate field studies.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1296-1301
• /
• 2004

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision making in complex systems. The fuzzy -neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes learning approach of fuzzy-neural network by immune algorithm. The proposed learning model is presented in an immune based fuzzy-neural network (FNN) form which can handle linguistic knowledge by immune algorithm. The learning algorithm of an immune based FNN is composed of two phases. The first phase used to find the initial membership functions of the fuzzy neural network model. In the second phase, a new immune algorithm based optimization is proposed for tuning of membership functions and structure of the proposed model.