• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2005.10a
• /
• pp.327-332
• /
• 2005

This paper aims to analysis for evaluation factor and success prediction of port innovative cluster. This paper is divided three factors such ac policy, source and operation. In addition, three factors are divided into the twelve detail factors. the weight of each factor is calculated by Kohonen Network. At the result, this paper places the priority on the source factor.

• Journal of Navigation and Port Research
• /
• v.30 no.1 s.107
• /
• pp.45-51
• /
• 2006

This paper aims to analysis on evaluation factor for success of port innovative cluster. This paper is divided three factors such ac policy, source and operation In addition, three factors are divided into the twelve detail factors. From a total of 30 survey cases, 50 percent randomly selected as the training group and the other 50 percent as the validation group. cases in the training group were used in the development of the Kohonen Network The validation group was used to test the performance of this model. The major findings may be summarized as follows; The prediction accuracy rate is $73.33\%$ The weight of real root and detail factors is calculated by Kohonen Network At the result, success prediction group of port innovative cluster, this paper places the priority on the source factor.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.2
• /
• pp.141-148
• /
• 2011

This study presents the optimal grouping technique of columns which groups together columns of similar shortening trends to improve the efficiency of column shortening compensation. Here, Kohonen's self-organizing feature map which can classify patterns of input data by itself with unsupervised learning was used as the optimal grouping algorithm. The Kohonen network applied in this study is composed of two input neurons and variable output neurons, here the number of output neuron is equal to the column groups to be classified. In input neurons the normalized mean and standard deviation of shortening of each columns are inputted and in the output neurons the classified column groups are presented. The applicability of the proposed algorithm was evaluated by applying it to the two buildings where column shortening analyses had already been performed. The proposed algorithm was able to classify columns with similar shortening trends as one group, and from this we were able to ascertain the field-applicability of the proposed algorithm as the optimal grouping of column shortening.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.5
• /
• pp.21-28
• /
• 2002

With the proliferation of internet and an increase in internet users, several kinds of vast information are provided to users on the internet. It is increasing in the need of personalization service by filtering user preferred news among various news documents provided through several news servers.. In this paper, we implemented a filtering agent system to meet to demand for personalized news service. In the proposed system, Kohonen network is used to train keywords provided by users and to classify news groups. Resulting from that, the personalized new service is achieved. After we trained and tested the filtering agent, we could provide users news groups with their intention.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.571-574
• /
• 2001

In our paper, We propose an efficient adaptive coding method using kohonen neural network. An efficient adaptive encoding method using Kohonen net work is discribed through the analysis of those compression methods with the application of the neural network. In order to increase the compression ratio, a image is first divided into 8*8 subimages, then all subimages are transformed by DCT. These DCT sub-blocks are divided into N(4) classes by Kohonen network. Hits are distributed according to the variance of the DCT sub-block. Thus we get N(4)bit allocation matrices. Excellent performance is shown by the computer simulation. so we found that our proposed method is better then classifing subimages by AC energy.

• The Journal of Information Technology
• /
• v.7 no.3
• /
• pp.11-18
• /
• 2004

Learning procedure in the neural network is updating of weights between neurons. Unadequate initial learning coefficient causes excessive iterations of learning process or incorrect learning results and degrades learning efficiency. In this paper, adaptive learning algorithm is proposed to increase the efficient in the learning algorithms of Self-Organization Neural Networks. The algorithm updates the weights adaptively when learning procedure runs. To prove the efficiency the algorithm is experimented to classification of strokes which is the reference handwritten character. The result shows improved classification rate about 1.44~3.65% proposed method compare with Kohonan and Mao's algorithms, in this paper.

• The Journal of Information Technology
• /
• v.8 no.1
• /
• pp.119-124
• /
• 2005

Learning procedure in the neural network is updating of weights between neurons. Unadequate initial learning coefficient causes excessive iterations of learning process or incorrect learning results and degrades learning efficiency. In this paper, adaptive learning algorithm is proposed to increase the efficient in the learning algorithms of Kohonens Self-Organization Neural networks. The algorithm updates the weights adaptively when learning procedure runs. To prove the efficiency the algorithm is experimented to clustering of the random weight. The result shows improved learning rate about 42~55% ; less iteration counts with correct answer.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.401-404
• /
• 2004

본 연구에서는 다양한 뉴스그룹들 중에서 사용자의 취향과 유사한 뉴스그룹들을 코호넨 신경망을 이용하여 추천해주는 방법을 제시한다. 신경망을 학습시키기 위한 뉴스 문서의 키워드들을 선택하기 위해 여러 문서들로부터 후보 용어들을 추출하고 퍼지 추론을 적용하여 대표 용어들을 선택한다. 하지만 신경망의 학습패턴을 관찰해 보면, 맡은 부분이 비어있는 희소성 문제를 발견할 수 있다. 이에 본 연구에서는 통계적인 결정계수를 도입하여 불필요한 차원을 제거한 후 신경망을 학습시키는 새로운 방법을 제안한다. 제안된 방법은 모든 차원을 활용할 때 보다 클러스터내 거리와 클러스터간 거리의 척도를 이용한 클러스터 중첩도 면에서 우수한 분류 성능을 보여줌을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.274-276
• /
• 2002

With the proliferation of internet, it is increasingly needed to realize personalized news filtering service reflecting user's interest. In this Paper, we implement a filtering agent for Personalized news service. In the proposed system, Kohonen network for an unsupervised learning is used to train keywords provided by users and the personalization is achieved by using the trained neural network. After we trained and tested our filtering agent we could provide users news groups considering their interests.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.289-294
• /
• 2015

This paper proposes an autonomous machine learning method applicable to the BCI(Brain-Computer Interface) is based on the self-organizing Kohonen method, one of the exemplary method of unsupervised learning. In addition we propose control method of learning region and self machine learning rule using an interactive function. The learning region control and machine learning was used to control the side effects caused by interaction function that is based on the self-organizing Kohonen method. After determining the winner neuron, we decided to adjust the connection weights based on the learning rules, and learning region is gradually decreased as the number of learning is increased by the learning. So we proposed the autonomous machine learning to reach to the network equilibrium state by reducing the flow toward the input to weights of output layer neurons.