• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.9
• /
• pp.739-746
• /
• 1991

This paper develops a modified multilayer perceptron architecture which speeds up learning as well as the net's mapping accuracy. In Phase I, a cluster partitioning algorithm like the Kohonen's self-organizing feature map or the leader clustering algorithm is used as the front end that determines the cluster to which the input data belongs. In Phase II, this cluster selects a subset of the hidden layer nodes that combines the input and outputs nodes into a subnet of the full scale backpropagation network. The proposed net has been applied to two mapping problems, one rather smooth and the other highly nonlinear. Namely, the inverse kinematic problem for a 3-link robot manipulator and the 5-bit parity mapping have been chosen as examples. The results demonstrate the proposed net's superior accuracy and convergence properties over the original backpropagation network or its existing improvement techniques.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.05a
• /
• pp.186-189
• /
• 2005

본 논문에서는 LVQ를 퍼지화한 새로운 퍼지 학습 법칙들을 제안하였다. 퍼지 LVQ 학습법칙 1은 기존의 학습률 대신에 퍼지 학습률을 사용하였는데 이는 조건 확률의 퍼지화에 기반을 두고 있다. 퍼지 LVQ 학습법칙 2는 클래스들 사이에 존재하는 입력벡터가 결정 경계선에 대한 정보를 더 가지고 있는 것을 반영한 것이다. 이 새로운 퍼지 학습 법칙들을 improved IAFC(Integrted Adaptive Fuzzy Clustering)신경회로망에 적용하였다. improved IAFC신경회로망은 ART-1 (Adaptive Resonance Theory)신경회로망과 Kohonen의 Self-Organizing Feature Map의 장점을 취합한 퍼지 신경회로망이다. 제안한 supervised IAFC 신경회로망 1과 supervised IAFC neural 신경회로망 2의 성능을 오류 역전파 신경회로망의 성능과 비교하기 위하여 iris 데이터를 사용하였는데 Supervised IAFC neural network 2가 오류 역전파 신경회로망보다 성능이 우수함을 보여주었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.372-372
• /
• 2000

In this paper, we propose Neuro Fuzzy Polynomial Networks(NFPN) based on Polynomial Neural Network(PNN) and Neuro-Fuzzy(NF) for model identification of complex and nonlinear systems. The proposed NFPN is generated from the mutually combined structure of both NF and PNN. The one and the other are considered as the premise part and consequence part of NFPN structure respectively. As the premise part of NFPN, NF 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. As the consequence part of NFPN, 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. NFPN is available effectively for multi-input variables and high-order polynomial according to the combination of NF with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. In order to evaluate the performance of proposed models, we use the nonlinear function. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously.

• Proceedings of the KIEE Conference
• /
• 2005.11a
• /
• pp.9-11
• /
• 2005

본 연구는 GIS 진단신뢰성 향상기술 개발을 목적으로, 16개의 인위적 결함을 이용하여 부분방전 신호를 발생시키고 검출하여 그 패턴인식 확률을 높이기 위하여 신경망에 Genetic Algorithm (GA) 을 적용하였다. 이를 위하여 다음과 같은 5가지 서로 다른 신경망 모델을 선택하였다: Back Propagation (BP), Jordan-Elman Network (JEN), Principal Component Analysis (PCA), Self-Organizing Feature Map (SOFM) 및 Support Vector Machine (SVM). 이와 같이 선택된 모델에 동일한 데이터를 학습 시키고 패턴인식 확률을 비교 및 분석하였다. 실험 결과에 의하면, BP의 인식률이 가장 높고 다음으로 JEN의 인식률이 높이 나타났으며, 후자의 경우 모든 결함에 대하여 정확한 패턴분류를 한 반면에 전자의 경우 1.8% 의 분류 오차가 발생하였다. 따라서 인식률이 높은 신경망이 더 정확한 패턴분류를 보장하지 못한다는 실험적 결과를 고려 할 때, 인식률이 높은 두 개의 모델을 선정하여 각각의 출력에 일정한 가중치를 주고 합산하여 새로운 출력을 얻는 방법을 제안한다.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2627-2629
• /
• 2003

In this paper, we propose a new architecture of Genetic Algorithms(GAs)-based Self-Organizing Polynomial Neural Networks(SOPNN). The conventional SOPNN is based on the extended Group Method of Data Handling(GMDH) method and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons (or nodes) located in each layer through a growth process of the network. Moreover it does not guarantee that the SOPNN generated through learning has the optimal network architecture. But the proposed GA-based SOPNN enable the architecture to be a structurally more optimized networks, and to be much more flexible and preferable neural network than the conventional SOPNN. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented with using nonlinear system data.

• Journal of Korea Port Economic Association
• /
• v.30 no.1
• /
• pp.23-55
• /
• 2014

The purpose of this paper is to show the clustering trend and to choose the clustering ports for 3 Korean ports(Busan, Incheon and Gwangyang Ports) by using the self organizing maps based on neural network(SOM) and Tier models for 38 Asian ports during 11 years(2001-2011) with 4 input variables(birth length, depth, total area, and number of crane) and 1 output variable(container TEU). The main empirical results of this paper are as follows. First, clustering results by using SOM show that 3 Korean ports[Busan(26.5%), Incheon(13.05%), and Gwangyang(22.95%) each]can increase the efficiency. Second, according to Tier model, Busan(Hongkong, Sanghai, Manila, and Singapore), Incheon(Aden, Ningbo, Dabao, and Bangkog), and Gwangyang(Aden, Ningbo, Bangkog, Hipa, Dubai, and Guangzhou) should be clustered with those ports in parentheses. Third, when both SOM and Tier models are mixed, (1) efficiency improvement of Busan Port is greater than those of Incheon and Gwangyang ports. (2) Incheon port has shown the slow improvement during 2001-2007, but after 2008, improvement speed was high. (3) improvement level of Gwangyang port was high during 2001-2003, but after 2004, improvement level was constantly decreased. The policy implication of this paper is that Korean port policy planner should introduce the SOM, and Tier models with the mixed two models when clustering among the Asian ports for enhancing the efficiency of inputs and outputs.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.887-890
• /
• 1993

By introducing the notion of constraint-oriented fuzzy inference, we will show that it provides us ways of fuzzy control methods that has abilities of adaptation, learning and self-organization. The basic supporting techniques behind these abilities are“hard”processing by Artificial Intelligence or traditional computational framework and“soft”processing by Neural Network or Genetic Algorithm techniques. The reason that these techniques can be incorporated to fuzzy control systems is that the notion of“constraint”itself has two fundamental properties, that is, the“modularity”property due to its declarativeness and the“logicality”property due to its two-valuedness. From the former property, the modularity property, decomposing and integrating constraints can be done easily and efficiently, which enables us to carry out the above“soft”processing. From the latter property, the logicality property, Qualitative Reasoning and Instance Generalization by Symbolic Reasoning an be carried out, thus enabling the“hard”processing.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.4
• /
• pp.37-47
• /
• 2003

In this paper. we propose a new digital watermarking technique which uses the self-similarity of OCT(Discrete Cosine Transform) coefficients for the ownership protection of an image, similar coefficients are classified by SOM(Self-Organizing Map) out of Neural Network. The watermark is inserted into the selected cluster among clusters which consist of coefficients. Generally, the inserted watermark in high frequency regions of an image is eliminated by the compression process such as JPEG compressions, and the inserted watermark in low frequency regions of an image causes the distortion of an image quality. Therefore, the watermark is inserted into the cluster that has many coefficients in the middle frequency regions. This algorithm reduces the distortion of an image quality because of inserting the watermark into an image according to the number of coefficients in selected cluster. To extract watermarks from the watermarked image, the selected cluster is used without an original image. In the experiment, the new proposed algorithm have a good quality and endure attacks(JPEG compressions, filtering. zoom in, zoom out, cropping, noises) very well.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.65-82
• /
• 2021

Stock market investors are generally split into foreign investors, institutional investors, and individual investors. Compared to individual investor groups, professional investor groups such as foreign investors have an advantage in information and financial power and, as a result, foreign investors are known to show good investment performance among market participants. The purpose of this study is to propose an investment strategy that combines investor-specific transaction information and machine learning, and to analyze the portfolio investment performance of the proposed model using actual stock price and investor-specific transaction data. The Korea Exchange offers daily information on the volume of purchase and sale of each investor to securities firms. We developed a data collection program in C# programming language using an API provided by Daishin Securities Cybosplus, and collected 151 out of 200 KOSPI stocks with daily opening price, closing price and investor-specific net purchase data from January 2, 2007 to July 31, 2017. The self-organizing map model is an artificial neural network that performs clustering by unsupervised learning and has been introduced by Teuvo Kohonen since 1984. We implement competition among intra-surface artificial neurons, and all connections are non-recursive artificial neural networks that go from bottom to top. It can also be expanded to multiple layers, although many fault layers are commonly used. Linear functions are used by active functions of artificial nerve cells, and learning rules use Instar rules as well as general competitive learning. The core of the backpropagation model is the model that performs classification by supervised learning as an artificial neural network. We grouped and transformed investor-specific transaction volume data to learn backpropagation models through the self-organizing map model of artificial neural networks. As a result of the estimation of verification data through training, the portfolios were rebalanced monthly. For performance analysis, a passive portfolio was designated and the KOSPI 200 and KOSPI index returns for proxies on market returns were also obtained. Performance analysis was conducted using the equally-weighted portfolio return, compound interest rate, annual return, Maximum Draw Down, standard deviation, and Sharpe Ratio. Buy and hold returns of the top 10 market capitalization stocks are designated as a benchmark. Buy and hold strategy is the best strategy under the efficient market hypothesis. The prediction rate of learning data using backpropagation model was significantly high at 96.61%, while the prediction rate of verification data was also relatively high in the results of the 57.1% verification data. The performance evaluation of self-organizing map grouping can be determined as a result of a backpropagation model. This is because if the grouping results of the self-organizing map model had been poor, the learning results of the backpropagation model would have been poor. In this way, the performance assessment of machine learning is judged to be better learned than previous studies. Our portfolio doubled the return on the benchmark and performed better than the market returns on the KOSPI and KOSPI 200 indexes. In contrast to the benchmark, the MDD and standard deviation for portfolio risk indicators also showed better results. The Sharpe Ratio performed higher than benchmarks and stock market indexes. Through this, we presented the direction of portfolio composition program using machine learning and investor-specific transaction information and showed that it can be used to develop programs for real stock investment. The return is the result of monthly portfolio composition and asset rebalancing to the same proportion. Better outcomes are predicted when forming a monthly portfolio if the system is enforced by rebalancing the suggested stocks continuously without selling and re-buying it. Therefore, real transactions appear to be relevant.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.58-65
• /
• 2003

This paper studies a steering control method using a neural network algorithm for an intelligent autonomous driving robot. Previous horizontal steering control methods were made by various possible situation on the road. However, it isn't possible to make out algorithms that consider all sudden variances on the road. In this paper, an intelligent steering control algorithm for an autonomous driving robot system is presented. The algorithm is based on Self Organizing Maps(SOM) and the feature points on the road are used as training datum. In a simulation test, it is available to handle a steering control using SOM for an autonomous steering control. The algorithm is evaluated on an autonomous driving robot. The algorithm is available to control a steering for an autonomous driving robot with better performance at the experiments.