• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.439-448
• /
• 2006

Previous recognition/clustering algorithms such as Kohonen SOM(Self-Organizing Map), MLP(Multi-Layer Percecptron) and SVM(Support Vector Machine) might not adapt to unexpected input pattern. And it's recognition rate depends highly on the complexity of own training patterns. We could make up for and improve the weak points with lowering complexity of original problem without losing original characteristics. There are so many ways to lower complexity of the problem, and we chose a kernel concepts as an approach to do it. In this paper, using a kernel concepts, original data are mapped to hyper-dimension space which is near infinite dimension. Therefore, transferred data into the hyper-dimension are distributed spasely rather than originally distributed so as to guarantee the rate to be risen. Estimating ratio of recognition is based on a new similarity-probing and learning method that are proposed in this paper. Using CEDAR DB which data is written in cursive letters, 0 to 9, we compare a recognition/clustering performance of kSOM that is proposed in this paper with previous SOM.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.429-438
• /
• 2006

Neural Networks(NNs) are applied for solving a wide variety of nonlinear problems in several areas, such as image processing, pattern recognition etc. Although NN can be simulated by using software, many potential NN applications required real-time processing. Thus they need to be implemented as hardware. The hardware implementation of multi-layer perceptrons(MLPs) in several kind of NNs usually uses a fixed-point arithmetic due to a simple logic operation and a shorter processing time compared to the floating-point arithmetic. However, the fixed-point arithmetic-based MLP has a drawback which is not able to apply the MLP software that use floating-point arithmetic. We propose a design method for MLPs which has the floating-point arithmetic-based fully-pipelining architecture. It has a processing speed that is proportional to the number of the hidden nodes. The number of input and output nodes of MLPs are generally constrained by given problems, but the number of hidden nodes can be optimized by user experiences. Thus our design method is using optimized number of hidden nodes in order to improve the processing speed, especially in field of a repeated processing such as image processing, pattern recognition, etc.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.71-78
• /
• 2011

This paper propose image steganalysis scheme based on independence between parent and child subband on the multi-layer wavelet domain. The proposed method decompose cover and stego images into 12 subbands by applying 3-level Haar UWT(Undecimated Wavelet Transform), analyze statistical independency between parent and child subband. Because this independency is appeared more difference in stego image than in cover image, we can use it as feature to differenciate between cover and stego image. Therefore we extract 72D features by calculation first 3 order statistical moments from joint characteristic function between parent and child subband. Multi-layer perceptron(MLP) is applied as classifier to discriminate between cover and stego image. We test the performance of proposed scheme over various embedding rates by the LSB, SS, BSS embedding method. The proposed scheme outperforms the previous schemes in detection rate to existence of hidden message as well as exactness of discrimination.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.3
• /
• pp.135-144
• /
• 2004

In this paper, we propose competitive fuzzy polynomial neurons-based advanced Self-Organizing Neural Networks(SONN) architecture for optimal model identification and discuss a comprehensive design methodology supporting its development. The proposed SONN dwells on the ideas of fuzzy rule-based computing and neural networks. And it consists of layers with activation nodes based on fuzzy inference rules and regression polynomial. Each activation node is presented as Fuzzy Polynomial Neuron(FPN) which includes either the simplified or regression polynomial fuzzy inference rules. As the form of the conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as linear, quadratic, and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership (unction are studied and the number of the premise input variables used in the rules depends on that of the inputs of its node in each layer. We introduce two kinds of SONN architectures, that is, the basic and modified one with both the generic and the advanced type. Here the basic and modified architecture depend on the number of input variables and the order of polynomial in each layer. The number of the layers and the nodes in each layer of the SONN are not predetermined, unlike in the case of the popular multi-layer perceptron structure, but these are generated in a dynamic way. The superiority and effectiveness of the Proposed SONN architecture is demonstrated through two representative numerical examples.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.45-51
• /
• 2020

Recently, many games provide data related to the users' game play, and there have been a few studies that predict opponent move by combining machine learning methods. This study predicts opponent move using match data of a real-time strategy game named ClashRoyale and a multi-label classification based on machine learning. In the initial experiment, binary card properties, binary card coordinates, and normalized time information are input, and card type and card coordinates are predicted using random forest and multi-layer perceptron. Subsequently, experiments were conducted sequentially using the next three data preprocessing methods. First, some property information of the input data were transformed. Next, input data were converted to nested form considering the consecutive card input system. Finally, input data were predicted by dividing into the early and the latter according to the normalized time information. As a result, the best preprocessing step was shown about 2.6% improvement in card type and about 1.8% improvement in card coordinates when nested data divided into the early.

• Structural Engineering and Mechanics
• /
• v.63 no.4
• /
• pp.429-438
• /
• 2017

Structural design has an imperative role in deciding the failure possibility of a Reinforced Concrete (RC) structure. Recent research works achieved the goal of predicting the structural failure of the RC structure with the assistance of machine learning techniques. Previously, the Artificial Neural Network (ANN) has been trained supported by Particle Swarm Optimization (PSO) to classify RC structures with reasonable accuracy. Though, keeping in mind the sensitivity in predicting the structural failure, more accurate models are still absent in the context of Machine Learning. Since the efficiency of multi-objective optimization over single objective optimization techniques is well established. Thus, the motivation of the current work is to employ a Multi-objective Genetic Algorithm (MOGA) to train the Neural Network (NN) based model. In the present work, the NN has been trained with MOGA to minimize the Root Mean Squared Error (RMSE) and Maximum Error (ME) toward optimizing the weight vector of the NN. The model has been tested by using a dataset consisting of 150 RC structure buildings. The proposed NN-MOGA based model has been compared with Multi-layer perceptron-feed-forward network (MLP-FFN) and NN-PSO based models in terms of several performance metrics. Experimental results suggested that the NN-MOGA has outperformed other existing well known classifiers with a reasonable improvement over them. Meanwhile, the proposed NN-MOGA achieved the superior accuracy of 93.33% and F-measure of 94.44%, which is superior to the other classifiers in the present study.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.2
• /
• pp.312-320
• /
• 2012

In this study, we introduce a new design methodology of a granular-oriented self-organizing polynomial neural networks (GoSOPNNs) that is based on multi-layer perceptron with Context-based Polynomial Neurons (CPNs) or Polynomial Neurons (PNs). In contrast to the typical architectures encountered in polynomial neural networks (PNN), our main objective is to develop a methodological design strategy of GoSOPNNs as follows : (a) The 1st layer of the proposed network consists of Context-based Polynomial Neuron (CPN). In here, CPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Context-based Fuzzy C-Means (C-FCM) clustering method. The context-based clustering supporting the design of information granules is completed in the space of the input data while the build of the clusters is guided by a collection of some predefined fuzzy sets (so-called contexts) defined in the output space. (b) The proposed design procedure being applied at each layer of GoSOPNN leads to the selection of preferred nodes of the network (CPNs or PNs) whose local characteristics (such as the number of contexts, the number of clusters, a collection of the specific subset of input variables, and the order of the polynomial) can be easily adjusted. These options contribute to the flexibility as well as simplicity and compactness of the resulting architecture of the network. For the evaluation of performance of the proposed GoSOPNN network, we describe a detailed characteristic of the proposed model using a well-known learning machine data(Automobile Miles Per Gallon Data, Boston Housing Data, Medical Image System Data).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.457-459
• /
• 2018

Solar power generation system is a energy generation technology that produces electricity from solar power, and it is growing fastest among renewable energy technologies. It is of utmost importance that the solar power system supply energy to the load stably. However, due to unstable energy production due to weather and weather conditions, accurate prediction of energy production is needed. In this paper, an Artificial Neural Network(ANN) that predicts solar energy using 15 kinds of meteorological data such as precipitation, long and short wave radiation averages and temperature is implemented and its performance is evaluated. The ANN is constructed by adjusting hidden parameters and parameters such as penalty for preventing overfitting. In order to verify the accuracy and validity of the prediction model, we use Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE) as performance indices. The experimental results show that MAPE = 19.54 and MAE = 2155345.10776 when Hidden Layer $Sizes=^{\prime}16{\times}10^{\prime}$.

• Computers and Concrete
• /
• v.22 no.2
• /
• pp.249-259
• /
• 2018

This paper presents Artificial Neural Network (ANN) models for evaluating bond strength of deformed, plain and cold formed bars in low strength concrete. The ANN models were implemented using the experimental database developed by conducting experiments in three different universities on total of 138 pullout and 108 splitting specimens under monotonic loading. The key parameters examined in the experiments are low strength concrete, bar development length, concrete cover, rebar type (deformed, cold-formed, plain) and diameter. These deficient parameters are typically found in non-engineered reinforced concrete structures of developing countries. To develop ANN bond model for each bar type, four inputs (the low strength concrete, development length, concrete cover and bar diameter) are used for training the neurons in the network. Multi-Layer-Perceptron was trained according to a back-propagation algorithm. The ANN bond model for deformed bar consists of a single hidden layer and the 9 neurons. For Tor bar and plain bars the ANN models consist of 5 and 6 neurons and a single hidden layer, respectively. The developed ANN models are capable of predicting bond strength for both pull and splitting bond failure modes. The developed ANN models have higher coefficient of determination in training, validation and testing with good prediction and generalization capacity. The comparison of experimental bond strength values with the outcomes of ANN models showed good agreement. Moreover, the ANN model predictions by varying different parameters are also presented for all bar types.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.10
• /
• pp.1991-2000
• /
• 1994

In this paper, an alagorithm with six types of classification is suggested for the recognition system of hand-written Korean characters. After thinning process and truncating process for noise redection. The input images are used generalized by $64\times64$ size. The six type classification is composed of preliminary and secondary classification process by using the learning algoritm of multi-layer perceptron. Subblock Hough transform is used as local feature and sampling Hough transform is used as global feature. Experiment is conducted for 1800 characters which is written 31 times per each type by 10 persons. The 90% recognition rate is resulted by the preliminary classification of detection the final consonant and by the secondary classification of detecting the vowels.