• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.2
• /
• pp.313-319
• /
• 1999

We devise the 3 models of Multilayered Recurrent Prediction Neural Network(MLRPNN), which are obtained by modifying the Multilayered Perceptron(MLP) with 4 layers. We experimentally study the speech recognition performance of 3 models by a comparative method, according to the variation of the prediction order, the number of neurons in two hidden layers, initial values of connecting weights and transfer function, respectively. By the experiment, the recognition performance of each MLRPNN is better than that of MLP. At the model that returns the output of the upper hidden layer to the lower hidden layer, the recognition performance shows the best value. All MLRPNNs, which have 10 or 15 neurons in the upper and lower hidden layer and is predicted by 3rd or 4th order, show the improved speech recognition rate. On learning, these MLRPNNs have a better recognition rate when we set the initial weights between -0.5 and 0.5, and use the unipolar sigmoid transfer function in the lower hidden layer.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.2032-2037
• /
• 2011

Marker genes are defined as genes in which the expression level characterizes a specific experimental condition. Such genes in which the expression levels differ significantly between different groups are highly informative relevant to the studied phenomenon. In this paper, first the system can detect marker genes that are selected by ranking genes according to statistics after normalizing data with methods that are the most widely used among several normalization methods proposed the while, And it compare and analyze a performance of each of normalization methods with mult-perceptron neural network layer. The Result that apply Multi-Layer perceptron algorithm at Microarray data set including eight of marker gene that are selected using ANOVA method after Lowess normalization represent the highest classification accuracy of 99.32% and the lowest prediction error estimate.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.5
• /
• pp.383-392
• /
• 2007

In this paper, we study the prediction of depth and width of a defect in steam generator tube in nuclear power plant using neural network. To this end, we first generate eddy current testing (ECT) signals for 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. In particular, we generate 400 ECT signals for various widths and depths for each defect type by the numerical analysis program based on finite element modeling. From those generated ECT signals, we extract new feature vectors for the prediction of defect size, which include the angle between the two points where the maximum impedance and half the maximum impedance are achieved. Using the extracted feature vector, multi-layer perceptron with one hidden layer is used to predict the size of defects. Through the computer simulation study, it is shown that the proposed method achieves decent prediction performance in terms of maximum error and mean absolute percentage error (MAPE).

• Journal of Korea Water Resources Association
• /
• v.38 no.7 s.156
• /
• pp.575-584
• /
• 2005

The judgement model to warn of possible pollution accident is constructed by multi-perceptron, multi layer neural network, neuro-fuzzy and it is trained stability, notice, and warming situation due to developed standard axis. The water quality forecasting model is linked to the runoff forecasting model, and joined with the judgement model to warn of possible pollution accident, which completes the artificial intelligence warning system. And GUI (Graphic User Interface) has been designed for that system. GUI screens, in order of process, are main page, data edit, discharge forecasting, water quality forecasting, warming system. The application capability of the system was estimated by the pollution accident scenario. Estimation results verify that the artificial intelligence warning system can be a reasonable judgement of the noized water pollution data.

• Journal of Navigation and Port Research
• /
• v.35 no.1
• /
• pp.83-91
• /
• 2011

The accuracy of forecasting is remarkably important to reduce total cost or to increase customer services, so it has been studied by many researchers. In this paper, the artificial neural network (ANN), one of the most popular nonlinear forecasting methods, is compared with autoregressive integrated moving average(ARIMA) model through performing a prediction of container traffic. It uses a hybrid methodology that combines both the linear ARIAM and the nonlinear ANN model to improve forecasting performance. Also, it compares the methodology with other models in performance for prediction. In designing network structure, this work specially applies the genetic algorithm which is known as the effectively optimal algorithm in the huge and complex sample space. It includes the time delayed neural network (TDNN) as well as multi-layer perceptron (MLP) which is the most popular neural network model. Experimental results indicate that both ANN and Hybrid models outperform ARIMA model.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.4
• /
• pp.266-274
• /
• 2003

Distance Fourier descriptors of local target boundary and feature information fusion using multiple MLPs (Multilayer perceptrons) are proposed. They are used to identify nonoccluded and partially occluded targets in natural FLIR (forward-looking infrared) images. After segmenting a target, radial Fourier descriptors as global shape features are defined from the target boundary. A target boundary is partitioned into four local boundaries to extract local shape features. In a local boundary, a distance function is defined from boundary points and a line between two extreme points. Distance Fourier descriptors as local shape features are defined by using distance function. One global feature vector and four local feature vectors are used as input data for multiple MLPs to determine final identification result of the target. In the experiments, we show that the proposed method is superior to the traditional feature sets with respect to the identification performance.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.135-144
• /
• 2003

A method for the automatic segmentation of speech signals is described. The method is dedicated to the construction of a large database for a Text-To-Speech (TTS) synthesis system. The main issue of the work involves the refinement of an initial estimation of phone boundaries which are provided by an alignment, based on a Hidden Market Model(HMM). Multi-layer perceptron (MLP) was used as a phone boundary detector. To increase the performance of segmentation, a technique which individually trains an MLP according to phonetic transition is proposed. The optimum partitioning of the entire phonetic transition space is constructed from the standpoint of minimizing the overall deviation from hand labelling positions. With single speaker stimuli, the experimental results showed that more than 95% of all phone boundaries have a boundary deviation from the reference position smaller than 20 ms, and the refinement of the boundaries reduces the root mean square error by about 25%.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.71-77
• /
• 2017

Virtual advertisement is an advertising technique that using computer graphic in a media production such as a sports image for inserting product image, logo, advertising slogan, etc. Recently, the image insertion of virtual advertisement is actively spreading due to the satisfaction of technical element for the image insertion of virtual advertisement in sports advertisement by increasing of the image processing technology and the computing performance. In addition, image processing technology for automatic insertion has become an important research field in the virtual advertisement field. In this paper, we propose the method of extracting less-informative region by using image processing technique and machine learning to insert a virtual advertisement automatically in sports image. The proposed method analyzes the brightness level of image through the histogram and extracts the less-informative region using the machine learning method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.513-520
• /
• 2020

Recently, the development of a vision inspection system using machine learning has become more active. This study seeks to develop a defect inspection model using machine learning. Defect detection problems for images correspond to classification problems, which are the method of supervised learning in machine learning. In this study, defect detection models are developed based on algorithms that automatically extract features and algorithms that do not extract features. One-dimensional CNN and two-dimensional CNN are used as algorithms for automatic extraction of features, and MLP and SVM are used as algorithms for non-extracting features. A defect detection model is developed based on four models and their accuracy and AUC compare based on AUC. Although image classification is common in the development of models using CNN, high accuracy and AUC is achieved when developing SVM models by converting pixels from images into RGB values in this study.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.209-214
• /
• 2017

The aim of the present study was to analyze the factors that affects the peer attachment in Korean youth. Subjects were 419 middle school students (210 male, 209 female). Dependent variable was defined as peer attachment. Explanatory variables were included as gender, academic achievement satisfaction, subjective household economy level, parent - child dialogue frequency, subjective health status, depression symptom, self - esteem, subjective life satisfaction, and mobile phone dependency. In the multi-layer perceptron artificial neural network algorithm analysis, depression symptoms, gender, parent-child dialogue level for school life, subjective household economy level, subjective health status were significantly associated with peer attachment in Korean youth. Based on this result, systematic programs are required in order to prevention of peer attachment in Korean youth.