• Journal of Biomedical Engineering Research
• /
• v.24 no.2
• /
• pp.99-106
• /
• 2003

In this paper, a method of discriminating EEG for diagnoses of mental activity is proposed. The proposed method for classification of schizophrenia and normal EEG is based on the wavelet transform and the artificial neural network. The wavelet coefficients of $\alpha$ band, $\beta$ band, $\theta$ band, and $\delta$ band are obtained using the wavelet transform. The magnitude, mean, and variance of wavelet coefficients for each EEG band are applied to the input data of the system's ANN. The architecture of the ANN s a four layered feedforward network with two hidden layer which implements the error back propagation learning algorithm. Through the classification of schizophrenia composed of 19 ANNs corresponding to 19 channels, the classifying system show that it can classify the 100% of the normal EEG group and the 86.67% of the schizophrenia EEG group.

• Korean Journal of Biological Psychiatry
• /
• v.6 no.1
• /
• pp.12-20
• /
• 1999

In order to understand the pathogenesis and progression of some synaptic loss related neuropsychiatric diseases, We attempted to develop a computer model in this study. We made a simple autoassociative memory network remembering numbers, transformed it into a disease model by pruning synapses, and measured its memory performance as a function of synaptic deletion. Decline in performance was measured as amount of synaptic loss increases and its mode of decline is sudden or gradual according to the mode of synaptic pruning. The developed computer model demonstrated how synaptic loss could cause memory impairment through a series of computer simulations, and suggested a new way of research in neuropsychiatry.

• Science of Emotion and Sensibility
• /
• v.7 no.3
• /
• pp.15-25
• /
• 2004

The regression analysis and Adaptive -Network based Fuzzy-inference system (ANFIS) were applied to the explanation on human's visual texture of cotton fabrics with 7 mechanical properties. The ANFIS uses the structure with fuzzy membership function and neural network. The results obtained by the statistical analysis through the coefficient of correlation and regression analysis showed that subjective texture had a linear relationship with mechanical properties. But It had a relatively low coefficient of determination and was difficult that the statistical analysis explained other relationship with the exception of a lineality and interaction among mechanical properties. Comparing the statistical analysis, the ANFIS was an effective tool to explain human's non-linear perceptions and their interactions. But to apply ANFIS to human's perceptions more effectively, it is necessary to discriminate effective input variables through controlling the properties of samples.

• Journal of KIISE:Software and Applications
• /
• v.35 no.10
• /
• pp.589-599
• /
• 2008

Accurate software effort estimation has always been a challenge for the software industrial and academic software engineering communities. Many studies have focused on effort estimation methods to improve the estimation accuracy of software effort. Although data quality is one of important factors for accurate effort estimation, most of the work has not considered it. In this paper, we investigate the influence of outlier elimination on the accuracy of software effort estimation through empirical studies applying two outlier elimination methods(Least trimmed square regression and K-means clustering) and three effort estimation methods(Least squares regression, Neural network and Bayesian network) associatively. The empirical studies are performed using two industry data sets(the ISBSG Release 9 and the Bank data set which consists of the project data collected from a bank in Korea) with or without outlier elimination.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.3
• /
• pp.75-81
• /
• 2007

Recently the subject of "wavelet analysis" has be drawn by both mathematical and engineering application fields such as Signal Processing, Compression/Decomposition, Wavelet-Neural Network, Statistics and etc. Even though its similar to Fourier analysis, wavelet is a versatile tool with much mathematical content and great potential for applications. Especially, wavelet transform uses localizable various mother wavelet functions in time-frequency domain. Therefore, wavelet transform has good time-analysis ability for high frequency component, and has good frequency-analysis ability for low frequency component. Using the discriminative ability is more easy method than other conventional techniques. In this paper, Morlet wavelet transform was applied to discriminate the kind of line fault by acquired data from real power transformation network. The experimental result presented that Morlet wavelet transform is easier, and more useful method than the Fast Fourier Transform(FFT).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.1
• /
• pp.14-22
• /
• 2001

Off-line handwritten numeral recognition is a very difficult task and hard to achieve high recognition results using a single feature and a single classifier, since handwritten numerals contain many pattern variations which mostly depend upon individual writing styles. In this paper, we propose handwritten numeral recognition system using hybrid features and combined classifier. To improve recognition rate, we select mutually helpful features -directional features, crossing point feature and mesh features- and make throe new hybrid feature sets by using these features. These hybrid feature sets hold the local and global characteristics of input numeral images. And we implement combined classifier by combining three neural network classifiers to achieve high recognition rate, where fuzzy integral is used for multiple network fusion. In order to verify the performance of the proposed recognition system, experiments with the unconstrained handwritten numeral database of Concordia University, Canada were performed. As a result, our method has produced 97.85% of the recognition rate.

• International Journal of Highway Engineering
• /
• v.20 no.2
• /
• pp.57-65
• /
• 2018

PURPOSES : The study aims to predict the service life of national highway asphalt pavements through deep learning methods by using maintenance history data of the National Highway Pavement Management System. METHODS : For the configuration of a deep learning network, this study used Tensorflow 1.5, an open source program which has excellent usability among deep learning frameworks. For the analysis, nine variables of cumulative annual average daily traffic, cumulative equivalent single axle loads, maintenance layer, surface, base, subbase, anti-frost layer, structural number of pavement, and region were selected as input data, while service life was chosen to construct the input layer and output layers as output data. Additionally, for scenario analysis, in this study, a model was formed with four different numbers of 1, 2, 4, and 8 hidden layers and a simulation analysis was performed according to the applicability of the over fitting resolution algorithm. RESULTS : The results of the analysis have shown that regardless of the number of hidden layers, when an over fitting resolution algorithm, such as dropout, is applied, the prediction capability is improved as the coefficient of determination ($R^2$) of the test data increases. Furthermore, the result of the sensitivity analysis of the applicability of region variables demonstrates that estimating service life requires sufficient consideration of regional characteristics as $R^2$ had a maximum of between 0.73 and 0.84, when regional variables where taken into consideration. CONCLUSIONS : As a result, this study proposes that it is possible to precisely predict the service life of national highway pavement sections with the consideration of traffic, pavement thickness, and regional factors and concludes that the use of the prediction of service life is fundamental data in decision making within pavement management systems.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.87-91
• /
• 2005

The cascade-correlation (CC) learning algorithm of Fahlman and Lebiere is one of the most influential constructive algorithm in a neural network. Cascading the hidden neurons results in a network that can represent very strong nonlinearities. Although this power is in principle useful, it can be a disadvantage if such strong nonlinearity is not required to solve the problem. 3 models are presented and compared empirically. All of them are based on valiants of the cascade architecture and output neurons weights training of the CC algorithm. Empirical results indicate the followings： (1) In the pattern classification, the model that train only new hidden neuron to output layer connection weights shows the best predictive ability; (2) In the function approximation, the model that removed input-output connection and used sigmoid-linear activation function is better predictability than CasCor algorithm.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.12
• /
• pp.90-97
• /
• 1999

Recently, there have been many researches to automate processing and analysing image data in medical field, due to the advance of image processing techniques, the fast communication network and high performance hardware. In this paper, we design and implement the system based on the multi-layer neural network model to be able to analyze, differentiate and count blood cells in the peripheral blood image. To do these, we segment red and white-blood cell in blood image acquired from microscope with CCD(Charge-coupled device) camera and then apply the various feature extraction algorithms to classify. In addition to, we reduce multi-variate feature number using PCA(Principle Component Analysis) to construct more efficient classifier. So, in this paper, we are sure that the proposed system can be applied to a pathological guided system.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.373-384
• /
• 2014

Data mining is to clarify pattern or correlation of mass data of complicated structure and to predict the diverse outcomes. This technique is used in the fields of finance, telecommunication, circulation, medicine and so on. In this paper, we selected risk factors of respiratory diseases in the field of medicine. The data we used was divided into respiratory diseases group and health group from the Gyeongsangbuk-do database of Community Health Survey conducted in 2012. In order to select major risk factors, we applied data mining techniques such as neural network, logistic regression, Bayesian network, C5.0 and CART. We divided total data into training and testing data, and applied model which was designed by training data to testing data. By the comparison of prediction accuracy, CART was identified as best model. Depression, smoking and stress were proved as the major risk factors of respiratory disease.