• Journal of the Korea Safety Management & Science
• /
• v.10 no.4
• /
• pp.105-109
• /
• 2008

The purpose of this study is to distinguish the causes of broken glass on doors or windows when it is originally kept among the remains on the floor in fire site - whether it was broken due to heating or outer power-through test and characteristics of the broken plane including the pattern on the plane. Addition to it, the study tries to find characteristics to judge the point and direction of breakdown through the analysis of glass broken by outer power. With two assumed causes - a) breakdown due to heating and b) breakdown due to outer power-3 pieces of glass plates ($30cm{\times}30cm{\times}5mm$) were tested for each case, getting the results as following: First, for the glass broken due to the change of temperature, the broken plane is of slow and smooth curve without any pattern. Second, for the glass broken due to outer power, with the impact point as the center, the glass shows breakdown of radial type and the side shows breakdown of near-perpendicular type. The far the broken piece is from the impact point, the bigger the size is. The broken piece at the impact point is of long triangle type and the two long planes of the triangle shows semi-arc with the center of breakdown point and the other plane shows opposite pattern. Third, when glass that is damaged by outer power is heated, damaged forms and side patterns of the glass that is damaged by outer power are heated and disappeared.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.526-533
• /
• 2014

In this study, we introduce design methodology to develop a guidance for issuing heavy rainfall warning by using both RBFNNs(Radial basis function neural networks) and SVR(Support vector regression) model, and then carry out the comparative studies between two pattern classifiers. Individual classifiers are designed as architecture realized with the aid of optimization and pre-processing algorithm. Because the predictive performance of the existing heavy rainfall forecast system is commonly affected from diverse processing techniques of meteorological data, under-sampling method as the pre-processing method of input data is used, and also data discretization and feature extraction method for SVR and FCM clustering and PSO method for RBFNNs are exploited respectively. The observed data, AWS(Automatic weather wtation), supplied from KMA(korea meteorological administration), is used for training and testing of the proposed classifiers. The proposed classifiers offer the related information to issue a heavy rain warning in advance before 1 to 3 hours by using the selected meteorological data and the cumulated precipitation amount accumulated for 1 to 12 hours from AWS data. For performance evaluation of each classifier, ETS(Equitable Threat Score) method is used as standard verification method for predictive ability. Through the comparative studies of two classifiers, neuro-fuzzy method is effectively used for improved performance and to show stable predictive result of guidance to issue heavy rainfall warning.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.182-188
• /
• 2013

In this paper, we propose a complex-valued support vector machine (SVM) classifier which process the complex valued signal measured by pulse doppler radar (PDR) to identify moving targets from the background. SVM is widely applied in the field of pattern recognition, but features which used to classify are almost real valued data. Proposed complex-valued SVM can classify the moving target using real valued data, imaginary valued data, and cross-information data. To design complex-valued SVM, we consider slack variables of real and complex axis, and use the KKT (Karush-Kuhn-Tucker) conditions for complex data. Also we apply radial basis function (RBF) as a kernel function which use a distance of complex values. To evaluate the performance of the complex-valued SVM, complex valued data from PDR were classified using real-valued SVM and complex-valued SVM. The proposed complex-valued SVM classification was improved compared to real-valued SVM for dog and human, respectively 8%, 10%, have been improved.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.157-177
• /
• 2003

This paper presents a comprehensive and successful application of data mining methodologies to improve and predict wafer yield in a semiconductor wafer fabrication system. As the wafer fabrication process is getting more complex and the volume of technological data gathered continues to be vast, it is difficult to analyze the cause of yield deterioration effectively by means of statistical or heuristic approaches. To begin with this paper applies a clustering method to automatically identify AUF (Area Uniform Failure) phenomenon from data instead of naked eye that bad chips occurs in a specific area of wafer. Next, sequential pattern analysis and classification methods are applied to and out machines and parameters that are cause of low yield, respectively. Furthermore, radial bases function method is used to predict yield of wafers that are in process. Finally, this paper demonstrates an information system, Y2R-PLUS (Yield Rapid Ramp-up, Prediction, analysis & Up Support), that is developed in order to analyze and predict wafer yield in a korea semiconductor manufacturer.

• Tunnel and Underground Space
• /
• v.9 no.3
• /
• pp.194-203
• /
• 1999

The axial stress in rock bolt, the shear stress at the bolt-grout interface and the neutral point are analyzed to understand the mechanical behavior of rook bolt. To analyze the support effects of rock bolt in various geological conditions, numerical analyses are performed with regard to bolt spacing and bolt length in several geological conditions and tunnel sizes. Through the numerical analyses, the distributions of maximum tensile stress and shear stress are determined. And the excavation width of underground opening affects the position of the neutral point. In the circular opening supported by pattern bolting, the increase of confining pressure, the reduction of plastic zone, and that of ground displacement are determined by using the radial stress increase ratio, the plastic zone reduction ratio and the displacement reduction ratio respectively. The results of this study can be applied to a practical tunnel design through understanding of the trends of these support effects.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.586-591
• /
• 2014

In this study, we introduce Radial Basis Function Neural Networks(RBFNNs) classifier using Artificial Bee Colony(ABC) algorithm in order to classify between precipitation event and non-precipitation event from given radar data. Input information data is rebuilt up through feature analysis of meteorological radar data used in Korea Meteorological Administration. In the condition phase of the proposed classifier, the values of fitness are obtained by using Fuzzy C-Mean clustering method, and the coefficients of polynomial function used in the conclusion phase are estimated by least square method. In the aggregation phase, the final output is obtained by using fuzzy inference method. The performance results of the proposed classifier are compared and analyzed by considering both QC(Quality control) data and CZ(corrected reflectivity) data being used in Korea Meteorological Administration.

• Nuclear Engineering and Technology
• /
• v.48 no.1
• /
• pp.55-63
• /
• 2016

Calculation of the core neutronic parameters is one of the key components in all nuclear reactors. In this research, the energy spectrum and spatial distribution of the neutron flux in a uranium target have been calculated. In addition, sensitivity of the core neutronic parameters in accelerator-driven subcritical advanced liquid metal reactors, such as electron beam energy ($E_e$) and source multiplication coefficient ($k_s$), has been investigated. A Monte Carlo code (MCNPX_2.6) has been used to calculate neutronic parameters such as effective multiplication coefficient ($k_{eff}$), net neutron multiplication (M), neutron yield ($Y_{n/e}$), energy constant gain ($G_0$), energy gain (G), importance of neutron source (${\varphi}^*$), axial and radial distributions of neutron flux, and power peaking factor ($P_{max}/P_{ave}$) in two axial and radial directions of the reactor core for four fuel loading patterns. According to the results, safety margin and accelerator current ($I_e$) have been decreased in the highest case of $k_s$, but G and ${\varphi}^*$ have increased by 88.9% and 21.6%, respectively. In addition, for LP1 loading pattern, with increasing $E_e$ from 100 MeV up to 1 GeV, $Y_{n/e}$ and G improved by 91.09% and 10.21%, and $I_e$ and $P_{acc}$ decreased by 91.05% and 10.57%, respectively. The results indicate that placement of the Np-Pu assemblies on the periphery allows for a consistent $k_{eff}$ because the Np-Pu assemblies experience less burn-up.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.5
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.6
• /
• pp.55-62
• /
• 2006

For the fault diagnosis of three-phase induction motors, we construct a experimental unit and then develop a diagnosis algorithm based on pattern recognition. The experimental unit consists of machinery module for induction motor drive and data acquisition module to obtain the fault signal. As the first step for diagnosis procedure, preprocessing is performed to make the acquired current simplified and normalized. To simplify the data, three-phase current is transformed into the magnitude of Concordia vector. As the next step, feature extraction is performed by kernel principal component analysis(KPCA) and linear discriminant analysis(LDA). Finally, we used the classifier based on radial basis function(RBF) network. To show the effectiveness, the proposed diagnostic system has been intensively tested with the various data acquired under different electrical and mechanical faults with varying load.

• Journal of the Korean Wood Science and Technology
• /
• v.25 no.3
• /
• pp.43-49
• /
• 1997

The lengths of fibers and vessel elements, vessel diameters, and ray spacings of tension and opposite woods in Quercus mongolica Fischer and their radial variations were examined. Crystallinity indices and crystallites orientations of tension, opposite and lateral woods were also investigated. The lengths of fibers and vessel elements, and ray spacings of tension wood were longer and denser than those of opposite wood, respectively. In the latewood, the vessels of tension wood had a little larger diameters than those of opposite wood. whereas the vessel diameters of earlywood were similar in both woods. With the exception of vessel diameters of earlywood, there were differences between tension and opposite woods in all anatomical characteristics examined. In the radial variation pattern, the fiber lengths of both woods increased markedly to about 15th annual ring and thereafter remained virtually constant. The vessel element lengths of earlywood in tension wood increased to certain annual ring and thereafter were stabilized, but opposite wood had a relatively constant trend from pith to bark. Those of late wood in both woods increased to certain annual ring and thereafter showed constant patterns. Vessel diameters appeared to show similar trend in both woods. Ray spacings decreased to about 15 annual ring and thereafter were stabilized in both woods. In the fine structures, tension wood had higher crystallinity index and better crystallites orientation than opposite and lateral woods.