• Journal of Environmental Impact Assessment
• /
• v.12 no.4
• /
• pp.271-279
• /
• 2003

Temperature and humidity forecasting have been performed using artificial neural networks model(ANN). We composed ANN with multi-layer perceptron which is 2 input layers, 2 hidden layers and 1 output layer. Back propagation algorithm was used to train the ANN. 6 nodes and 12 nodes in the middle layers were appropriate to the temperature model for training. And 9 nodes and 6 nodes were also appropriate to the humidity model respectively. 90% of the all data was used learning set, and the extra 10% was used to model verification. In the case of temperature, average temperature before 15 minute and humidity at present constituted input layer, and temperature at present constituted out-layer and humidity model was vice versa. The sensitivity analysis revealed that previous value data contributed to forecasting target value than the other variable. Temperature was pseudo-linearly related to the previous 15 minute average value. We confirmed that ANN with multi-layer perceptron could support pollutant dispersion model by computing meterological data at real time.

• Journal of Korean Society on Water Environment
• /
• v.21 no.1
• /
• pp.21-28
• /
• 2005

The training and prediction modeling using an artificial neural network was implemented to predict the turbidity of treated water as well as to estimate the optimized feed concentration of polyaluminium chloride (PACl) in a water treatment plant. The parameters used in the input layers were pH, temperature, turbidity and alkalinity, while those in output layers were PACl and turbidity of treated water. Levenberg-Marquadt method of feedforward back-propagation perceptron in the neural network toolbox of MATLAB program was used in this study. Correlation coefficients of the training data with the measured data were 0.9997 for PACl and 0.6850 for turbidity and those of the testing data with measured data were 0.9140 for PACl and 0.3828 for turbidity, when four parameters at input layer, 12-12 nodes each at both the first and the second hidden layers, and two parameters(PACl and turbidity) at output layer were used. Although the predictability of PACl was improved, compared to that of the previous studies to use the only coagulant dose as output layer, turbidity in treated water could not be predicted well. Acquisition of more data through several years obtained with the advanced on-line measuring system could make the artificial neural network useful and practical in actual water treatment plants.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 1998.11a
• /
• pp.123-126
• /
• 1998

We have conducted surface electrical resistivity surveys along with the electrical logging at Bookil-Myun, Chungwon-Goon, Choongchungbuk-Do to determine the depths of basement and water table, and for the purpose of preparing the basic input data for hydrogeologic model combined with GIS. A twenty lines of dipole-dipole array survey and a twenty-five stations of resistivity sounding were performed and ten holes were employed for electrical logging to cross check the surface data. A combined interpretation gave the quantitative information of the shallow geologic structure over the area and we constructed layers using the grid analysis of Arc/info. The constructed layers were turned out to be similar to the geologic structure confirmed from the drilling data and we concluded that the methodology adopted in this study would be applicable to hydrogeologic model setup as a tool of providing the basic input data.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 1999.11a
• /
• pp.15-21
• /
• 1999

This study investigates the free and forced vibration characteristics of an annular piezoelectric motor stator constructed of two piezoelectric material layers and one stainless steel layer. The annular piezoelectric motor stator is subjected to a travelling load produced by piezo drive electrical voltage input to the two piezoelectric layers. The stator is modeled as an annular laminated plate based on the classical plate theory and the governing equations are derived via Hamilton's variational principle. Variation of the free vibration characteristics as a function of several design parameters has been studied and based on this result, the forced vibration responses to the input electricity of various frequencies and magnitudes are investigated. The obtained results will provide an important criterion, a priori, in the design of piezoelectric motors.

• Economic and Environmental Geology
• /
• v.33 no.4
• /
• pp.283-293
• /
• 2000

A set of geophysical survey results over an area in Bookil-myun, Chungwon-Gun, Chungcheongbuk-Do is presented; resistivity logging, d.c. sounding, dipole-dipole resistivity, and controlled-source magnetotelluric (CSMT) surveys. These surveys were chosen in this research for the estimation of the basement depth and the delineation of the hydrogeologic structure over the survey area. The results provide an optimal input to a hydrogeologic modeling analysis using the strategies built in GIS software. A total of 14 lines of dipole-dipole resistivity surveys, 25 stations of d.c. sounding and 6 stations of CSMT sounding were performed. In addition 10 boreholes were chosen for resistivity logging to correlate the logs to the surface data. A quantitative information on the hydrogeologic structure over the area is provided by synthesizing the results from various geophysical data and attribute layers are constructed by utilizing a GIS software Arc/ Info. The constructed layers match well to the hydrogeologic structures, which were outlined from the drilling data. The methodology tested and adopted in this study would be useful for providing a more reliable input to the hydrogeologic model setup.

• International Journal of CAD/CAM
• /
• v.8 no.1
• /
• pp.21-28
• /
• 2009

In the present work, an attempt has been made to construct branching surface from 2-D contours, which are given at different layers and may have branches. If a layer having more than one contour and corresponds to contour at adjacent layers, then it is termed as branching problem and approximated by adding additional points in between the layers. Firstly, the branching problem is converted to single contour case in which there is no branching at any layer and the final branching surface is obtained by skinning. Contours are constructed from the given input points at different layers by energy-based B-Spline approximation. 3-D curves are constructed after adding additional points into the contour points for all the layers having branching problem by using energy-based B-Spline formulation. Final 3-D surface is obtained by skinning 3-D curves and 2-D contours. There are three types of branching problems: (a) One-to-one, (b) One-to-many and (c) Many-to-many. Oneto-one problem has been done by plethora of researchers based on minimizations of twist and curvature and different tiling techniques. One-to-many problem is the one in which at least one plane must have more than one contour and have correspondence with the contour at adjacent layers. Many-to-many problem is stated as m contours at i-th layer and n contours at (i+1)th layer. This problem can be solved by combining one-to-many branching methodology. Branching problem is very important in CAD, medical imaging and geographical information system(GIS).

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.9
• /
• pp.94-105
• /
• 1993

In this paper propose a Koaren character recognition system using a neural network is proposed. This system is a multilayer neural network based on the masking field model which consists of a input layer, four feature extraction layers which extracts type, direction, stroke, and connection features, and an output layer which gives us recognized character codes. First, 4x4 subpatterns of an NxN character pattern stored in the input buffer are applied into the feature extraction layers sequentially. Then, each of feature extraction layers extracts sequentially features such as type, direction, stroke, and connection, respectively. Type features for direction and connection are extracted by the type feature extraction layer, direction features for stroke by the direction feature extraction layer and stroke and connection features for stroke by the direction feature extraction layer and stroke and connection features for the recongnition of character by the stroke and the connection feature extractions layers, respectively. The stroke and connection features are saved in the sequential buffer layer sequentially and using these features the characters are recognized in the output layer. The recognition results of this system by tests with 8 single consonants and 6 single vowels are promising.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2E
• /
• pp.32-37
• /
• 1997

This paper proposes a isolated speech recognition method of Korean digits using a TDNN(Time Delay Neural Network) which is able to recognizc time-varying speech properties. We also make an investigation of effect on network parameter of TDNN ; hidden layers and time-delays. TDNNs in our experiments consist of 2 and 3 hidden layers and have several time-delays. From experiment result, TDNN structure which has 2 hidden-layers, gives a good result for speech recognition of Korean digits. Mis-recognition by time-delays can be improved by changing TDNN structures and mis-recognition separated from time-delays can be improved by changing input patterns.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.32A no.1
• /
• pp.70-78
• /
• 1995

In order to implement broadband RAM's(Radar Absorbing Materials) made up of multiple dielectricl layers, the design variables such as the dielectrci constaints, the depths and the loss tangents of dielectric are optimized. The wave impedances regarding the reflective wave are found in dielectrics, input impedances and reflection coefficients with multiple dielectric layers are derived from the transmission line circuit theory. Finally, minimum average reflective power and optimum design variables are obtained by applying the numerical technique, called modified Powell method. In case of four dielectric layers with inequality constraints in design variables, a quite favourable and feasible result with the total depth of 1.1 cm, the average reflective power of 0.85% over the bradband frequency range is obtained for a specific example.