• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.4
• /
• pp.357-362
• /
• 2010

This paper proposes the speech and noise recognition system by using a neural network in order to detect the speech and noise sections at each frame. The proposed neural network consists of a layered neural network training by back-propagation algorithm. First, a power spectrum obtained by fast Fourier transform and linear predictive coefficients are used as the input to the neural network for each frame, then the neural network is trained using these power spectrum and linear predictive coefficients. Therefore, the proposed neural network can train using clean speech and noise. The performance of the proposed recognition system was evaluated based on the recognition rate using various speeches and white, printer, road, and car noises. In this experiment, the recognition rates were 92% or more for such speech and noise when training data and evaluation data were the different.

• Transactions on Electrical and Electronic Materials
• /
• v.15 no.4
• /
• pp.226-229
• /
• 2014

In this study, lead-free $(Ba_{0.85}Ca_{0.15})(Ti_{1-x}Zr_x)O_3$ ceramics and a bimorph-type piezoelectric actuator were fabricated using the normal oxide-mixed sintering method, and their dielectric properties, microstructure, and displacement properties were investigated. From the results of X-ray diffraction, the pattern of the specimen has a pure perovskite structure. In addition, no secondary impurity phases were found. The excellent piezoelectric coefficient of $d_{33}=454pC/N$, the electromechanical coupling factor $k_p=0.51$, the dielectric constant ${\varepsilon}_r=3,657$, the mechanical quality factor $Q_m=239$, and $T_c$(Tetragonal-Cubic) =$90^{\circ}C$ were shown at x= 0.085. ${\Delta}k_p/k_p20^{\circ}C$ and ${\Delta}f_r/f_r20^{\circ}C$ showed the maximum value of -0.255 and 0.111 at $-20^{\circ}C$ and $80^{\circ}C$, respectively. The maximum total-displacement was $60{\mu}m$ under the input voltage of 50 V. As a result, it is considered that lead-free $(Ba_{0.85}Ca_{0.15})(Ti_{1-x}Zr_x)O_3$ ceramics is a promising candidate for piezoelectric actuator application for x= 0.085.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.21 no.7
• /
• pp.669-673
• /
• 2008

ITO thin film was deposited on PC substrate in Facing Targets Sputtering (FTS) system with various sputtering conditions. After it is applied to external bending force, we investigated how change the surface and electrical property of as-deposited ITO thin film. As the L(face-plate distance) of substrate decreases, it found that the maximum crack density is increasing at the center position and decreasing crack density as goes to the edge. So to apply same curvature (r) and bending force to PC substrate with ITO thin film, we fixed the L that is equal to curvature radius (2r). Before bending test, ITO thin films that deposited in the input current of 0.4 A and thickness of 200 nm already had biaxial tensile failure because of each different CTE (Coefficient of Thermal Expansion) and Others had been shown no bending or crack. After bending test, all samples had been shown cracks at about 200 times and as increasing the crack density, resistivity increased.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.6
• /
• pp.1091-1096
• /
• 2011

Currently, the concern about the environment is the issue all over the world, and in particular, carbon emissions of the power plants will not be able to disregard from the respect of generation cost. This paper proposes DR (demand response) as a method of reducing carbon emissions and therefore, carbon emissions cost. There are a number of studies considering DR, and in this paper, the effect of DR is focused on the side of carbon emission reduction effect considering Time-Of-Use (TOU) program, which is one of the most important economic methods in DSM. Demand-price elasticity matrix is used in this paper to model and analyze DR effect. Carbon emissions is calculated by using the carbon emission coefficient provided by IPCC (Intergovernmental Panel on Climate Change), and generator's input-output characteristic coefficients are also used to estimate carbon emission cost as well as the amount of carbon emissions. Case study is conducted on the RBTS IEEE with six buses. For the TOU program, it is assumed that parameters of time period partition consist of three time periods (peak, flat, off-peak time period).

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.11
• /
• pp.2108-2116
• /
• 2008

The paper concerns Fuzzy C-Means clustering based Radial Basis Function neural networks (FCM-RBFNN) and the optimization of the network is carried out by means of Particle Swarm Optimization(PSO). FCM-RBFNN is the extended architecture of Radial Basis Function Neural Network(RBFNN). In the proposed network, the membership functions of the premise part of fuzzy rules do not assume any explicit functional forms such as Gaussian, ellipsoidal, triangular, etc., so its resulting fitness values directly rely on the computation of the relevant distance between data points by means of FCM. Also, as the consequent part of fuzzy rules extracted by the FCM - RBFNN model, the order of four types of polynomials can be considered such as constant, linear, quadratic and modified quadratic. Weighted Least Square Estimator(WLSE) are used to estimates the coefficients of polynomial. Since the performance of FCM-RBFNN is affected by some parameters of FCM-RBFNN such as a specific subset of input variables, fuzzification coefficient of FCM, the number of rules and the order of polynomials of consequent part of fuzzy rule, we need the structural as well as parametric optimization of the network. In this study, the PSO is exploited to carry out the structural as well as parametric optimization of FCM-RBFNN. Moreover The proposed model is demonstrated with the use of numerical example and gas furnace data set.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.2
• /
• pp.181-188
• /
• 2015

This paper present, the result of the guidance and control law for a course correction munitions(CCM) with 2sets of canards positioned in the rotating nose section. The nonlinear simulation model of the CCM was developed based on 7DOF equation of motion. The ability of correcting position was verified by open-loop control input with nonlinear model. The guidance and control command was constructed by reference trajectory which can be obtained with no control. Finally, the performance of the guidance and control law was evaluated through Monte-carlo simulation. The CEP(Circular Error Probability) was obtained by considering the errors in muzzle velocity, aerodynamic coefficient, wind, elevation and azimuth angle and density.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.9
• /
• pp.2003-2008
• /
• 2013

In this paper, a design method for a ultra-wideband printed semi-circular-shaped dipole antenna operating in the band of 1-15 GHz is studied. The effects of the gap between the two arms of the semi-circular-shaped dipole and the radius of the semi-circle on the input reflection coefficient and gain characteristics are examined to obtain the optimal design parameters. The optimized printed semi-circular-shaped dipole antenna is fabricated on an FR4 substrate and the experimental results show that the antenna has a desired extremely wideband characteristic with a frequency band of 1-15 GHz (175%) for a VSWR < 2.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.8
• /
• pp.3644-3653
• /
• 2011

This study proposes the automation of disinfection process in water treat plant to reach target effluent chlorine concentration rate according to chlorine consumption rate by varying travel time. Hydraulic analysis about the process and local facility was surveyed first and the program for automatic operation was developed to solve current problem, whose applied result was presented and proved to be better than present controller. Especially using multi variable process algorithm, the correlation coefficient is analyzed between environment factor and reaction time, and process control prove to be stable through model estimation with optimal control input.

• Composites Research
• /
• v.14 no.5
• /
• pp.26-37
• /
• 2001

After impact analysis of the composite cylindrical shells was performed. obtained outputs at 9 equally divided points of the shell were used as input patterns of the neural networks. Identification of impact loading characteristics was predicted simultaneously. Momentum backpropagation algorithm of neural networks which can modify the momentum coefficient and learning rate was developed and applied to identify the loading characteristics. Hidden layers of the backpropagation increased from 1 layer to 3 layers and trained the loading characteristics. Developed program with variable learning rate was converged close to real load characteristics under 1% error. Inverse engineering which identify the impact loading characteristics can be applicable to the composite laminated cylindrical shells with developed neural networks.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.9
• /
• pp.1541-1550
• /
• 2016

In this paper, we introduce a novel learning methodology of fuzzy clustering-based neural network pattern classifier. Fuzzy clustering-based neural network pattern classifier depicts the patterns of given classes using fuzzy rules and categorizes the patterns on unseen data through fuzzy rules. Least squares estimator(LSE) or weighted least squares estimator(WLSE) is typically used in order to estimate the coefficients of polynomial function, but this study proposes a novel coefficient estimate method which includes advantages of the existing methods. The premise part of fuzzy rule depicts input space as "If" clause of fuzzy rule through fuzzy c-means(FCM) clustering, while the consequent part of fuzzy rule denotes output space through polynomial function such as linear, quadratic and their coefficients are estimated by the proposed local least squares estimator(LLSE)-based learning. In order to evaluate the performance of the proposed pattern classifier, the variety of machine learning data sets are exploited in experiments and through the comparative analysis of performance, it provides that the proposed LLSE-based learning method is preferable when compared with the other learning methods conventionally used in previous literature.