• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.09a
• /
• pp.325-333
• /
• 1995

Back-propagation is the most widely used algorithm for supervised learning in multi-layer feed-forward networks. However, back-propagation is very slow in convergence. In this paper, a new weight initialization method, called rough map initialization, in multi-layer perceptrons is proposed. To overcome the long convergence time, possibly due to the random initialization of the weights of the existing multi-layer perceptrons, the rough map initialization method initialize weights by utilizing relationship of input-output features with singular value decomposition technique. The results of this initialization procedure are compared to random initialization procedure in encoder problems and xor problems.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.4 no.2
• /
• pp.189-201
• /
• 2001

For a design of multi-layer armor, the extensive full scale or sub-scale penetration test data are required. In generally, the collection of penetration data is in need of time-consuming and expensive processes. However, the application of numerical or analytical method is very limited due to poor understanding about penetration mechanics. In this paper, we have developed a neural network analyzer which can be used as a design tool for a new armor. Calculation results show that the developed neural network analyzer can predict relatively exact penetration depth of a new armor through the effective analysis of the pre-existing penetration database.

• Journal of KSNVE
• /
• v.7 no.5
• /
• pp.803-810
• /
• 1997

This paper is concerned with the vibration control of multi-layer structure for ultra-tall buildings and main tower of large bridge etc. We have modeled the multi-layer structure with the distributed mass system as the lumped mass system of two-degree-of-freedom structure and made experimental equipment. The $H_\infty$control theory was applied to the design of the control system. The designed control system was simulated by computer. As a result, the designed $H_\infty$controller showed the good vibration control performance to impulse response and frequency response.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.2
• /
• pp.31-38
• /
• 2011

Skin color is a very important information for an automatic face recognition. In this paper, we proposed a skin region extraction method using the MLP(Multi-Layer Perceptron) and skin color model. We use the adaptive lighting compensation technique for improved performance of skin region extraction. Also, using an preprocessing filter, normally large areas of easily distinct non-skin pixels, are eliminated from further processing. Experimental results show that the proposed method has better performance than the conventional methods, and reduces processing time by 31~49% on average.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.6
• /
• pp.93-99
• /
• 1993

In previous paper we proposed a multi-layer bidirectional associative memory (MBAM) which is an extended model of the bidirectional associative memory (BAM) into a multilayer architecture. And we showed that the MBAM has the possibility to have binary storage for easy implementation. In this paper we present a MOdified MBAM(MOMBAM) with high performance compared to MBAM and multi-layer perceptron. The contents will include the architecture, the learning method, the computer simulation results for MOMBAM with MBAM and multi-layer perceptron, and the convergence properties shown by computer simulation examples.. And we will show that the proposed model can be used as classifier with a little restriction.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.2
• /
• pp.431-434
• /
• 2011

In this paper, bandwidth enhanced design of dielectric resonator antenna fabricated in multi-layer substrate is introduced. The proposed dielectric resonator antenna is operating with fundamental TE101 mode and higher-order TM111 mode. Each resonance frequency is dependent on resonator dimensions. As increasing the height of radiating aperture, the higher-order TM111 mode resonance frequency approach the fundamental TE101 mode resonance frequency and the antenna bandwidth increase by double resonance. Three different aperture height size antennas that operated at 7GHz are fabricated in FR4 multi-layer substrate. Measured 10 dB matching bandwidth is 8 percent for single resonace antenna and 18 percent for double resonance antenna.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.30 no.3
• /
• pp.59-64
• /
• 2016

Applications of electrolytic ion water generated by the oxidation-reduction have gradually been expanded due to their strong sterilizing power and a surface active force. We demonstrate the effect of the multi-layer type electrode for effective ion water generation. The multi-layer type electrode has ability to generate stronger acid and alkali water by increase of the electrode reactive area. Also power consumption efficiency enhances because the electrodes disposed in middle position of the reactive cell raise the usage rate by overlapped effect as an electrolysis electrode.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.49 no.9
• /
• pp.495-501
• /
• 2000

This paper presents a method to minimize the initial deflection of a multi-layer piezoelectric microactuator without loosing its piezoelectric deflection performance required for light modulating micromirror devices. The multi-layer piezoelectric actuator composed of PZT silicon nitride and platinum layers deflects or buckles due to the gradient of residual stress. Based on the structural analysis results and relationship between process conditions and mechanical properties we have modified the fabrication process and the thickness of thin film layers to reduce the initial residual stress deflection without decreasing its piezoelectric deflection performance. The modified designs fabricated by surface-micromachining process achieved the 77% reduction of the initial deflection compared with that of the conventional method based on the measured micromechanical material properties is applicable to the design refinement of multi-layer MEMS devices and micromechanical structures.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.2
• /
• pp.27-31
• /
• 2017

AZO/Ag/AZO multi-layer films deposited on glass substrate by RF magnetron sputtering and thermal evaporator have a much better electrical properties than Al-doped ZnO thin films. The multi-layer structure consisted of three layers, AZO/Ag/AZO, the electrical and optical properties of AZO/Ag/AZO were changed mainly by thickness of Ag layers. The optimum thickness of Ag layers was determined to be $90{\AA}$ for high optical transmittance and good electrical conductivity. The Ag layers thickness $90{\AA}$ is an optical transmittance greater than 80% of visible light and the obtained multilayer thin film with the low resistivity of $8.05{\times}10-3{\Omega}cm$ and the low sheet resistance $5.331{\Omega}/sq$. Applying to TCO and Solar electrode will improve efficiency.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.156-161
• /
• 2003

It is an interest problem to predict substance distributions in three-dimensional space. Recently, a research field as Geostatistics is advanced. It is a kind of inter- or extrapolation mathematically. Some useful means for the inter- and extrapolation are known, in which slide window method with neural networks is hopeful one. We propose multi-dimensional extrapolation using multi-layer neural networks and the slide-window method. The multi-dimensional extrapolation is not similar to one-dimension. It has plural algorithms. We researched line predictors and local-plain predictors I two-dimensional space. The both predictors are equivalent; however, in multi-dimensional extrapolation, it is very important to find the direction of predictions. Especially, since the slide window method requires information to predict the future in sampling data, if they are not ordered appropriately in the direction, the predictor cannot operate. We tested the extrapolation for typical two-dimensional functions, and found an excellent character of slide-window method based on local-plain. By using the method, we can extrapolate the function until twice-outer regions of the definitions.