• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1994년도 추계학술대회
• /
• pp.81-84
• /
• 1994

A clinically oriented EEG and EP mapping system was developed with user-friendly interface and easy interactive operations. The system was based on the graphical user interface developed with C/C++ and Software Development Kit (SDK) operated under Microsoft Windows 3.1. Continuous acquisition for the EEG signal and burst mode acquisition for EEG signal syncronized to the external stimuli arc implemented with real time display. A neural network based automatic artifact discrimation is developed and implemented with which examination time can be reduced by a factor of 3 or more. Several bands of spectral maps and spectrums arc displayed for EEG diagnosis. Amplitude maps of EP signal at specified times by operator are displayed together with cine mode of EP maps for dynamic study. Source localization and other statistical signal processing are also included.

• 한국통신학회논문지
• /
• 제22권11호
• /
• pp.2365-2374
• /
• 1997

This paper describes two algorithms for technology mapping of multiple output functions into interesting and pupular FPGAs(Field Programmable Gate Array) that use look-yp table memories. For improvement of technology mapping for FPGA, we use the functional decompoition method for multiple output functions. Two algorithms are proposed. The one is the Roth-Karpalgorithm extended for multiple output functions. The other is the efficient algorithm which looks for common decomposition functions through the decomposition procedure. The cost function is used to minimize the number of CLBs and nets and to improve performance of the network. Finally we compare our new algorithm with previous logic design technique. Experimental resutls show sigificant reduction in the number of CLBs and nets.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.842-847
• /
• 2005

This paper proposes a novel real-time EMG pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals. To cope with the nonstationary signal property of the EMG, features are extracted by wavelet packet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear feature projection composed of PCA and SOFM. The dimensionality reduction by PCA simplifies the structure of the classifier, and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features to a new feature space with high class separability. Finally a multilayer neural network is employed as the pattern classifier. We implement a real-time control system for a multifunction virtual hand. From experimental results, we show that all processes, including virtual hand control, are completed within 125 msec, and the proposed method is applicable to real-time myoelectric hand control without an operation time delay.

• 전자공학회논문지A
• /
• 제33A권10호
• /
• pp.177-185
• /
• 1996

This paper describes several algorithms for technolgoy mapping of logic functions into interesting and popular FPGAs that use look-up table memories. In order to improved the technology mapping for FPGA, some existing multi-level logic synthesis, decomposition reduction and packing techniques are analyzed and compared. And then new algorithms such as merging fanin, unified reduction and multiple disjoint decomposition which are used for combinational logic design, are proposed. The cost function is used to minimize the number of CLBs and edges of the network. The cost is a linear combination of each weight that is given by user. Finally we compare our new algorithm with previous logic design technique. In an experimental comparison our algorithm requires 10% fewer CLB and nets than SIS-pga.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.68.3-68
• /
• 2002

This paper presents a neural network approach to control exhaust gas recirculation(EGR) in a Liquefied Petroleum Gas(LPG) engine. In order to meet Increasingly stringent automotive exhaust emission regulations, alternative fuels such as LPG engines have been developed in many countries. HC&CO emissions of LPG engines can be easily reduced through air-fuel ratio control, but the control effect on NOx reduction is not good enough. Consequently EGR system is introduced to achieve a significant reduction in NOx emissions. Conventional EGR control uses the mapping method. The calibration time is long and the work is complex when adopting this mapping method. However neural networks are suitable f...

• 한국항행학회논문지
• /
• 제15권4호
• /
• pp.616-625
• /
• 2011

본 연구에서는 지형을 Rendering 기법의 대표적인 방법인 Geometry Clipmaps와 ROAM 2.0을 분석하여 Rendering 연산에 소요되는 연산을 CPU가 아닌 GPU에 중점을 두어 보다 빠르고 넓은 가시화 영역을 보장하는 확장된 Geometry Clipmaps 알고리즘을 제안한다. 확장된 알고리즘은 LOD(Level of Detail)을 통한 각 레벨의 Mesh 구성 방법, 레벨간의 연결망 Mesh 구성 방법, VFC(View Frustum Culling)을 사용하여 Rendering을 최적화 할 수 있는 Mesh Block화 방안 그리고 최대 1m 해상도를 갖는 고해상도 영상 Mapping 방안 등을 포함하고 있다.

• 한국정밀공학회지
• /
• 제15권3호
• /
• pp.107-118
• /
• 1998

Two-phase neuro-system identification method is presented. The 1$^{st}$-phase identification uses conventional neural network mapping for modeling an input-output system. The 2$^{nd}$ -phase modeling is also performed sequentially using the 1$^{st}$-phase modeling errors. In the 2$^{nd}$ a phase modeling, newly generated input signals, which are obtained by summing the 1st-phase modeling error and artificially generated uniform series, are utilized as system's I-O mapping elements. The 1$^{st}$-phase identification is interpreted as a “Real Model” system identification because it uses system's real data(i.e., observations and control inputs) while the 2$^{nd}$ -phase identification as a “Artificial Model” identification because of using artificial data. Experimental results are given to verify that the two-phase neuro-system identification could reduce the overall modeling errors.rrors.

• 수산해양교육연구
• /
• 제25권1호
• /
• pp.192-197
• /
• 2013

To overcome the mismatch of heat demand and heat supply is important as considering point on heat utilizing aspects in Urban area. At this point, It need to know the plan of heat networks on the heat balance aspects. The purpose of this study is to know the method of heat evaluation on heat network around costal area. It is need to building uses to calculate the amounts of heat demand. 25 different types of building uses were supplied, but it was reclassified 10 types and calculated the amounts of heat demand in the costal area. The results was described on the area with GIS mapping.

• Journal of electromagnetic engineering and science
• /
• 제11권3호
• /
• pp.192-200
• /
• 2011

This paper proposes a new modeling method for estimating the impedance of an on-chip power/ground meshed plane. Frequency dependent R, L, and C parameters are extracted based on the proposed method so that the model can be applied from DC to high frequencies. The meshed plane model is composed of two parts: coplanar multi strip (CMS) and conductor-backed CMS. The conformal mapping technique and the scaled conductivity concept are used for accurate modeling of the CMS. The developed microstrip approach is applied to model the conductor-backed CMS. The proposed modeling method has been successfully verified by comparing the impedance of RLC circuit based on extracted parameters and the simulated impedance using a 3D-field solver.

• 산업공학
• /
• 제10권3호
• /
• pp.125-132
• /
• 1997

We proposed a 2-step neural network approach for estimating machining parameters of electric discharge wire cut. The first step net, which is described as a backward neuro-estimation, is designed for estimating coarse cutting parameters while the second phase net, as a polishing forward neuro-estimation, is utilized for determining fine parameters. Sequential estimation procedure, based on backward and forward net, is performed using the net's approximation capability which is M to 1 and 1 to M mapping property. Experimental results an given to evaluate the accuracy of the proposed 2-step neuro-estimation.