• Title/Summary/Keyword: Multi-step

Search Result 1,469, Processing Time 0.027 seconds

Chromosome Karyotype Classification using Multi-Step Multi-Layer Artificial Neural Network (다단계 다층 인공 신경회로망을 이용한 염색체 핵형 분류)

  • Chang, Yong-Hoon;Lee, Kwon-Soon;Chong, Hyeng-Hwan;Jun, Kye-Rok
    • Proceedings of the KOSOMBE Conference
    • /
    • v.1995 no.11
    • /
    • pp.197-200
    • /
    • 1995
  • In this paper, we proposed the multi-step multi-layer artificial neural network(MMANN) to classify the chromosome, Which is used as a chromosome pattern classifier after learning. We extracted three chromosome morphological feature parameters such as centromeric index, relative length ratio, and relative area ratio by means of preprocessing method from ten chromosome images. The feature parameters of five chromosome images were used to learn neural network and the rest of them were used to classify the chromosome images. The experiment results show that the chromosome classification error is reduced much more, comparing with less feature parameters than that of the other researchers.

  • PDF

Design and Development of Multi-rotorcraft-based Unmanned Prototypes of Personal Aerial Vehicle

  • Muljowidodo, Muljowidodo;Budiyono, Agus
    • International Journal of Aeronautical and Space Sciences
    • /
    • v.10 no.2
    • /
    • pp.140-147
    • /
    • 2009
  • The paper presents the design, development and testing activities of the multi-rotorcraft-based unmanned aerial vehicle at the Center for Unmanned System Studies, Institut Teknologi Bandung (ITB), Indonesia. The multi-rotor system was selected as the design stepping stone for future development of personal aerial vehicle prototypes. A step-by-step design program is conducted to study the technology building blocks and critical issues associated with the design, development and operation of personal aerial vehicles. A number of multi-rotor configurations have been investigated providing basic guidelines for developing a stable unmanned aerial platform. The benefit of the presently selected configuration is highlighted and some preliminary testing results are presented.

The Single Step Prediction of Multi-Input Multi-Output System using Chaotic Neural Networks (카오틱 신경망을 이용한 다입력 다출력 시스템의 단일 예측)

  • 장창화;김상희
    • Proceedings of the IEEK Conference
    • /
    • 1999.06a
    • /
    • pp.1041-1044
    • /
    • 1999
  • In This paper, we investigated the single step prediction for output responses of chaotic system with multi Input multi output using chaotic neural networks. Since the systems with chaotic characteristics are coupled between internal parameters, the chaotic neural networks is very suitable for output response prediction of chaotic system. To evaluate the performance of the proposed neural network predictor, we adopt for Lorenz attractor with chaotic responses and compare the results with recurrent neural networks. The results demonstrated superior performance on convergence and computation time than the predictor using recurrent neural networks. And we could also see good predictive capability of chaotic neural network predictor.

  • PDF

Error Analysis and Improvement of the Timoshenko Beam based Finite Element Model for Multi-Stepped Beam Structures (다단 보 구조에서의 티모센코 보 유한요소 모델링 오차분석 및 개선)

  • 홍성욱;이용덕;김만달
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.20 no.10
    • /
    • pp.199-207
    • /
    • 2003
  • The Timoshenko beam model has been known as the most accurate model for representing beam structures. However, the Timoshenko beam model may give rise to a significant error when it is applied to multi-stepped beam structures. This paper is intended to demonstrate the modeling error of Timoshenko beam based finite element model for multi-stepped beam structures and to suggest a new modeling method to improve the accuracy. A tentative bending spring is introduced into the stepped section to represent the softening effect due to the presence of step. This paper also proposes a finite element modeling method in the light with the tentative bending spring model for the step softening effect. The proposed method rigorously adapts computation results from a commercial finite element code. The validity of the proposed method is demonstrated through a series of simulation and experiment.

Multi-lane Detection using TPLF for Smart Navigation (스마트 내비게이션을 위한 TPLF 기반 다중차선 검출 기법)

  • Kim, Sungho;Kwon, Soon
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2014.05a
    • /
    • pp.896-897
    • /
    • 2014
  • Multi-lane detection is useful for the smart navigation system. In this paper, a novel multi-lane detection method is presented. The proposed three point Laplacian filter (TPLF) can complement the weak points of the previous box filter and step filter. The experimental results validate the feasibility of the proposed multi-lane detection method.

  • PDF

Development of Calibration System for Multi-Axis Force/Moment Sensor and Its Uncertainty Evaluation (다축 힘/모멘트 센서 교정기의 개발 및 그의 불확도 평가)

  • Kim, Gab-Soon;Yoon, Jung-Won
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.24 no.10
    • /
    • pp.91-98
    • /
    • 2007
  • This paper describes the development of the calibration system for a multi-axis force/moment sensor and its uncertainty evaluation. This calibration system can generate the continuous forces (${\pm}Fx,\;{\pm}Fy$ and ${\pm}Fz$) and moments (${\pm}Mx,\;{\pm}My$ and ${\pm}Mz$). Many kinds of multi-axis force/moment sensors in industries should be carried out the characteristic test or the calibration with the calibration system that can generate the forces and the moments. The calibration systems have been already developed are the disadvantages of the low capacity, the generation of step forces(10N, 20N ...) and step moments(1Nm, 2Nm ...) with weights, the high coasts in manufacture and so on. In this paper, the calibration system for a multi-axis force/moment sensor that can generate the continuous three forces and three moments was developed. Their ranges are $0{\sim}2000N$ in all force-directions and $0{\sim}400Nm$ in all moment-directions. And the system was evaluated in the expanded relative uncertainty. They were ${\pm}0.0004$ in all forces ${\pm}Fx,\;{\pm}Fy$ and ${\pm}Fz$, and ${\pm}0.0004$ in all moments ${\pm}Mx,\;{\pm}My$ and ${\pm}Mz$.

The Electro-Chemical Treatment for Nitrogen Removal of Metal Finishing Wastewater (질소제거를 위한 금속표면처리폐수의 전기화학적 처리)

  • Sim, Joo-Hyun;Seo, Hyung-Joon;Kim, Dae-Hwan
    • Korean Chemical Engineering Research
    • /
    • v.45 no.2
    • /
    • pp.190-196
    • /
    • 2007
  • This study examined the nitrate removal efficiency which uses an electrowinning, and also analyzed the nitrate removal efficiency under a variety of operating conditions such as nitrate concentrations, pH, current densities, electrodes, reducing agents in order to determine optimal conditions. In addition, the multi-step electro-chemical process test has been also analyzed. During the electrowinning, the identical Zn-Zn and Pt-Ti electrodes in the insoluble oxidation electrode(Pt) has shown the highest nitrate removal efficiency in the 100 mg $NO_3^{-}$ -N/L concentration. In the concentration of 150 mg $NO_3^{-}$ -N/L, the efficiency of the Zn-Zn electrode were 70~85%, and that of Pt-Ti electrode were 40~50% without any change of pH. In the high concentration of 500 and 1,000 mg $NO_3^{-}$ -N/L, the higher the concentration, the more decrease of its nitrate removal efficiency decreased. However, the energy consumed for nitrogen removal increased when the nitrate concentration was high. As a result of the multi-step electro-chemical process test, We chose the Test 4. Because the first, most of the zinc consumed from 1 step was recovered from over the 2 step. The second, amount of consumption anode decreased with insoluble anode Pt from over the 2 step. And the third, Zn cathode increased the possibility of reusing Zn deposited. In view of the results so far achieved, the multi-step electro-chemical process would be applied to treat nitrogen involved in metal finishing wastewater.

The Ground Reinforcement on Daylight Collapsed Block of Crown Head in the Face of the Tunnel of Highway (고속도로 터널막장 천단부의 붕락구간에 대한 지반보강)

  • 천병식;정덕교;한기식;정진교
    • Proceedings of the Korean Geotechical Society Conference
    • /
    • 1999.03a
    • /
    • pp.323-330
    • /
    • 1999
  • Daylight collapse have been occurred by about 5.0m deep at ground surface and collapse of the crown head part of the tunnel have connected to the ground surface during first step of shotcrete work after blasting of upper half section of the tunnel driving at two-way double track tunnel face section on highway construction. This study is for a successful illustration case for the earth improvement method through applying such strengthening methods as cement milk grouting, S.G.R grouting,, steel pipe reinforced multi-step grouting etc. for the purpose of earth strengthening of loosened earth block occurred by tunnel collapse.

  • PDF

A Study on the Tube Sinking Process of the Industrial Boiler Tube (산업용 보일러 Tube의 Sinking 공정에 관한 연구)

  • Kwon, I.K.;Kang, K.P.;Lee, W.J.
    • Proceedings of the KSME Conference
    • /
    • 2001.06c
    • /
    • pp.94-99
    • /
    • 2001
  • Theoretical analysis using finite element method are peformed in order to clarify the formation of the flare-shape defect for multi-step tube sinking process. The parameters of concern were the friction between the tube and the die, and geometrical parameters, such as the die inclination angle, the diameters of the die entrance and exit, and the curvature at the corner of the die exit. The effect of the curvature at the comer of the die exit is dominant for determining the flare-shape defect. In order to minimize the flare-shape defect the curvature at the corner of the die exit should be increased up to a certain level(120mm). Using three-step tube sinking die sets which have different curvatures at the comer of the die exit, several numbers of tests were performed and its results are compared with that of theoretical analysis.

  • PDF

Analysis of Race Car Handling Characteristics Using DADS in Initial Design Step (DADS를 이용한 초기 설계 단계에서의 경기용 차량의 핸들링 특성 해석)

  • Jang, Woon-Geun
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.11 no.2
    • /
    • pp.71-82
    • /
    • 2008
  • In this study, 3 dimensional non-linear race car vehicle model including Chassis, steering and suspension systems were modeled by using Multi-Body Dynamics Simulation Program, DADS 9.5(Dynamic Analysis and Design System),which was used in kinematic and dynamic analysis. A full race car vehicle dynamics model using DADS program was presented and analysis was carried out to estimate the handling characteristics that may be very useful to design a race car in early design stage. The simulation of vehicle handling behavior for step steering input was simulated and compared with different design parameters: torsional stiffness of the front and rear anti roll bars, the motion ratio of the front and rear suspension system, the location of the tie rod joint, in multibody dynamic model. Therefore this simulation model before race car construction in early design step will be helpful for race car designer to save time and limited budget.

  • PDF