• Title/Summary/Keyword: 방사 기저 함수 신경망

Search Result 19, Processing Time 0.03 seconds

3D face recognition based on radial basis function network (방사 기저 함수 신경망을 이용한 3차원 얼굴인식)

  • Yang, Uk-Il;Sohn, Kwang-Hoon
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.44 no.2 s.314
    • /
    • pp.82-92
    • /
    • 2007
  • This paper describes a novel global shape (GS) feature based on radial basis function network (RBFN) and the extraction method of the proposed feature for 3D face recognition. RBFN is the weighted sum of RBfs, it well present the non-linearity of a facial shape using the linear combination of RBFs. It is the proposed facial feature that the weights of RBFN learned by the horizontal profiles of a face. RBFN based feature expresses the locality of the facial shape even if it is GS feature, and it reduces the feature complexity like existing global methods. And it also get the smoothing effect of the facial shape. Through the experiments, we get 94.7% using the proposed feature and hidden markov model (HMM) to match the features for 100 gallery set with those for 300 test set.

A Study on Speaker Recognition Algorithm Through Wire/Wireless Telephone (유무선 전화를 통한 화자인식 알고리즘에 관한 연구)

  • 김정호;정희석;강철호;김선희
    • The Journal of the Acoustical Society of Korea
    • /
    • v.22 no.3
    • /
    • pp.182-187
    • /
    • 2003
  • In this thesis, we propose the algorithm to improve the performance of speaker verification that is mapping feature parameters by using RBF neural network. There is a big difference between wire vector region and wireless one which comes from the same speaker. For wire/wireless speakers model production, speaker verification system should distinguish the wire/wireless channel that based on speech recognition system. And the feature vector of untrained channel models is mapped to the feature vector(LPC Cepstrum) of trained channel model by using RBF neural network. As a simulation result, the proposed algorithm makes 0.6%∼10.5% performance improvement compared to conventional method such as cepstral mean subtraction.

Structural Design of Differential Evolution-based Multi Output Radial Basis Funtion Polynomial Neural Networks (차분 진화알고리즘 기반 다중 출력 방사형 기저 함수 다항식 신경 회로망 구조 설계)

  • Kim, Wook-Dong;Ma, Chang-Min;Oh, Sung-Kwun
    • Proceedings of the KIEE Conference
    • /
    • 2011.07a
    • /
    • pp.1964-1965
    • /
    • 2011
  • 본 연구에서는 패턴분류를 위해 기존의 방사형 기저 함수 신경회로망(Radial Basis Funtion Neural Network)과 다항식 신경회로망(Polynomial Neural Network)을 결합한 다중 출력 방사형 기저 함수다항식 신경회로망 (Multi Output Radial Basis Funtion Polynomial Neural Network)의 분류기를 제안한다. 제안된 모델은 PNN을 기본 구조로 하여 1층에 기존의 다항식 노드 대신 다중 출력 형태의 RBFNN을 적용 한다. RBFNN의 은닉층에는 기존의 활성함수가 아닌 fuzzy 클러스터링을 사용하여 입력 데이터의 특성을 고려한 적합도를 사용하였다. PNN은 입력변수의 수와 다항식 차수가 모델의 성능을 결정함으로 최적화가 필요하며 본 논문에서는 Differential Evolution(DE)을 사용하여 모델의 구조 및 파라미터를 최적화시켜 모델의 성능을 향상시켰다. 패턴분류기로써의 제안된 모델을 평가하기 위해 pima 데이터를 이용하였다.

  • PDF

Load Modeling Method Based on Radial Basis Function Networks Considering of Hormonic components (고조파를 고려한 방사기저함수 네트워크 기반의 부하모델링 기법)

  • Ji, Pyeong-Shik;Lee, Dae-Jong;Lee, Jong-Pil;Lim, Jae-Yoon
    • Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
    • /
    • v.22 no.4
    • /
    • pp.46-53
    • /
    • 2008
  • In this study, we developed RBFN(Radial Basis Function Networks) based load modeling method with harmonic components. The developed method considers harmonic information as well as fundamental frequency and voltage considered as essential factors in conventional method. Thus, the reposed method makes it possible to effectively estimate load characteristics in power lines with harmonics. RBFN has some advantage such as simple structure and rapid computation ability compared with multi-layer perceptorn which is extensively applied for load modeling. To verify the effectiveness, the proposed method has been intensively tested with various dataset acquired under the different frequency and voltage and compared it with conventional methods such as polynomial method, MLPN and RBFN with no harmonic components.

RBFNN Based Decentralized Adaptive Tracking Control Using PSO for an Uncertain Electrically Driven Robot System with Input Saturation (입력 포화를 가지는 불확실한 전기 구동 로봇 시스템에 대해 PSO를 이용한 RBFNN 기반 분산 적응 추종 제어)

  • Shin, Jin-Ho;Han, Dae-Hyun
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.19 no.2
    • /
    • pp.77-88
    • /
    • 2018
  • This paper proposes a RBFNN(Radial Basis Function Neural Network) based decentralized adaptive tracking control scheme using PSO(Particle Swarm Optimization) for an uncertain electrically driven robot system with input saturation. Practically, the magnitudes of input voltage and current signals are limited due to the saturation of actuators in robot systems. The proposed controller overcomes this input saturation and does not require any robot link and actuator model parameters. The fitness function used in the presented PSO scheme is expressed as a multi-objective function including the magnitudes of voltages and currents as well as the tracking errors. Using a PSO scheme, the control gains and the number of the RBFs are tuned automatically and thus the performance of the control system is improved. The stability of the total control system is guaranteed by the Lyapunov stability analysis. The validity and robustness of the proposed control scheme are verified through simulation results.

Radial Basis Function Neural Network Modeling of Depression Experience in Elementary School Students of Multi-cultural Families (방사기저함수 인공 신경망을 이용한 다문화가정 초등학생의 우울증상 경험 예측 모델링)

  • Byeon, Haewon
    • Journal of the Korea Convergence Society
    • /
    • v.8 no.11
    • /
    • pp.293-298
    • /
    • 2017
  • The purpose of this study was to analyze the risk factors of depression in elementary school students in Korea. The subjects of the study were 23,291 elementary school students (12,016 male, 11,275 female) aged 9 to 12 years. Dependent variable was defined as experience of depression. Explanatory variables were included as sex, residential areas, social discrimination experience, experience of school violence for the past year, experience of Korean language education, experience of using multicultural family support center, reading to Korean, speaking to Korean, and writing to Korean, listening to Korean. In the RBF neural network analysis, experience of Korean education, experience of school violence, experience of Korean social discrimination, level of Korean reading were significantly associated with depression in elementary school students. In order to prevent depression in multicultural children, priority attention and counseling are needed for the group whose level of Korean reading is low.

Surrogate Models and Genetic Algorithm Application to Approximate Optimization of Discrete Design for A60 Class Deck Penetration Piece (A60 급 갑판 관통 관의 이산설계 근사최적화를 위한 대리모델과 유전자 알고리즘 응용)

  • Park, Woo Chang;Song, Chang Yong
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.27 no.2
    • /
    • pp.377-386
    • /
    • 2021
  • The A60 class deck penetration piece is a fire-resistant system installed on a horizontal compartment to prevent flame spreading and protect lives in fire accidents in ships and offshore plants. This study deals with approximate optimization using discrete variables for the fire resistance design of an A60 class deck penetration piece using different surrogate models and a genetic algorithm. Transient heat transfer analysis was performed to evaluate the fire resistance design of the A60 class deck penetration piece. For the approximate optimization of the piece, the length, diameter, material type, and insulation density were applied to discrete design variables, and temperature, productivity, and cost constraints were considered. The approximate optimum design problem based on the surrogate models was formulated such that the discrete design variables were determined by minimizing the weight of the piece subjected to the constraints. The surrogate models used in the approximate optimization were the response surface model, Kriging model, and radial basis function-based neural network. The approximate optimization results were compared with the actual analysis results in terms of approximate accuracy. The radial basis function-based neural network showed the most accurate optimum design results for the fire resistance design of the A60 class deck penetration piece.

Absolute Vehicle Speed Estimation using Neural Network Model (신경망 모델을 이용한 차량 절대속도 추정)

  • Oh, Kyeung-Heub;Song, Chul-Ki
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.19 no.9
    • /
    • pp.51-58
    • /
    • 2002
  • Vehicle dynamics control systems are. complex and non-linear, so they have difficulties in developing a controller for the anti-lock braking systems and the auto-traction systems. Currently the fuzzy-logic technique to estimate the absolute vehicle speed is good results in normal conditions. But the estimation error in severe braking is discontented. In this paper, we estimate the absolute vehicle speed by using the wheel speed data from standard 50-tooth anti-lock braking system wheel speed sensors. Radial symmetric basis function of the neural network model is proposed to implement and estimate the absolute vehicle speed, and principal component analysis on input data is used. Ten algorithms are verified experimentally to estimate the absolute vehicle speed and one of those is perfectly shown to estimate the vehicle speed with a 4% error during a braking maneuver.

A Comparative Study on Approximate Models and Sensitivity Analysis of Active Type DSF for Offshore Plant Float-over Installation Using Orthogonal Array Experiment (직교배열실험을 이용한 해양플랜트 플로트오버 설치 작업용 능동형 DSF의 민감도해석과 근사모델 비교연구)

  • Kim, Hun-Gwan;Song, Chang Yong
    • Journal of the Korea Convergence Society
    • /
    • v.12 no.3
    • /
    • pp.187-196
    • /
    • 2021
  • The paper deals with comparative study for characteristics of approximation of design space according to various approximate models and sensitivity analysis using orthogonal array experiments in structure design of active type DSF which was developed for float-over installation of offshore plant. This study aims to propose the orthogonal array experiments based design methodology which is able to efficiently explore an optimum design case and to generate the accurate approximate model. Thickness sizes of main structure member were applied to the design factors, and output responses were considered structure weight and strength performances. Quantitative effects on the output responses for each design factor were evaluated using the orthogonal array experiment. Best design case was also identified to improve the structure design with weight minimization. From the orthogonal array experiment results, various approximate models such as response surface model, Kriging model, Chebyshev orthogonal polynomial model, and radial basis function based neural network model were generated. The experiment results from orthogonal array method were validated by the approximate modeling results. It was found that the radial basis function based neural network model among the approximate models was able to approximate the design space of the active type DSF with the highest accuracy.

Decentralized Robust Adaptive Neural Network Control for Electrically Driven Robot Manipulators with Bounded Input Voltages (제한된 입력 전압을 갖는 전기 구동 로봇 매니퓰레이터에 대한 분산 강인 적응 신경망 제어)

  • Shin, Jin-Ho;Kim, Won-Ho
    • Transactions of the Korean Society for Noise and Vibration Engineering
    • /
    • v.25 no.11
    • /
    • pp.753-763
    • /
    • 2015
  • This paper proposes a decentralized robust adaptive neural network control scheme using multiple radial basis function neural networks for electrically driven robot manipulators with bounded input voltages in the presence of uncertainties. The proposed controller considers both robot link dynamics and actuator dynamics. Practically, the controller gain coefficients applied at each joint may be nonlinear time-varying and the input voltage at each joint is saturated. The proposed robot controller overcomes the various uncertainties and the input voltage saturation problem. The proposed controller does not require any robot and actuator parameters. The adaptation laws of the proposed controller are derived by using the Lyapunov stability analysis and the stability of the closed-loop control system is guaranteed. The validity and robustness of the proposed control scheme are verified through simulation results.