• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.849-856
• /
• 2003

본 논문에서는 다층 퍼셉트론의 학습을 위한 새로운 두 단계 학습방법을 제안하였다. 첫 번째 단계는 국소최적해로 빨리 수렴하기 위해 Levenberg-Marquardt 알고리즘을 이용한 국소 탐색 단계이다. 두 번째 단계는 첫 번째 단계에서 찾은 국소최적해가 원하는 수준에 미치지 못할 경우 새로운 국소최적해로 벗어나기 위한 선형탐색을 기반의 터널링 단계이다. 이 방법은 연결가중치 공간에서 전역최적해를 빠르게 찾을 수 잇는 새로운 방법을 제공한다. 4가지 벤치마크 문제에 기존의 다층 퍼셉트론의 학습 알고리즘과 비교 실험을 통해, 제안된 알고리즘이 빠른 수렴 속도와 낮은 오차값을 가짐을 알 수 있었다.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.187-197
• /
• 2005

In this paper, we propose a method to estimate camera motion parameter based on invariant point features, Typically, feature information of image has drawbacks, it is variable to camera viewpoint, and therefore information quantity increases after time, The LM(Levenberg-Marquardt) method using nonlinear minimum square evaluation for camera extrinsic parameter estimation also has a weak point, which has different iteration number for approaching the minimal point according to the initial values and convergence time increases if the process run into a local minimum, In order to complement these shortfalls, we, first proposed constructing feature models using invariant vector of geometry, Secondly, we proposed a two-stage calculation method to improve accuracy and convergence by using 2D homography and LM method, In the experiment, we compared and analyzed the proposed method with existing method to demonstrate the superiority of the proposed algorithms.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.5
• /
• pp.466-472
• /
• 2009

An acoustic leak monitoring system(ALMS) using acoustic emission(AE) technique was applied for leakage detection of nuclear power plant's pipeline which is operated in high temperature and pressure condition. Since this system only monitors the existence of leak using the root mean square(RMS) value of raw signal from AE sensor, the difficulty occurs when the characteristics of leak size and shape need to be evaluated. In this study, dual monitoring system using AE sensor and accelerometer was introduced in order to solve this problem. In addition, artificial neural network(ANN) with Levenberg.Marquardt(LM) training algorithm was also applied due to rapid training rate and gave the reliable classification performance. The input parameters of this ANN were extracted from varying signal received from experimental conditions such as the fluid pressure inside pipe, the shape and size of the leak area. Additional experiments were also carried out and with different objective which is to study the generation and characteristic of lamb and surface wave according to the pipe thickness.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.7
• /
• pp.557-566
• /
• 2018

In this paper, a vision-based relative navigation system is addressed for autonomous aerial refueling. In the air-to-air refueling, it is assumed that the tanker has the drogue, and the receiver has the probe. To obtain the relative information from the drogue, a vision-based imaging technology by infra-red camera is applied. In this process, the relative information is obtained by using Gaussian Least Squares Differential Correction (GLSDC), and Levenberg-Marquadt(LM), where the drouge geometric information calculated through image processing is used. These two approaches proposed in this paper are analyzed through numerical simulations.

• Journal of Radiation Protection and Research
• /
• v.40 no.1
• /
• pp.55-64
• /
• 2015

Dose calculations which are a crucial requirement for radiotherapy treatment planning systems require accuracy and rapid calculations. The conventional radiotherapy treatment planning dose algorithms are rapid but lack precision. Monte Carlo methods are time consuming but the most accurate. The new combined system that Monte Carlo methods calculate part of interesting domain and the rest is calculated by neural can calculate the dose distribution rapidly and accurately. The preliminary study showed that neural networks can map functions which contain discontinuous points and inflection points which the dose distributions in inhomogeneous media also have. Performance results between scaled conjugated gradient algorithm and Levenberg-Marquardt algorithm which are used for training the neural network with a different number of neurons were compared. Finally, the dose distributions of homogeneous phantom calculated by a commercialized treatment planning system were used as training data of the neural network. In the case of homogeneous phantom;the mean squared error of percent depth dose was 0.00214. Further works are programmed to develop the neural network model for 3-dimensinal dose calculations in homogeneous phantoms and inhomogeneous phantoms.

• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.1
• /
• pp.31-36
• /
• 2003

8개의 수정진동자 위에 서로 다른 종류의 Lipid를 코팅하여서 만든 센서 배열을 가지고 유기용매를 인식할 수 있는 System을 구성한다. 유기용매 인식센서에 대한 수학적 모델을 사용하여 여러 가지 유기용매에 대한 센서의 응답으로부터 센서 표면과 유기용매 간의 물질 전달속도 패턴과 친화력 패턴을 얻어 유기용매 종류를 인식하였다. 패턴인식은 인공신경망을 이용하였으며 인공신경망의 연결 강도 수정은 Levenberg-Marquardt 알고리즘을 사용하였다. 신경망의 출력은 4개로 하였고, 디지털 신호인 0과 1의 조합으로 유기용매 종류를 구분하였다. 이 시스템을 이용하여 9개의 유기용매 Acetone, Benzene, Chloroform, Carbon-tetrachloride, Ethylacetate, Buthylacetate, Cyclohexane, Dichloromethane, 1,1,2,2,Tetrachloroethane, 2,2,4Trimethylpentane을 구분하여 인식할 수 있었다.

• Proceedings of the KIPE Conference
• /
• 2017.11a
• /
• pp.71-72
• /
• 2017

본 논문에서는 비선형 최적화 기법을 이용하여 자기 포화(magnetic saturation) 및 교차 결합 현상(cross-coupling effect)을 고려한 매입형 영구자석 전동기(IPMSM)의 실시간 MTPA 제어 방법을 제안한다. 이는 토크 지령 추종과 최소 동손 운전을 만족하는 제한 최적화(constraint optimization) 문제로 접근할 수 있다. 이를 통해 유도한 연립 비선형 방정식의 경우, Levenberg-Marquardt 수치 해석법을 적용하여 안정적이면서 빠르게 해를 구할 수 있다. 이러한 방법을 이용하면 참조표(look-up table) 없이 운전 환경의 실시간 변동을 고려한 효율적인 MTPA 운전이 가능하다. 시뮬레이션을 통해 제안된 알고리즘의 전류 해가 최적 운전점과 일치함을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.105-107
• /
• 2006

As internet streaming data increase, transport protocol such as TCP, TGP-Friendly is important to study control transmission rate and share of Internet bandwidth. In this paper, we propose a TCP-Friendly protocol using Neural Network for media delivery over wired Internet which has various traffic size(PTFRC). PTFRC can effectively send streaming data when occur congestion and predict one-step ahead round trip time and packet loss rate. A multi-layer perceptron structure is used as the prediction model, and the Levenberg-Marquardt algorithm is used as a traning algorithm. The performance of the PTFRC was evaluated by the share of Bandwidth and packet loss rate with various protocols.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.11
• /
• pp.124-131
• /
• 2001

Fault diagnosis of an assembled small motor relies usually on human experts hearing ability. The quality of diagnosis depends, however, heavily on physical conditions of the human experts. A fault diagnosis system for assembled small motors is developed using artificial neural network (ANN) in this paper. It is consisted of sound sampling device and fault diagnosis software package. Six parameters are defined to characterize the sampled sound waves. The Levenberg-Marquardt Backpropagation (LMBP) Algorithm is used to diagnose the fault of assembled small motors. Experimental results for more than two hundred small motors verify the performance of the developed system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.4 s.310
• /
• pp.88-102
• /
• 2006

In multimedia information retrieval, multimedia data are represented as vectors in high dimensional space. To search these vectors effectively, a variety of indexing methods have been proposed. However, the performance of these indexing methods degrades dramatically with increasing dimensionality, which is known as the dimensionality curse. To resolve the dimensionality curse, dimensionality reduction methods have been proposed. They map feature vectors in high dimensional space into the ones in low dimensional space before indexing the data. This paper proposes a method for dimensionality reduction based on a function approximating the Euclidean distance, which makes use of the norm and angle components of a vector. First, we identify the causes of the errors in angle estimation for approximating the Euclidean distance, and discuss basic directions to reduce those errors. Then, we propose a novel method for dimensionality reduction that composes a set of subvectors from a feature vector and maintains only the norm and the estimated angle for every subvector. The selection of a good reference vector is important for accurate estimation of the angle component. We present criteria for being a good reference vector, and propose a method that chooses a good reference vector by using Levenberg-Marquardt algorithm. Also, we define a novel distance function, and formally prove that the distance function lower-bounds the Euclidean distance. This implies that our approach does not incur any false dismissals in reducing the dimensionality effectively. Finally, we verify the superiority of the proposed method via performance evaluation with extensive experiments.