• Title/Summary/Keyword: Local Minimum

Search Result 222, Processing Time 0.381 seconds

Avoidance obstacles using A* algorithm in the Eyebot (A*를 이용한 장애물 회피)

  • 정현룡;김영배
    • Proceedings of the Korean Society of Precision Engineering Conference
    • /
    • 2003.06a
    • /
    • pp.468-471
    • /
    • 2003
  • The A* algorithm is usually used in game programming, mainly because it is fast in finding a optimal path to goal. In this paper. This algorithm was utilized for path finding, HIMM(Histogramic In-Motion Mapping) method is used in map-building. Map is updated continuously with range data sampled by PSD sensors From the map, A* algorithm finds a optimal path and sends subsequently the most suitable point to the Eyebot. A* algorithm has been tested on the Eyebot in various unknown maps of unknown and proved to work well. It could escape the local minimum, also.

  • PDF

Optimal Feature Extraction for Multiclass Problems through Proper Choice of Initial Feature Vectors (초기 피춰벡터 설정을 통한 다중클래스 문제에 대한 최적 피춰 추출 기법)

  • 최의선;이철희
    • Proceedings of the IEEK Conference
    • /
    • 1999.06a
    • /
    • pp.647-650
    • /
    • 1999
  • In this Paper, we propose an optimal feature extraction for multiclass problems through proper choice of initial feature vectors. Although numerous feature extraction algorithms have been proposed, those algorithms are not optimal for multiclass problems. Recently, an optimal feature extraction algorithm for multiclass problems has been proposed, which provides a better performance than the conventional feature extraction algorithms. In this paper, we improve the algorithm by choosing good initial feature vectors. As a result, the searching time is significantly reduced. The chance to be stuck in a local minimum is also reduced.

  • PDF

GEOMETRIC FITTING OF CIRCLES

  • Kim, Ik-Sung
    • Journal of applied mathematics & informatics
    • /
    • v.7 no.3
    • /
    • pp.983-994
    • /
    • 2000
  • We consider the problem of determining the circle of best fit to a set of data points in the plane. In [1] and [2] several algorithms already have been given for fitting a circle in least squares sense of minimizing the geometric distances to the given data points. In this paper we present another new descent algorithm which computes a parametric represented circle in order to minimize the sum of the squares of the distances to the given points. For any choice of starting values our algorithm has the advantage of ensuring convergence to a local minimum. Numerical examples are given.

Efficient Motion Estimation for Depth Map (깊이영상에 적합한 효율적인 움직임 예측 방법)

  • Oh, Byung Tae
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2013.06a
    • /
    • pp.348-350
    • /
    • 2013
  • 본 논문에서는 깊이영상의 특징을 이용하여 깊이영상에 보다 적합한 움직임 예측방법에 대한 방식을 제안한다. 기존 컬러영상 기반으로 제안되었던 대부분의 움직임 예측 방법들이 깊이영상에 적용할 경우 local minimum 에 빠지게 되어 이에 따른 압축 성능 저하가 있음을 확인하였다. 본 논문에서는 이러한 문제점들이 깊이영상의 오브젝트 경계 영역에서 나타나게 됨을 분석하며, 이러한 문제점을 해결하기 위해 깊이영상의 경계 영역에 대해 feature matching 방식을 이용한 full search 방식을 제안한다. 실험적인 결과는 제안방식이 기존 full search 방식과 비교하여 성능은 비슷하게 유지한 채 복잡도를 크게 개선할 수 있음을 보여준다.

  • PDF

AN ALGORITHM FOR CIRCLE FITTING IN ℝ3

  • Kim, Ik Sung
    • Communications of the Korean Mathematical Society
    • /
    • v.34 no.3
    • /
    • pp.1029-1047
    • /
    • 2019
  • We are interested in the problem of determining the best fitted circle to a set of data points in space. This can be usually obtained by minimizing the geometric distances or various approximate algebraic distances from the fitted circle to the given data points. In this paper, we propose an algorithm in such a way that the sum of the squares of the geometric distances is minimized in ${\mathbb{R}}^3$. Our algorithm is mainly based on the steepest descent method with a view of ensuring the convergence of the corresponding objective function Q(u) to a local minimum. Numerical examples are given.

Prediction of Daily Water Supply Using Neuro Genetic Hybrid Model (뉴로 유전자 결합모형을 이용한 상수도 1일 급수량 예측)

  • Rhee, Kyoung-Hoon;Kang, Il-Hwan;Moon, Byoung-Seok;Park, Jin-Geum
    • Journal of Environmental Impact Assessment
    • /
    • v.14 no.4
    • /
    • pp.157-164
    • /
    • 2005
  • Existing models that predict of Daily water supply include statistical models and neural network model. The neural network model was more effective than the statistical models. Only neural network model, which predict of Daily water supply, is focused on estimation of the operational control. Neural network model takes long learning time and gets into local minimum. This study proposes Neuro Genetic hybrid model which a combination of genetic algorithm and neural network. Hybrid model makes up for neural network's shortcomings. In this study, the amount of supply, the mean temperature and the population of the area supplied with water are use for neural network's learning patterns for prediction. RMSE(Root Mean Square Error) is used for a MOE(Measure Of Effectiveness). The comparison of the two models showed that the predicting capability of Hybrid model is more effective than that of neural network model. The proposed hybrid model is able to predict of Daily water, thus it can apply real time estimation of operational control of water works and water drain pipes. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 11.81% and the average error was lower than 1.76%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

Preprocessing Effect by Using k-means Clustering and Merging .Algorithms in MR Cardiac Left Ventricle Segmentation (자기공명 심장 영상의 좌심실 경계추출에서의 k 평균 군집화와 병합 알고리즘의 사용으로 인한 전처리 효과)

  • Ik-Hwan Cho;Jung-Su Oh;Kyong-Sik Om;In-Chan Song;Kee-Hyun Chang;Dong-Seok Jeong
    • Journal of Biomedical Engineering Research
    • /
    • v.24 no.2
    • /
    • pp.55-60
    • /
    • 2003
  • For quantitative analysis of the cardiac diseases. it is necessary to segment the left-ventricle (LY) in MR (Magnetic Resonance) cardiac images. Snake or active contour model has been used to segment LV boundary. However, the contour of the LV front these models may not converge to the desirable one because the contour may fall into local minimum value due to image artifact inside of the LY Therefore, in this paper, we Propose the Preprocessing method using k-means clustering and merging algorithms that can improve the performance of the active contour model. We verified that our proposed algorithm overcomes local minimum convergence problem by experiment results.

Stochastic Optimization Approach for Parallel Expansion of the Existing Water Distribution Systems (추계학적 최적화방법에 의한 기존관수로시스템의 병열관로 확장)

  • Ahn, Tae-Jin;Choi, Gye-Woon;Park, Jung-Eung
    • Water for future
    • /
    • v.28 no.2
    • /
    • pp.169-180
    • /
    • 1995
  • The cost of a looped pipe network is affected by a set of loop flows. The mathematical model for optimizing the looped pipe network is expressed in the optimal set of loop flows to apply to a stochastic optimization method. Because the feasible region of the looped pipe network problem is nonconvex with multiple local optima, the Modified Stochastic Probing Method is suggested to efficiently search the feasible region. The method consists of two phase: i) a global search phase(the stochastic probing method) and ii) a local search phase(the nearest neighbor method). While the global search sequentially improves a local minimum, the local search escapes out of a local minimum trapped in the global search phase and also refines a final solution. In order to test the method, a standard test problem from the literature is considered for the optimal design of the paralled expansion of an existing network. The optimal solutions thus found have significantly smaller costs than the ones reported previously by other researchers.

  • PDF

Development of Google Map-based USGS HYSEP and Application (Web 기반 USGS HYSEP 기저유출 분리 시스템 개발과 평가)

  • Jang, Won-Seok;Park, Youn-Shik;Kim, Jong-Gun;Engel, Bernard A.;Lim, Kyoung-Jae
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2009.05a
    • /
    • pp.1417-1421
    • /
    • 2009
  • 최근 들어 유역의 정확한 수문현상을 파악하기 위하여 유역의 유출량 자료를 직접 유출과 기저유출로 분리한 후 수문 모형의 직접유출 및 기저유출의 수문컴포넌트 검증에 활용하는 연구가 많이 이루어지고 있다. 미국 국립지리국 (USGS) 에서 개발한 HYSEP 모형이 지난 수 년 동안 유출 컴포넌트 분리에 널리 이용되어 오고 있다. 그러나 USGS 기반의 HYSEP의 경우 능숙한 컴퓨터 사용자가 아닌 비전문가들이 HYSEP을 운영하기에는 여러 가지 많은 제한점이 있어 왔다. 그리하여 본 연구에서는 고해상도 위성영상 Google Map 기반의 기저유출분리 프로그램인 Web-based HYSEP 인터페이스를 개발하였다. 이 시스템에는 HYSEP에서 제공하는 3가지 방법인 Fixed Interval / Sliding Interval / Local Minimum 방법이 제공되고 있다. 본 연구에서 개발된 Google Map 기반의 HYSEP 시스템은 USGS 유량 관측지점들에 대해 XML 데이터 포맷으로 DB를 구축하여 Google Map 과 연계하였으며 이를 통해 사용자가 원하는 관측소의 실시간 유량자료를 다운로드 할 수 있도록 개발되어졌다. Google Map 기반의 HYSEP 기저유출 분리 시스템(http://www.EnvSys.co.kr/${\sim}$hysep)은 Perl/CGI 및 자바스크립트, Google Map script 등을 이용하여 개발되었다. 현재 개발된 Google Map 기반의 USGS HYSEP 시스템은 한 곳의 유량관측지점에 대해서 총 3가지 기저유출 모듈을 적용하여 결과를 제공하고 있으며, 그 결과를 테이블이나 그래프 형태로 제공하도록 되어 있다. 본 연구에서는 Google Map 기반의 USGS HYSEP 시스템을 이용하여 미국 인디애나 주의 Little Eagle Creek 유역의 유량자료와 Fixed Interval / Sliding Interval / Local Minimum 방법을 이용하여 기저유출을 분리하였으며, 기존에 널리 활용되는 기저유출 분리 프로그램인 Web 기반의 WHAT 시스템 (http://www.EnvSys.co.k.r/~what) 산정 기저유출량과 비교분석하였다. 분석결과 HYSEP 예측 기저유출치가 전반적으로 WHAT 예측치보다 크게 산정되었다. WHAT 시스템과 본 연구에서 개발한 Web 기반의 HYSEP 일단위 기저유출량을 비교해 본 결과 $R^{2}$가 0.56, EI는 0.52로 어느 정도 비슷한 경향을 나타냈으나, 유역의 특성을 반영하는 WHAT 시스템과는 달리 주어진 유량자료만을 이용하여 기저유출을 분리하는 Web 기반의 HYSEP 기저유출 분리모듈을 개선할 필요가 있는 것으로 판단된다.

  • PDF

Principal Feature Extraction on Image Data Using Neural Networks of Learning Algorithm Based on Steepest Descent and Dynamic tunneling (기울기하강과 동적터널링에 기반을 둔 학습알고리즘의 신경망을 이용한 영상데이터의 주요특징추출)

  • Jo, Yong-Hyeon
    • The Transactions of the Korea Information Processing Society
    • /
    • v.6 no.5
    • /
    • pp.1393-1402
    • /
    • 1999
  • This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12${\times}$12pixels and the Lenna image of 128${\times}$128 pixels respectively. The simulation results shows that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer neural networks and the BP algorithm for multilayer neural network.

  • PDF