• 제목/요약/키워드: Lorena order

검색결과 4건 처리시간 0.019초

ORDER RESTRICTED STATISTICAL INFERENCE ON LORENZ CURVES OF PARETO DISTRIBUTIONS

  • Oh, Myongsik
    • Journal of applied mathematics & informatics
    • /
    • 제13권1_2호
    • /
    • pp.457-470
    • /
    • 2003
  • The comparison of two or more Lorenz curves of Pareto distributions of first kind under arbitrary order restriction is studied. The problem is turned out to be a statistical inference problem concerning scale parameters under order restriction. We assume that the location parameters of Palate distributions are completely unknown. In this paper the maximum likelihood estimation and likelihood ratio tests for and against order restriction are proposed.

Curved beam through matrices associated with support conditions

  • Gimena, Faustino N.;Gonzaga, Pedro;Valdenebro, Jose V.;Goni, Mikel;Reyes-Rubiano, Lorena S.
    • Structural Engineering and Mechanics
    • /
    • 제76권3호
    • /
    • pp.395-412
    • /
    • 2020
  • In this article, the values of internal force and deformation of a curved beam under any action with the firm or elastic supports are determined by using structural matrices. The article presents the general differential formulation of a curved beam in global coordinates, which is solved in an orderly manner using simple integrals, thus obtaining the transfer matrix expression. The matrix expression of rigidity is obtained through reordering operations on the transfer notation. The support conditions, firm or elastic, provide twelve equations. The objective of this article is the construction of the algebraic system of order twenty-four, twelve transfer equations and twelve support equations, which relates the values of internal force and deformation associated with the two ends of the directrix of the curved beam. This final algebraic system, expressed in matrix form, is divided into two subsystems: twelve algebraic equations of internal force and twelve algebraic equations of deformation. The internal force and deformation values for any point in the curved beam directrix are determined from these values in the initial position. The five examples presented show how to apply the matrix procedures developed in this article, whether they are curved beams with the firm or elastic support.

Study of the Dependency of the Specific Power Absorption Rate on Several Characteristics of the Excitation Magnetic Signal when Irradiating a SPION-containing Ferrofluid

  • Rosales, Alejandra Mina;Aznar, Elena;Coll, Carmen;Mendoza, Ruben A. Garcia;Bojorge, A. Lorena Urbano;Gonzalez, Nazario Felix;Martinez-Manez, Ramon;del Pozo Guerrero, Francisco;Olmedo, Jose Javier Serrano
    • Journal of Magnetics
    • /
    • 제21권3호
    • /
    • pp.460-467
    • /
    • 2016
  • Magnetic hyperthermia mediated by superparamagnetic particles is mainly based in sinusoidal waveforms as excitation signals. Temperature changes are conventionally explained by rotation of the particles in the surrounding medium. This is a hypothesis quite questionable since habitual experimental setups only produce changes in the magnetic module, not in the field lines trajectories. Theoretical results were tested by changing the waveform of the exciting signal in order to compare non-sinusoidal signals against sinusoidal signals. Experiments were done at different frequencies: 200 KHz, 400 KHz, 600 KHz, 800 KHz and 1 MHz. Superparamagnetic Iron Oxide samples (SPION), made of magnetite ($Fe_3O_4$) and suspended in water (100 mg/ml), were used. Magnetic field strength varies from $0.1{\pm}0.015KA/m$ to $0.6{\pm}0.015KA/m$. In this study was observed that the power loss depends on the applied frequency: for 1 to 2.5 RMS current the responses for each signal are part of the higher section of the exponential function, and for 3.5 to 8 RMS current the response is clearly the decrement exponential function's tale (under $1{\times}10^3LER/gr$).

유전자 알고리즘을 이용한 다분류 SVM의 최적화: 기업신용등급 예측에의 응용 (Optimization of Multiclass Support Vector Machine using Genetic Algorithm: Application to the Prediction of Corporate Credit Rating)

  • 안현철
    • 경영정보학연구
    • /
    • 제16권3호
    • /
    • pp.161-177
    • /
    • 2014
  • 기업신용등급은 금융시장의 신뢰를 구축하고 거래를 활성화하는데 있어 매우 중요한 요소로서, 오래 전부터 학계에서는 보다 정확한 기업신용등급 예측을 가능케 하는 다양한 모형들을 연구해 왔다. 구체적으로 다중판별분석(Multiple Discriminant Analysis, MDA)이나 다항 로지스틱 회귀분석(multinomial logistic regression analysis, MLOGIT)과 같은 통계기법을 비롯해, 인공신경망(Artificial Neural Networks, ANN), 사례기반추론(Case-based Reasoning, CBR), 그리고 다분류 문제해결을 위해 확장된 다분류 Support Vector Machines(Multiclass SVM)에 이르기까지 다양한 기법들이 학자들에 의해 적용되었는데, 최근의 연구결과들에 따르면 이 중에서도 다분류 SVM이 가장 우수한 예측성과를 보이고 있는 것으로 보고되고 있다. 본 연구에서는 이러한 다분류 SVM의 성능을 한 단계 더 개선하기 위한 대안으로 유전자 알고리즘(GA, Genetic Algorithm)을 활용한 최적화 모형을 제안한다. 구체적으로 본 연구의 제안모형은 유전자 알고리즘을 활용해 다분류 SVM에 적용되어야 할 최적의 커널 함수 파라미터값들과 최적의 입력변수 집합(feature subset)을 탐색하도록 설계되었다. 실제 데이터셋을 활용해 제안모형을 적용해 본 결과, MDA나 MLOGIT, CBR, ANN과 같은 기존 인공지능/데이터마이닝 기법들은 물론 지금까지 가장 우수한 예측성과를 보이는 것으로 알려져 있던 전통적인 다분류 SVM 보다도 제안모형이 더 우수한 예측성과를 보임을 확인할 수 있었다.