• 제목/요약/키워드: Coefficient Selection

검색결과 514건 처리시간 0.025초

Note on Use of $R^2$ for No-intercept Model

  • Do, Jong-Doo;Kim, Tae-Yoon
    • Journal of the Korean Data and Information Science Society
    • /
    • 제17권2호
    • /
    • pp.661-668
    • /
    • 2006
  • There have been some controversies on the use of the coefficient of determination for linear no-intercept model. One definition of the coefficient of determination, $R^2={\sum}\;{\widehat{y^2}}\;/\;{\sum}\;y^2$, is being widely accepted only for linear no-intercept models though Kvalseth (1985) demonstrated some possible pitfalls in using such $R^2$. Main objective of this note is to report that $R^2$ is not a desirable measure of fit for the no-intercept linear model. In fact it is found that mean square error(MSE) could replace $R^2$ efficiently in most cases where selection of no-intercept model is at issue.

  • PDF

유한요소법을 이용한 지상 파이프 반사계수 규명 (Identification of Reflection Coefficients for Overground Pipes Using Finite Element Method)

  • 김영환;박경조;강우석
    • 동력기계공학회지
    • /
    • 제15권3호
    • /
    • pp.18-24
    • /
    • 2011
  • In this study, the reflection of the L(0,2), axially symmetric guided elastic wave from defects in pipes above ground is examined using finite element method. Phase and group velocity dispersion curves for the pipe were presented for the selection of the excitation mode. Some simple signal processing was applied to determine the amplitude of each of the reflected waves and to calculate the reflection coefficient. The results show the reflection coefficient of this mode is very close to a linear function of the circumferential extent of the defect. The motivation for the work was the development of a technique for inspecting chemical plant pipelines, but the study addresses the nature of the reflection function and its general applicability.

유전 알고리즘을 이용한 강성회전체의 평형잡이 (Balancing of a Rigid Rotor using Genetic Algorithms)

  • 양보석;주호진
    • Journal of Advanced Marine Engineering and Technology
    • /
    • 제20권2호
    • /
    • pp.108-108
    • /
    • 1996
  • This paper describes a new approach to solve balancing of a rigid rotor. In this paper, the balancing of the rigid rotor using genetic algorithms, which are search algorithms based on the mechanics of natural selection and natural genetics is proposed. Under the assumption that the initial vibration values used to calculate correction masses contain errors, the influence coefficient method, the least squares method and a genetic algorithm are compared. The results show that the vibration amplitude obtained with the least squares method and the genetic algorithm is smaller than that obtained with the influence coefficient method.

유전 알고리즘을 이용한 강성회전체의 평형잡이 (Balancing of a Rigid Rotor using Genetic Algorithms)

  • 양보석;주호진
    • Journal of Advanced Marine Engineering and Technology
    • /
    • 제20권2호
    • /
    • pp.40-47
    • /
    • 1996
  • This paper describes a new approach to solve balancing of a rigid rotor. In this paper, the balancing of the rigid rotor using genetic algorithms, which are search algorithms based on the mechanics of natural selection and natural genetics is proposed. Under the assumption that the initial vibration values used to calculate correction masses contain errors, the influence coefficient method, the least squares method and a genetic algorithm are compared. The results show that the vibration amplitude obtained with the least squares method and the genetic algorithm is smaller than that obtained with the influence coefficient method.

  • PDF

Agronomic performance of 20 soybean recommended varieties in Korea

  • Kim, Yong-Ho
    • Plant Resources
    • /
    • 제3권3호
    • /
    • pp.206-210
    • /
    • 2000
  • A total of 20 soybean recommended varieties which were developed until late 1980's in Korea was evaluated at Suwon. Comprehensive evaluation and correlation analysis were conducted on the agronomic characters. Great variations were found in these genotypes for branch number, pod number, and grain yield per plant. The variation in number of pods/plant ranged from 53 to 164, and in grain yield from 25.9 to 68.8 g. The coefficient of variation for most of the characters had a wide range. In correlation coefficient, grain yield per plant showed a positive phenotypic association with weight of pods, pod number of branches, and weight of stem. Multiple regression analysis was done to formulate selection criteria. It indicated that stout and medium-stature genotypes with more branches, resulting in varieties with more pods per plant but with medium-size seeds are available to obtain high-yielding varieties.

  • PDF

텍스트 마이닝 기법을 이용한 연관용어 선정에 관한 실험적 연구 (An Experimental Study on Selecting Association Terms Using Text Mining Techniques)

  • 김수연;정영미
    • 정보관리학회지
    • /
    • 제23권3호
    • /
    • pp.147-165
    • /
    • 2006
  • 이 연구에서는 전체 문헌집단으로부터 초기 질의어에 대한 연관용어 선정 시 사용할 수 있는 최적의 기법을 찾기 위해 연관규칙 마이닝과 용어 클러스터링 기법을 이용하여 연관용어 선정 실험을 수행하였다. 연관규칙 마이닝 기법에서는 Apriori 알고리즘을 사용하였으며, 용어 클러스터링 기법에서는 연관성 척도로 GSS 계수, 자카드계수, 코사인계수, 소칼 & 스니스 5, 상호정보량을사용하였다. 성능평가 척도로는 연관용어 정확률과 연관용어 일치율을 사용하였으며, 실험결과 Apriori 알고리즘과 GSS 계수가 가장 좋은 성능을 나타냈다.

Investigations of H-Darrieus rotors for different blade parameters at low wind speeds

  • Sengupta, Anal R.;Biswas, Agnimitra;Gupta, Rajat
    • Wind and Structures
    • /
    • 제25권6호
    • /
    • pp.551-567
    • /
    • 2017
  • Studies of unsymmetrical blade H-Darrieus rotors at low wind speeds in terms of starting time, static torque, and power performances for different blade parameters: thickness-to-chord (t/c), camber position, and solidity are scarce. However these are required for knowing insights of rotor performances to obtain some design guidelines for the selection of these rotors. Here, an attempt is made to quantify the effects of these blade parameters on the performances of three different H-Darrieus rotors at various low wind streams. Different blade profiles, namely S815, EN0005 (both unsymmetrical), and NACA 0018 (symmetrical blade for comparison) are considered. The rotors are investigated rigorously in a centrifugal blower apparatus. Firstly the dynamic and static performances of the rotors are evaluated to determine the best performing rotor and their optimum solidity. Generalised performance equations are developed based on selected blade parameters which are validated for the unsymmetrical rotors. Further, the starting time is quantified with respect to the rotor inertia to determine the suitable range of inertia that helps the unsymmetrical blade rotor to self-start earlier than the symmetrical one. This study can work as a benchmark for the selection of optimum blade parameters while designing an unsymmetrical blade rotor at low wind speeds.

지게차용 엔진식 드라이브 액슬 수명평가를 위한 가속수명시험 선정 연구 (Accelerated Life Test Selection Study for Life Evaluation of Engine Type Drive Axle for Forklift)

  • 김준영;유영준;이철희
    • 드라이브 ㆍ 컨트롤
    • /
    • 제20권3호
    • /
    • pp.9-14
    • /
    • 2023
  • In this paper, the selection of a reliable accelerated life test code for a 2-ton forklift was accomplished by choosing the driving resistance coefficient failure-free test time based on a 10,000-hour B10 life. The overall life and average equivalent load of the vehicle were then calculated based on actual driving test conditions using the selected driving resistance coefficient. The gear train's accelerated life test code was selected by adjusting the equivalent load to a torque and rotation speed that did not exceed 125%(about 75HP) of the vehicle rated power. The safety of the test standards was validated by conducting an actual accelerated life test utilizing the proposed test method in this study and comparing the test result with the corresponding theoretical value. It is anticipated that the reliability of the accelerated life test in this paper will be enhanced, by incorporating actual driving performance data collected directly from the forklift and adjusting the conditions used in developing the accelerated life test code.

상호정보량 기법을 적용한 인공신경망 입력자료의 선정 (Input Variables Selection of Artificial Neural Network Using Mutual Information)

  • 한광희;류용준;김태순;허준행
    • 한국수자원학회논문집
    • /
    • 제43권1호
    • /
    • pp.81-94
    • /
    • 2010
  • 본 연구는 인공신경망의 성능을 향상시키기 위한 여러 가지 방법들 중의 하나인 입력변수 선정기법에 관한 연구로서, 일반적으로 널리 사용되고 있는 상관계수를 이용한 입력변수 선정기법 외에 상호정보량을 활용한 방법을 적용하여 인공신경망의 성능을 향상시키고자 하였다. 대상자료는 기상청에서 제공하는 RDAPS자료의 152개 출력값으로 지상강우량의 예측값인 APCP를 포함하고 있으며, 강우관측값간의 상호정보량을 구해 가장 영향력이 큰 변수를 입력변수로 사용하였다. 기존연구결과, 그리고 상관계수만을 이용해서 입력변수를 선정한 결과와 비교해볼 때, 상호정보량을 적용한 경우 입력변수는 주로 바람과 관련된 변수들이 선정되었으며, 평균제곱근오차, 평균제곱근상대오차, 그룹별로 구분한 경우의 절대오차, 그리고 구간별로 구분한 경우의 상대오차를 비교한 경과 상호정보량을 이용한 입력변수 선정방법의 정확도가 전반적으로 높은 것으로 나타났으며, 특히 강우량이 상대적으로 큰 경우의 오차를 많이 감소시킬 수 있는 것으로 나타났다.

유전자 알고리즘과 Feature Wrapping을 통한 마이크로어레이 데이타 중복 특징 소거법 (Removing Non-informative Features by Robust Feature Wrapping Method for Microarray Gene Expression Data)

  • 이재성;김대원
    • 한국정보과학회논문지:소프트웨어및응용
    • /
    • 제35권8호
    • /
    • pp.463-478
    • /
    • 2008
  • 본 논문에서는 유전자 사이의 상관계수가 높은 마이크로어레이 데이타에 대하여 제안하는 알고리즘을 통해 상관계수가 낮은 유전자들의 부집합을 만들고, 이에 대해 적합 함수를 통한 평가로 기존 방법론이 가지는 한계를 극복할 수 있도록 하였다. 기존 방법론은 개별 특징의 평가를 통해 중복 특징을 제거하며, 상관계수에 대한 고려가 없어 선택된 유전자 부집합들의 상관계수가 논은 문제가 있었다. 이에 따라 제안하는 알고리즘은 특징간의 관계를 평가하는 Feature Wrapping 기법을 활용하여, 추출된 유전자 부집합에 포함된 유전자 사이의 상관관계가 낮고, 클래스 구분력이 높은 특징을 갖도록 하였다.