• Title/Summary/Keyword: discriminant analysi

Search Result 13, Processing Time 0.016 seconds

Application of Hybrid Conjoint Analysis to Improve Competitive Power of Theme Parks in Seoul and Its Suburbs (주제공원의 경쟁력 제고 방안에 관한 연구: Hybrid Conjoint Analysis의 적용)

  • 홍성권
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.23 no.2
    • /
    • pp.1-16
    • /
    • 1995
  • This study was carried out to suggest method which can be used to improve competitive power of theme parks. The characteristics of Hybrid Conjoint Analysis were described and its usefulness for identification of specific types of service theme parks have to provide was tested "Lotte World, " "Seoul land," and "farmland" were selected as study areas, and .7 attributes with 3 levels were utilized for analyses. Master design with 81 profiles was constructed to meet the requirement of ′Compromise Plan 1,′and data was collected by in-personal interviews on the study areas. Respondents were grouped by cluster analysis, and their characteristics were analyzed by discriminant analysis. Then, part-worth of each attribute . was estimated by stagewise estimation model Calibrated model of each group did not show part-worths of attributes clearly because both main effects and 2-way interaction effects were included in the models. Therefore, calibrated models′ coefficients were used to calculate utilities of all possible combinations of attributes levels. The results showed that managers of theme parks have several options for providing a new service: the combination of attribute levels with the highest utility is they however, they can choose the other combinations with next highest utlities is they can not afford it. Several suggestions were described to cope with the problems when Hybrid Conjoint Analysis is applied to landscape architectural study.

  • PDF

Speciation of the Two Species of the Genus Hyla (Anura) in Korea (한국산 청개구리속 2조의 종분화에 관한 연구)

  • 양서영;박병상
    • The Korean Journal of Zoology
    • /
    • v.31 no.1
    • /
    • pp.11-20
    • /
    • 1988
  • A comparison between two species of Hyla japonica and H. suweonesis in Korea was carried out to clarify their morphological, genetic and ecological differences, to estimate presumed divergent time between them, and to elucidate their probable process and mechanism of speciation. The results are as follows; 1.The breeding season of H. japonica was earlier than that of H. suweonensis about one and half months. 2.H.japonica was distributed all over the country, while H. suweonensis was restricted in Kyonggi plains. 3.On the extemal morphometric characters, differences were hardiy seen between two species. But on the discriminant function analysis, there was apparent differences between them. 4.Genic variation based on 24 loci showed that H. japonica populations were about two fold more variable than that of H. suweonensis populations. 5.Genetic relatedness between two species was rather remote (S =0.520, D=0.634) 6.Their presumed divergent time was estimated to be about three and a quarter mfllon years. It is presumed that H. suweonensis was originated from H. japonica during the period of late pleocene and early pleistocene. 7.Premating isolating mechanisrns (breeding season, mating call, and microhabitat segregation) may be operating to prevent gene ifow between them.

  • PDF

EEG Analysis Following Change in Hand Grip Force Level for BCI Based Robot Arm Force Control (BCI 기반 로봇 손 제어를 위한 악력 변화에 따른 EEG 분석)

  • Kim, Dong-Eun;Lee, Tae-Ju;Park, Seung-Min;Ko, Kwang-Eun;Sim, Kwee-Bo
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.23 no.2
    • /
    • pp.172-177
    • /
    • 2013
  • With Brain Computer Interface (BCI) system, a person with disabled limb could use this direct brain signal like electroencephalography (EEG) to control a device such as the artifact arm. The precise force control for the artifact arm is necessary for this artificial limb system. To understand the relationship between control EEG signal and the gripping force of hands, We proposed a study by measuring EEG changes of three grades (25%, 50%, 75%) of hand grip MVC (Maximal Voluntary Contract). The acquired EEG signal was filtered to obtain power of three wave bands (alpha, beta, gamma) by using fast fourier transformation (FFT) and computed power spectrum. Then the power spectrum of three bands (alpha, beta and gamma) of three classes (MVC 25%, 50%, 75%) was classified by using PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis). The result showed that the power spectrum of EEG is increased at MVC 75% more than MVC 25%, and the correct classification rate was 52.03% for left hand and 77.7% for right hand.