• DocumentCode
    699022
  • Title

    Study of Eye Movement Behavior Pattern Diversity between Chinese Ethnic Groups

  • Author

    Duan Xiaodong ; Lu Bo ; Liu Peng ; Gao Chunhong

  • Author_Institution
    Dalian Key Lab. of Digital Technol. for Nat. Culture, Dalian Nat. Univ., Dalian, China
  • fYear
    2015
  • fDate
    13-14 Feb. 2015
  • Firstpage
    767
  • Lastpage
    770
  • Abstract
    China is a country of many different ethnic groups since genetic, geographical and culture formation of a different customs and ways of thinking. In order to study the eye movement behavior when the different ethnic groups observe things, firstly, we use Tobii eye tracker to record the representation data from the different ethnic groups which are used to solve Sudoku problem. Meanwhile, the data from different ethnic groups were compressed into 16 dimensional data and constructed the data sets. Secondly, we analysis the diversity of eye movement behavior data sets derive from Buyi, Mongolian, Korean, Dong and Han five ethnics respectively. Furthermore, a variety of machine learning methods are explored to analysis the eye movement behavior data sets. The experimental results show that eye movement behavior diversity between different ethnic groups.
  • Keywords
    cultural aspects; data analysis; learning (artificial intelligence); Buyi ethnics; Chinese ethnic groups; Dong ethnics; Han ethnics; Korean ethnics; Mongolian ethnics; Sudoku problem; Tobii eye tracker; culture formation; data sets; eye movement behavior pattern diversity; genetic formation; geographical formation; machine learning methods; Accuracy; Benchmark testing; Learning systems; Support vector machines; Tracking; Training; Tobii eye tracker; data mining; ethnic groups; eye movement behavior;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence & Communication Technology (CICT), 2015 IEEE International Conference on
  • Conference_Location
    Ghaziabad
  • Print_ISBN
    978-1-4799-6022-4
  • Type

    conf

  • DOI
    10.1109/CICT.2015.160
  • Filename
    7078806