A virtual reality system for high-dimentional data visualization

S. Sanji, M. Murata, P. Hartono, S. Hashimoto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 Citations (Scopus)

    Abstract

    It is generally difficult to extract the essence or meaning of complexly distributed multivariate data. The essential information is distributed in the data space. Therefore, we have to perform both local and global analyses of the given data set. It is also possible that the data-space contains important information that is encoded locally. Such information will be difficult to extract without performing local data analysis. Effective data visualization is also very important to support intuitive understanding o f the meaning embedded in the data. In this paper we propose a virtual reality system for high-dimensional data visualization as a tool for intuitive data understanding. Our method is based on data clustering techniques and Principal Component Analysis (PCA), in which data can be recursively clustered to obtain arbitrary degree of locality and then analyzed using PCA. We have also developed a virtual reality system supported by stereo-glass and motion-capture that enables a user to " tour" the 4-dimensional data space. The ability of the proposed system to present data in 4-dimensional space in which each axis is the eigen vector generated by PCA, allows us to intuitively visualize multivariate data without losing too much information. Experiments using a number of real world data show the effectiveness of the proposed system for intuitive understanding of complex data.

    Original languageEnglish
    Title of host publicationProceedings - IEEE International Conference on Multimedia and Expo
    PublisherIEEE Computer Society
    Pages1049-1052
    Number of pages4
    ISBN (Print)0769511988
    DOIs
    Publication statusPublished - 2001
    Event2001 IEEE International Conference on Multimedia and Expo, ICME 2001 - Tokyo
    Duration: 2001 Aug 222001 Aug 25

    Other

    Other2001 IEEE International Conference on Multimedia and Expo, ICME 2001
    CityTokyo
    Period01/8/2201/8/25

    Fingerprint

    Data visualization
    Principal component analysis
    Virtual reality
    Glass
    Experiments

    ASJC Scopus subject areas

    • Computer Networks and Communications
    • Computer Science Applications

    Cite this

    Sanji, S., Murata, M., Hartono, P., & Hashimoto, S. (2001). A virtual reality system for high-dimentional data visualization. In Proceedings - IEEE International Conference on Multimedia and Expo (pp. 1049-1052). [1237905] IEEE Computer Society. https://doi.org/10.1109/ICME.2001.1237905

    A virtual reality system for high-dimentional data visualization. / Sanji, S.; Murata, M.; Hartono, P.; Hashimoto, S.

    Proceedings - IEEE International Conference on Multimedia and Expo. IEEE Computer Society, 2001. p. 1049-1052 1237905.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Sanji, S, Murata, M, Hartono, P & Hashimoto, S 2001, A virtual reality system for high-dimentional data visualization. in Proceedings - IEEE International Conference on Multimedia and Expo., 1237905, IEEE Computer Society, pp. 1049-1052, 2001 IEEE International Conference on Multimedia and Expo, ICME 2001, Tokyo, 01/8/22. https://doi.org/10.1109/ICME.2001.1237905
    Sanji S, Murata M, Hartono P, Hashimoto S. A virtual reality system for high-dimentional data visualization. In Proceedings - IEEE International Conference on Multimedia and Expo. IEEE Computer Society. 2001. p. 1049-1052. 1237905 https://doi.org/10.1109/ICME.2001.1237905
    Sanji, S. ; Murata, M. ; Hartono, P. ; Hashimoto, S. / A virtual reality system for high-dimentional data visualization. Proceedings - IEEE International Conference on Multimedia and Expo. IEEE Computer Society, 2001. pp. 1049-1052
    @inproceedings{9118a33eef7a48d3b21713d8a5b5b79c,
    title = "A virtual reality system for high-dimentional data visualization",
    abstract = "It is generally difficult to extract the essence or meaning of complexly distributed multivariate data. The essential information is distributed in the data space. Therefore, we have to perform both local and global analyses of the given data set. It is also possible that the data-space contains important information that is encoded locally. Such information will be difficult to extract without performing local data analysis. Effective data visualization is also very important to support intuitive understanding o f the meaning embedded in the data. In this paper we propose a virtual reality system for high-dimensional data visualization as a tool for intuitive data understanding. Our method is based on data clustering techniques and Principal Component Analysis (PCA), in which data can be recursively clustered to obtain arbitrary degree of locality and then analyzed using PCA. We have also developed a virtual reality system supported by stereo-glass and motion-capture that enables a user to {"} tour{"} the 4-dimensional data space. The ability of the proposed system to present data in 4-dimensional space in which each axis is the eigen vector generated by PCA, allows us to intuitively visualize multivariate data without losing too much information. Experiments using a number of real world data show the effectiveness of the proposed system for intuitive understanding of complex data.",
    author = "S. Sanji and M. Murata and P. Hartono and S. Hashimoto",
    year = "2001",
    doi = "10.1109/ICME.2001.1237905",
    language = "English",
    isbn = "0769511988",
    pages = "1049--1052",
    booktitle = "Proceedings - IEEE International Conference on Multimedia and Expo",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - A virtual reality system for high-dimentional data visualization

    AU - Sanji, S.

    AU - Murata, M.

    AU - Hartono, P.

    AU - Hashimoto, S.

    PY - 2001

    Y1 - 2001

    N2 - It is generally difficult to extract the essence or meaning of complexly distributed multivariate data. The essential information is distributed in the data space. Therefore, we have to perform both local and global analyses of the given data set. It is also possible that the data-space contains important information that is encoded locally. Such information will be difficult to extract without performing local data analysis. Effective data visualization is also very important to support intuitive understanding o f the meaning embedded in the data. In this paper we propose a virtual reality system for high-dimensional data visualization as a tool for intuitive data understanding. Our method is based on data clustering techniques and Principal Component Analysis (PCA), in which data can be recursively clustered to obtain arbitrary degree of locality and then analyzed using PCA. We have also developed a virtual reality system supported by stereo-glass and motion-capture that enables a user to " tour" the 4-dimensional data space. The ability of the proposed system to present data in 4-dimensional space in which each axis is the eigen vector generated by PCA, allows us to intuitively visualize multivariate data without losing too much information. Experiments using a number of real world data show the effectiveness of the proposed system for intuitive understanding of complex data.

    AB - It is generally difficult to extract the essence or meaning of complexly distributed multivariate data. The essential information is distributed in the data space. Therefore, we have to perform both local and global analyses of the given data set. It is also possible that the data-space contains important information that is encoded locally. Such information will be difficult to extract without performing local data analysis. Effective data visualization is also very important to support intuitive understanding o f the meaning embedded in the data. In this paper we propose a virtual reality system for high-dimensional data visualization as a tool for intuitive data understanding. Our method is based on data clustering techniques and Principal Component Analysis (PCA), in which data can be recursively clustered to obtain arbitrary degree of locality and then analyzed using PCA. We have also developed a virtual reality system supported by stereo-glass and motion-capture that enables a user to " tour" the 4-dimensional data space. The ability of the proposed system to present data in 4-dimensional space in which each axis is the eigen vector generated by PCA, allows us to intuitively visualize multivariate data without losing too much information. Experiments using a number of real world data show the effectiveness of the proposed system for intuitive understanding of complex data.

    UR - http://www.scopus.com/inward/record.url?scp=84908287489&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84908287489&partnerID=8YFLogxK

    U2 - 10.1109/ICME.2001.1237905

    DO - 10.1109/ICME.2001.1237905

    M3 - Conference contribution

    SN - 0769511988

    SP - 1049

    EP - 1052

    BT - Proceedings - IEEE International Conference on Multimedia and Expo

    PB - IEEE Computer Society

    ER -