Development of a cognition system for analyzing rat's behaviors

Qing Shi, Shunsyuke Miyagishima, Shogo Fumino, Shinichiro Konno, Hiroyuki Ishii, Atsuo Takanishi

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

    9 Citations (Scopus)

    Abstract

    The interaction experiment, between a robot and a rat, will benefit significantly when the rat's actions can be recognized automatically in real time. Regarding quantitative behavior analysis, the number and duration of a rat's actions should be measured efficiently and accurately. Therefore, aiming at the above-mentioned objectives, a novel cognition system capable of detecting rats' actions has been proposed in this paper. The main function of this cognition system lies on the real-time recognition and offline analysis of rats' behaviors. Basic image processing algorithm as Labeling and Contour Finding were employed to extract feature parameters (body length, body area, body radius, rotational angle, and ellipticity) of rat's actions. These parameters are integrated as the input feature vector of NN (Neural Network) and SVM (Support Vector Machine) training system respectively. Preliminary experiments reveal that the grooming, rotating and rearing actions could be recognized with extremely high rate (more than 90%) by both NN and SVM. Compared to NN, SVM provides better recognition rate and less computational cost.

    Original languageEnglish
    Title of host publication2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010
    Pages1399-1404
    Number of pages6
    DOIs
    Publication statusPublished - 2010
    Event2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010 - Tianjin
    Duration: 2010 Dec 142010 Dec 18

    Other

    Other2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010
    CityTianjin
    Period10/12/1410/12/18

    Fingerprint

    Cognition
    Rats
    Support vector machines
    Neural networks
    Grooming
    Labeling
    Image processing
    Experiments
    Robots
    Costs and Cost Analysis
    Support Vector Machine
    Costs
    Recognition (Psychology)

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Biotechnology
    • Human-Computer Interaction

    Cite this

    Shi, Q., Miyagishima, S., Fumino, S., Konno, S., Ishii, H., & Takanishi, A. (2010). Development of a cognition system for analyzing rat's behaviors. In 2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010 (pp. 1399-1404). [5723534] https://doi.org/10.1109/ROBIO.2010.5723534

    Development of a cognition system for analyzing rat's behaviors. / Shi, Qing; Miyagishima, Shunsyuke; Fumino, Shogo; Konno, Shinichiro; Ishii, Hiroyuki; Takanishi, Atsuo.

    2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010. 2010. p. 1399-1404 5723534.

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

    Shi, Q, Miyagishima, S, Fumino, S, Konno, S, Ishii, H & Takanishi, A 2010, Development of a cognition system for analyzing rat's behaviors. in 2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010., 5723534, pp. 1399-1404, 2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010, Tianjin, 10/12/14. https://doi.org/10.1109/ROBIO.2010.5723534
    Shi Q, Miyagishima S, Fumino S, Konno S, Ishii H, Takanishi A. Development of a cognition system for analyzing rat's behaviors. In 2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010. 2010. p. 1399-1404. 5723534 https://doi.org/10.1109/ROBIO.2010.5723534
    Shi, Qing ; Miyagishima, Shunsyuke ; Fumino, Shogo ; Konno, Shinichiro ; Ishii, Hiroyuki ; Takanishi, Atsuo. / Development of a cognition system for analyzing rat's behaviors. 2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010. 2010. pp. 1399-1404
    @inproceedings{e5e22148639840c689c0d9c5ad77d2f4,
    title = "Development of a cognition system for analyzing rat's behaviors",
    abstract = "The interaction experiment, between a robot and a rat, will benefit significantly when the rat's actions can be recognized automatically in real time. Regarding quantitative behavior analysis, the number and duration of a rat's actions should be measured efficiently and accurately. Therefore, aiming at the above-mentioned objectives, a novel cognition system capable of detecting rats' actions has been proposed in this paper. The main function of this cognition system lies on the real-time recognition and offline analysis of rats' behaviors. Basic image processing algorithm as Labeling and Contour Finding were employed to extract feature parameters (body length, body area, body radius, rotational angle, and ellipticity) of rat's actions. These parameters are integrated as the input feature vector of NN (Neural Network) and SVM (Support Vector Machine) training system respectively. Preliminary experiments reveal that the grooming, rotating and rearing actions could be recognized with extremely high rate (more than 90{\%}) by both NN and SVM. Compared to NN, SVM provides better recognition rate and less computational cost.",
    author = "Qing Shi and Shunsyuke Miyagishima and Shogo Fumino and Shinichiro Konno and Hiroyuki Ishii and Atsuo Takanishi",
    year = "2010",
    doi = "10.1109/ROBIO.2010.5723534",
    language = "English",
    isbn = "9781424493173",
    pages = "1399--1404",
    booktitle = "2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010",

    }

    TY - GEN

    T1 - Development of a cognition system for analyzing rat's behaviors

    AU - Shi, Qing

    AU - Miyagishima, Shunsyuke

    AU - Fumino, Shogo

    AU - Konno, Shinichiro

    AU - Ishii, Hiroyuki

    AU - Takanishi, Atsuo

    PY - 2010

    Y1 - 2010

    N2 - The interaction experiment, between a robot and a rat, will benefit significantly when the rat's actions can be recognized automatically in real time. Regarding quantitative behavior analysis, the number and duration of a rat's actions should be measured efficiently and accurately. Therefore, aiming at the above-mentioned objectives, a novel cognition system capable of detecting rats' actions has been proposed in this paper. The main function of this cognition system lies on the real-time recognition and offline analysis of rats' behaviors. Basic image processing algorithm as Labeling and Contour Finding were employed to extract feature parameters (body length, body area, body radius, rotational angle, and ellipticity) of rat's actions. These parameters are integrated as the input feature vector of NN (Neural Network) and SVM (Support Vector Machine) training system respectively. Preliminary experiments reveal that the grooming, rotating and rearing actions could be recognized with extremely high rate (more than 90%) by both NN and SVM. Compared to NN, SVM provides better recognition rate and less computational cost.

    AB - The interaction experiment, between a robot and a rat, will benefit significantly when the rat's actions can be recognized automatically in real time. Regarding quantitative behavior analysis, the number and duration of a rat's actions should be measured efficiently and accurately. Therefore, aiming at the above-mentioned objectives, a novel cognition system capable of detecting rats' actions has been proposed in this paper. The main function of this cognition system lies on the real-time recognition and offline analysis of rats' behaviors. Basic image processing algorithm as Labeling and Contour Finding were employed to extract feature parameters (body length, body area, body radius, rotational angle, and ellipticity) of rat's actions. These parameters are integrated as the input feature vector of NN (Neural Network) and SVM (Support Vector Machine) training system respectively. Preliminary experiments reveal that the grooming, rotating and rearing actions could be recognized with extremely high rate (more than 90%) by both NN and SVM. Compared to NN, SVM provides better recognition rate and less computational cost.

    UR - http://www.scopus.com/inward/record.url?scp=79952907982&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79952907982&partnerID=8YFLogxK

    U2 - 10.1109/ROBIO.2010.5723534

    DO - 10.1109/ROBIO.2010.5723534

    M3 - Conference contribution

    SN - 9781424493173

    SP - 1399

    EP - 1404

    BT - 2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010

    ER -