Estimation of diffusive states from single-particle trajectory in heterogeneous medium using machine-learning methods

yu Matsuda, Itsuo Hanasaki, Ryo Iwao, Hiroki Yamaguchi, Tomohide Niimi

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    We propose a novel approach to analyze random walks in heterogeneous medium using a hybrid machine-learning method based on a gamma mixture and a hidden Markov model. A gamma mixture and a hidden Markov model respectively provide the number and the most probable sequence of diffusive states from the time series position data of particles/molecules obtained by single-particle/molecule tracking (SPT/SMT) method. We evaluate the performance of our proposed method for numerically generated trajectories. It is shown that our proposed method can correctly extract the number of diffusive states when each trajectory is long enough to be frame averaged. We also indicate that our method can provide an indicator whether the assumption of a medium consisting of discrete diffusive states is appropriate or not based on the available amount of trajectory data. Then, we demonstrate an application of our method to the analysis of experimentally obtained SPT data.

    Original languageEnglish
    Pages (from-to)24099-24108
    Number of pages10
    JournalPhysical Chemistry Chemical Physics
    Volume20
    Issue number37
    DOIs
    Publication statusPublished - 2018 Jan 1

    Fingerprint

    machine learning
    particle trajectories
    Learning systems
    Trajectories
    trajectories
    Hidden Markov models
    Molecules
    Surface mount technology
    random walk
    molecules
    Time series

    ASJC Scopus subject areas

    • Physics and Astronomy(all)
    • Physical and Theoretical Chemistry

    Cite this

    Estimation of diffusive states from single-particle trajectory in heterogeneous medium using machine-learning methods. / Matsuda, yu; Hanasaki, Itsuo; Iwao, Ryo; Yamaguchi, Hiroki; Niimi, Tomohide.

    In: Physical Chemistry Chemical Physics, Vol. 20, No. 37, 01.01.2018, p. 24099-24108.

    Research output: Contribution to journalArticle

    Matsuda, yu ; Hanasaki, Itsuo ; Iwao, Ryo ; Yamaguchi, Hiroki ; Niimi, Tomohide. / Estimation of diffusive states from single-particle trajectory in heterogeneous medium using machine-learning methods. In: Physical Chemistry Chemical Physics. 2018 ; Vol. 20, No. 37. pp. 24099-24108.
    @article{5c29eb1e38494a2f9c84fef57fd540be,
    title = "Estimation of diffusive states from single-particle trajectory in heterogeneous medium using machine-learning methods",
    abstract = "We propose a novel approach to analyze random walks in heterogeneous medium using a hybrid machine-learning method based on a gamma mixture and a hidden Markov model. A gamma mixture and a hidden Markov model respectively provide the number and the most probable sequence of diffusive states from the time series position data of particles/molecules obtained by single-particle/molecule tracking (SPT/SMT) method. We evaluate the performance of our proposed method for numerically generated trajectories. It is shown that our proposed method can correctly extract the number of diffusive states when each trajectory is long enough to be frame averaged. We also indicate that our method can provide an indicator whether the assumption of a medium consisting of discrete diffusive states is appropriate or not based on the available amount of trajectory data. Then, we demonstrate an application of our method to the analysis of experimentally obtained SPT data.",
    author = "yu Matsuda and Itsuo Hanasaki and Ryo Iwao and Hiroki Yamaguchi and Tomohide Niimi",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.1039/C8CP02566E",
    language = "English",
    volume = "20",
    pages = "24099--24108",
    journal = "Physical Chemistry Chemical Physics",
    issn = "1463-9076",
    publisher = "Royal Society of Chemistry",
    number = "37",

    }

    TY - JOUR

    T1 - Estimation of diffusive states from single-particle trajectory in heterogeneous medium using machine-learning methods

    AU - Matsuda, yu

    AU - Hanasaki, Itsuo

    AU - Iwao, Ryo

    AU - Yamaguchi, Hiroki

    AU - Niimi, Tomohide

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - We propose a novel approach to analyze random walks in heterogeneous medium using a hybrid machine-learning method based on a gamma mixture and a hidden Markov model. A gamma mixture and a hidden Markov model respectively provide the number and the most probable sequence of diffusive states from the time series position data of particles/molecules obtained by single-particle/molecule tracking (SPT/SMT) method. We evaluate the performance of our proposed method for numerically generated trajectories. It is shown that our proposed method can correctly extract the number of diffusive states when each trajectory is long enough to be frame averaged. We also indicate that our method can provide an indicator whether the assumption of a medium consisting of discrete diffusive states is appropriate or not based on the available amount of trajectory data. Then, we demonstrate an application of our method to the analysis of experimentally obtained SPT data.

    AB - We propose a novel approach to analyze random walks in heterogeneous medium using a hybrid machine-learning method based on a gamma mixture and a hidden Markov model. A gamma mixture and a hidden Markov model respectively provide the number and the most probable sequence of diffusive states from the time series position data of particles/molecules obtained by single-particle/molecule tracking (SPT/SMT) method. We evaluate the performance of our proposed method for numerically generated trajectories. It is shown that our proposed method can correctly extract the number of diffusive states when each trajectory is long enough to be frame averaged. We also indicate that our method can provide an indicator whether the assumption of a medium consisting of discrete diffusive states is appropriate or not based on the available amount of trajectory data. Then, we demonstrate an application of our method to the analysis of experimentally obtained SPT data.

    UR - http://www.scopus.com/inward/record.url?scp=85054073113&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85054073113&partnerID=8YFLogxK

    U2 - 10.1039/C8CP02566E

    DO - 10.1039/C8CP02566E

    M3 - Article

    AN - SCOPUS:85054073113

    VL - 20

    SP - 24099

    EP - 24108

    JO - Physical Chemistry Chemical Physics

    JF - Physical Chemistry Chemical Physics

    SN - 1463-9076

    IS - 37

    ER -