Edge mining the internet of things

Elena Gaura, James Brusey, Michael Allen, Ross Wilkins, Daniel Goldsmith, Ramona Rednic

    Research output: Contribution to journalArticle

    50 Citations (Scopus)
    33 Downloads (Pure)

    Abstract

    This paper examines the benefits of edge mining – data mining that takes place on the wireless, battery-powered smart sensing devices that sit at the edge points of the Internet of Things. Through local data reduction and transformation, edge mining can quantifiably reduce the number of packets that must be sent, reducing energy usage and remote storage requirements. Additionally, edge mining has the potential to reduce the risk to personal privacy through embedding of information requirements at the sensing point, limiting inappropriate use. The benefits of edge mining are examined with respect to three specific algorithms: Linear Spanish Inquisition Protocol (L-SIP), ClassAct, and Bare Necessities (BN), which are all instantiations of the General SIP (G-SIP). In general, the benefits provided by edge mining are related to the predictability of data streams and availability of precise information requirements; results show that L-SIP typically reduces packet transmission by around 95% (20-fold), BN reduces packet transmission by 99.98% (5000-fold) and ClassAct reduces packet transmission by 99.6% (250-fold). Although energy reduction is not as radical due to other overheads, minimisation of these overheads can lead to up to a 10-fold battery life extension for L-SIP, for example. These results demonstrate the importance of edge mining to the feasibility of many IoT applications.
    Original languageEnglish
    Pages (from-to)3816-3825
    JournalIEEE Sensors
    Volume13
    Issue number10
    DOIs
    Publication statusPublished - 2013

    Fingerprint

    packet transmission
    Network protocols
    Data mining
    Data reduction
    requirements
    electric batteries
    Availability
    privacy
    data mining
    data reduction
    Internet of things
    embedding
    availability
    optimization
    energy

    Bibliographical note

    © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

    Keywords

    • edge mining
    • data mining
    • Internet of Things

    Cite this

    Edge mining the internet of things. / Gaura, Elena; Brusey, James; Allen, Michael; Wilkins, Ross; Goldsmith, Daniel; Rednic, Ramona.

    In: IEEE Sensors, Vol. 13, No. 10, 2013, p. 3816-3825.

    Research output: Contribution to journalArticle

    Gaura, Elena ; Brusey, James ; Allen, Michael ; Wilkins, Ross ; Goldsmith, Daniel ; Rednic, Ramona. / Edge mining the internet of things. In: IEEE Sensors. 2013 ; Vol. 13, No. 10. pp. 3816-3825.
    @article{e57f17c3b8ed4c0e87339b3b8a6583c0,
    title = "Edge mining the internet of things",
    abstract = "This paper examines the benefits of edge mining – data mining that takes place on the wireless, battery-powered smart sensing devices that sit at the edge points of the Internet of Things. Through local data reduction and transformation, edge mining can quantifiably reduce the number of packets that must be sent, reducing energy usage and remote storage requirements. Additionally, edge mining has the potential to reduce the risk to personal privacy through embedding of information requirements at the sensing point, limiting inappropriate use. The benefits of edge mining are examined with respect to three specific algorithms: Linear Spanish Inquisition Protocol (L-SIP), ClassAct, and Bare Necessities (BN), which are all instantiations of the General SIP (G-SIP). In general, the benefits provided by edge mining are related to the predictability of data streams and availability of precise information requirements; results show that L-SIP typically reduces packet transmission by around 95{\%} (20-fold), BN reduces packet transmission by 99.98{\%} (5000-fold) and ClassAct reduces packet transmission by 99.6{\%} (250-fold). Although energy reduction is not as radical due to other overheads, minimisation of these overheads can lead to up to a 10-fold battery life extension for L-SIP, for example. These results demonstrate the importance of edge mining to the feasibility of many IoT applications.",
    keywords = "edge mining, data mining, Internet of Things",
    author = "Elena Gaura and James Brusey and Michael Allen and Ross Wilkins and Daniel Goldsmith and Ramona Rednic",
    note = "{\circledC} 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
    year = "2013",
    doi = "10.1109/JSEN.2013.2266895",
    language = "English",
    volume = "13",
    pages = "3816--3825",
    journal = "IEEE Sensors Journal",
    issn = "1530-437X",
    publisher = "Institute of Electrical and Electronics Engineers",
    number = "10",

    }

    TY - JOUR

    T1 - Edge mining the internet of things

    AU - Gaura, Elena

    AU - Brusey, James

    AU - Allen, Michael

    AU - Wilkins, Ross

    AU - Goldsmith, Daniel

    AU - Rednic, Ramona

    N1 - © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

    PY - 2013

    Y1 - 2013

    N2 - This paper examines the benefits of edge mining – data mining that takes place on the wireless, battery-powered smart sensing devices that sit at the edge points of the Internet of Things. Through local data reduction and transformation, edge mining can quantifiably reduce the number of packets that must be sent, reducing energy usage and remote storage requirements. Additionally, edge mining has the potential to reduce the risk to personal privacy through embedding of information requirements at the sensing point, limiting inappropriate use. The benefits of edge mining are examined with respect to three specific algorithms: Linear Spanish Inquisition Protocol (L-SIP), ClassAct, and Bare Necessities (BN), which are all instantiations of the General SIP (G-SIP). In general, the benefits provided by edge mining are related to the predictability of data streams and availability of precise information requirements; results show that L-SIP typically reduces packet transmission by around 95% (20-fold), BN reduces packet transmission by 99.98% (5000-fold) and ClassAct reduces packet transmission by 99.6% (250-fold). Although energy reduction is not as radical due to other overheads, minimisation of these overheads can lead to up to a 10-fold battery life extension for L-SIP, for example. These results demonstrate the importance of edge mining to the feasibility of many IoT applications.

    AB - This paper examines the benefits of edge mining – data mining that takes place on the wireless, battery-powered smart sensing devices that sit at the edge points of the Internet of Things. Through local data reduction and transformation, edge mining can quantifiably reduce the number of packets that must be sent, reducing energy usage and remote storage requirements. Additionally, edge mining has the potential to reduce the risk to personal privacy through embedding of information requirements at the sensing point, limiting inappropriate use. The benefits of edge mining are examined with respect to three specific algorithms: Linear Spanish Inquisition Protocol (L-SIP), ClassAct, and Bare Necessities (BN), which are all instantiations of the General SIP (G-SIP). In general, the benefits provided by edge mining are related to the predictability of data streams and availability of precise information requirements; results show that L-SIP typically reduces packet transmission by around 95% (20-fold), BN reduces packet transmission by 99.98% (5000-fold) and ClassAct reduces packet transmission by 99.6% (250-fold). Although energy reduction is not as radical due to other overheads, minimisation of these overheads can lead to up to a 10-fold battery life extension for L-SIP, for example. These results demonstrate the importance of edge mining to the feasibility of many IoT applications.

    KW - edge mining

    KW - data mining

    KW - Internet of Things

    U2 - 10.1109/JSEN.2013.2266895

    DO - 10.1109/JSEN.2013.2266895

    M3 - Article

    VL - 13

    SP - 3816

    EP - 3825

    JO - IEEE Sensors Journal

    JF - IEEE Sensors Journal

    SN - 1530-437X

    IS - 10

    ER -