Fusion of Smartphone Motion Sensors for Physical Activity Recognition

M. Shoaib, S. Bosch, O. Durmaz, Johan Scholten, Paul J.M. Havinga

    Research output: Contribution to journalArticleAcademicpeer-review

    181 Citations (Scopus)
    51 Downloads (Pure)

    Abstract

    For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.
    Original languageUndefined
    Pages (from-to)10146-10176
    Number of pages31
    JournalSensors (Switserland)
    Volume14
    Issue number6
    DOIs
    Publication statusPublished - 10 Jun 2014

    Keywords

    • EWI-24775
    • Sensor fusion
    • assisted living
    • smartphone sensors
    • well-being applications
    • IR-91463
    • Activity Recognition
    • Magnetometer
    • Gyroscope
    • Health Monitoring
    • METIS-305896
    • Accelerometer

    Cite this

    @article{b296958b66c0443f9e2dd44638c7cb59,
    title = "Fusion of Smartphone Motion Sensors for Physical Activity Recognition",
    abstract = "For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.",
    keywords = "EWI-24775, Sensor fusion, assisted living, smartphone sensors, well-being applications, IR-91463, Activity Recognition, Magnetometer, Gyroscope, Health Monitoring, METIS-305896, Accelerometer",
    author = "M. Shoaib and S. Bosch and O. Durmaz and Johan Scholten and Havinga, {Paul J.M.}",
    note = "eemcs-eprint-24775",
    year = "2014",
    month = "6",
    day = "10",
    doi = "10.3390/s140610146",
    language = "Undefined",
    volume = "14",
    pages = "10146--10176",
    journal = "Sensors (Switserland)",
    issn = "1424-8220",
    publisher = "Multidisciplinary Digital Publishing Institute",
    number = "6",

    }

    Fusion of Smartphone Motion Sensors for Physical Activity Recognition. / Shoaib, M.; Bosch, S.; Durmaz, O.; Scholten, Johan; Havinga, Paul J.M.

    In: Sensors (Switserland), Vol. 14, No. 6, 10.06.2014, p. 10146-10176.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Fusion of Smartphone Motion Sensors for Physical Activity Recognition

    AU - Shoaib, M.

    AU - Bosch, S.

    AU - Durmaz, O.

    AU - Scholten, Johan

    AU - Havinga, Paul J.M.

    N1 - eemcs-eprint-24775

    PY - 2014/6/10

    Y1 - 2014/6/10

    N2 - For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.

    AB - For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.

    KW - EWI-24775

    KW - Sensor fusion

    KW - assisted living

    KW - smartphone sensors

    KW - well-being applications

    KW - IR-91463

    KW - Activity Recognition

    KW - Magnetometer

    KW - Gyroscope

    KW - Health Monitoring

    KW - METIS-305896

    KW - Accelerometer

    U2 - 10.3390/s140610146

    DO - 10.3390/s140610146

    M3 - Article

    VL - 14

    SP - 10146

    EP - 10176

    JO - Sensors (Switserland)

    JF - Sensors (Switserland)

    SN - 1424-8220

    IS - 6

    ER -