ActiRecognizer

Design and Implementation of a Real-Time Human Activity Recognition System

Liang Cao, Yufeng Wang, Qun Jin, Jianhua Ma

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

    Abstract

    In our society, inadequate physical activity is one of severe problems issues for human health, which may increase the health risks of many diseases. Nowadays, smartphones are ubiquitous and widely used around the world, in which multi-functional sensors and wireless interfaces are embedded. Therefore, smartphone is viewed as an appropriate platform for real-time activity recognition to address these healthy problems by monitoring and detecting user's everyday activities. In this paper, unlike other wearable devices based applications (e.g., watches, bands, or clip-on devices), ActiRecognizer, a smartphone-based prototype of a real-time human activity recognition (HAR) is designed and implemented, in which a detailed activity report of individuals (i.e. a pie chart containing the proportion and duration of each activity) can be correspondingly generated based on the detected real-time activities. Specifically, ActiRecognizer adopts client/server (C/S) architecture. At client side, smartphone associated with each individual periodically uploads the accelerometer and gyroscope sensing data to server for activity recognition and monitoring. At serve side, HAR is composed of offline training phase and online activity recognition phase: In training phase, sensing data are collected to extract the desired features that can appropriately characterize behaviors, classification model is generated utilizing these features, and then the trained classification model is used to classify user activity in real time. Finally, detailed activity reports and statistics are available to the user via a secure web interface.

    Original languageEnglish
    Title of host publicationProceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages266-271
    Number of pages6
    Volume2018-January
    ISBN (Electronic)9781538622094
    DOIs
    Publication statusPublished - 2018 Jan 8
    Event9th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017 - Nanjing, China
    Duration: 2017 Oct 122017 Oct 14

    Other

    Other9th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017
    CountryChina
    CityNanjing
    Period17/10/1217/10/14

    Fingerprint

    Smartphones
    Servers
    Monitoring
    Health risks
    Watches
    Gyroscopes
    Accelerometers
    Health
    Statistics
    Sensors

    Keywords

    • Activity recognition
    • data mining
    • machine learning
    • smartphone

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Networks and Communications
    • Hardware and Architecture
    • Software

    Cite this

    Cao, L., Wang, Y., Jin, Q., & Ma, J. (2018). ActiRecognizer: Design and Implementation of a Real-Time Human Activity Recognition System. In Proceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017 (Vol. 2018-January, pp. 266-271). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CyberC.2017.71

    ActiRecognizer : Design and Implementation of a Real-Time Human Activity Recognition System. / Cao, Liang; Wang, Yufeng; Jin, Qun; Ma, Jianhua.

    Proceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 266-271.

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

    Cao, L, Wang, Y, Jin, Q & Ma, J 2018, ActiRecognizer: Design and Implementation of a Real-Time Human Activity Recognition System. in Proceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 266-271, 9th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017, Nanjing, China, 17/10/12. https://doi.org/10.1109/CyberC.2017.71
    Cao L, Wang Y, Jin Q, Ma J. ActiRecognizer: Design and Implementation of a Real-Time Human Activity Recognition System. In Proceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 266-271 https://doi.org/10.1109/CyberC.2017.71
    Cao, Liang ; Wang, Yufeng ; Jin, Qun ; Ma, Jianhua. / ActiRecognizer : Design and Implementation of a Real-Time Human Activity Recognition System. Proceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 266-271
    @inproceedings{f3328b713e7b4119985c0434d74c19bb,
    title = "ActiRecognizer: Design and Implementation of a Real-Time Human Activity Recognition System",
    abstract = "In our society, inadequate physical activity is one of severe problems issues for human health, which may increase the health risks of many diseases. Nowadays, smartphones are ubiquitous and widely used around the world, in which multi-functional sensors and wireless interfaces are embedded. Therefore, smartphone is viewed as an appropriate platform for real-time activity recognition to address these healthy problems by monitoring and detecting user's everyday activities. In this paper, unlike other wearable devices based applications (e.g., watches, bands, or clip-on devices), ActiRecognizer, a smartphone-based prototype of a real-time human activity recognition (HAR) is designed and implemented, in which a detailed activity report of individuals (i.e. a pie chart containing the proportion and duration of each activity) can be correspondingly generated based on the detected real-time activities. Specifically, ActiRecognizer adopts client/server (C/S) architecture. At client side, smartphone associated with each individual periodically uploads the accelerometer and gyroscope sensing data to server for activity recognition and monitoring. At serve side, HAR is composed of offline training phase and online activity recognition phase: In training phase, sensing data are collected to extract the desired features that can appropriately characterize behaviors, classification model is generated utilizing these features, and then the trained classification model is used to classify user activity in real time. Finally, detailed activity reports and statistics are available to the user via a secure web interface.",
    keywords = "Activity recognition, data mining, machine learning, smartphone",
    author = "Liang Cao and Yufeng Wang and Qun Jin and Jianhua Ma",
    year = "2018",
    month = "1",
    day = "8",
    doi = "10.1109/CyberC.2017.71",
    language = "English",
    volume = "2018-January",
    pages = "266--271",
    booktitle = "Proceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - ActiRecognizer

    T2 - Design and Implementation of a Real-Time Human Activity Recognition System

    AU - Cao, Liang

    AU - Wang, Yufeng

    AU - Jin, Qun

    AU - Ma, Jianhua

    PY - 2018/1/8

    Y1 - 2018/1/8

    N2 - In our society, inadequate physical activity is one of severe problems issues for human health, which may increase the health risks of many diseases. Nowadays, smartphones are ubiquitous and widely used around the world, in which multi-functional sensors and wireless interfaces are embedded. Therefore, smartphone is viewed as an appropriate platform for real-time activity recognition to address these healthy problems by monitoring and detecting user's everyday activities. In this paper, unlike other wearable devices based applications (e.g., watches, bands, or clip-on devices), ActiRecognizer, a smartphone-based prototype of a real-time human activity recognition (HAR) is designed and implemented, in which a detailed activity report of individuals (i.e. a pie chart containing the proportion and duration of each activity) can be correspondingly generated based on the detected real-time activities. Specifically, ActiRecognizer adopts client/server (C/S) architecture. At client side, smartphone associated with each individual periodically uploads the accelerometer and gyroscope sensing data to server for activity recognition and monitoring. At serve side, HAR is composed of offline training phase and online activity recognition phase: In training phase, sensing data are collected to extract the desired features that can appropriately characterize behaviors, classification model is generated utilizing these features, and then the trained classification model is used to classify user activity in real time. Finally, detailed activity reports and statistics are available to the user via a secure web interface.

    AB - In our society, inadequate physical activity is one of severe problems issues for human health, which may increase the health risks of many diseases. Nowadays, smartphones are ubiquitous and widely used around the world, in which multi-functional sensors and wireless interfaces are embedded. Therefore, smartphone is viewed as an appropriate platform for real-time activity recognition to address these healthy problems by monitoring and detecting user's everyday activities. In this paper, unlike other wearable devices based applications (e.g., watches, bands, or clip-on devices), ActiRecognizer, a smartphone-based prototype of a real-time human activity recognition (HAR) is designed and implemented, in which a detailed activity report of individuals (i.e. a pie chart containing the proportion and duration of each activity) can be correspondingly generated based on the detected real-time activities. Specifically, ActiRecognizer adopts client/server (C/S) architecture. At client side, smartphone associated with each individual periodically uploads the accelerometer and gyroscope sensing data to server for activity recognition and monitoring. At serve side, HAR is composed of offline training phase and online activity recognition phase: In training phase, sensing data are collected to extract the desired features that can appropriately characterize behaviors, classification model is generated utilizing these features, and then the trained classification model is used to classify user activity in real time. Finally, detailed activity reports and statistics are available to the user via a secure web interface.

    KW - Activity recognition

    KW - data mining

    KW - machine learning

    KW - smartphone

    UR - http://www.scopus.com/inward/record.url?scp=85050074779&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85050074779&partnerID=8YFLogxK

    U2 - 10.1109/CyberC.2017.71

    DO - 10.1109/CyberC.2017.71

    M3 - Conference contribution

    VL - 2018-January

    SP - 266

    EP - 271

    BT - Proceedings - 2017 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2017

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -