GCHAR

An efficient Group-based Context-aware human activity recognition on smartphone

Liang Cao, Yufeng Wang, Bo Zhang, Qun Jin, Athanasios V. Vasilakos

    Research output: Contribution to journalArticle

    12 Citations (Scopus)

    Abstract

    With smartphones increasingly becoming ubiquitous and being equipped with various sensors, nowadays, there is a trend towards implementing HAR (Human Activity Recognition) algorithms and applications on smartphones, including health monitoring, self-managing system and fitness tracking. However, one of the main issues of the existing HAR schemes is that the classification accuracy is relatively low, and in order to improve the accuracy, high computation overhead is needed. In this paper, an efficient Group-based Context-aware classification method for human activity recognition on smartphones, GCHAR is proposed, which exploits hierarchical group-based scheme to improve the classification efficiency, and reduces the classification error through context awareness rather than the intensive computation. Specifically, GCHAR designs the two-level hierarchical classification structure, i.e., inter-group and inner-group, and utilizes the previous state and transition logic (so-called context awareness) to detect the transitions among activity groups. In comparison with other popular classifiers such as RandomTree, Bagging, J48, BayesNet, KNN and Decision Table, thorough experiments on the realistic dataset (UCI HAR repository) demonstrate that GCHAR achieves the best classification accuracy, reaching 94.1636%, and time consumption in training stage of GCHAR is four times shorter than the simple Decision Table and is decreased by 72.21% in classification stage in comparison with BayesNet.

    Original languageEnglish
    JournalJournal of Parallel and Distributed Computing
    DOIs
    Publication statusAccepted/In press - 2016 Dec 27

    Fingerprint

    Activity Recognition
    Smartphones
    Context-aware
    Decision Table
    Context-awareness
    Decision tables
    Hierarchical Classification
    Bagging
    Health Monitoring
    Recognition Algorithm
    Repository
    Fitness
    Human
    High Accuracy
    Classifier
    Logic
    Classifiers
    Sensor
    Health
    Monitoring

    Keywords

    • Context awareness
    • Hierarchical classifier
    • Human Activity Recognition (HAR)
    • Machine learning

    ASJC Scopus subject areas

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

    Cite this

    GCHAR : An efficient Group-based Context-aware human activity recognition on smartphone. / Cao, Liang; Wang, Yufeng; Zhang, Bo; Jin, Qun; Vasilakos, Athanasios V.

    In: Journal of Parallel and Distributed Computing, 27.12.2016.

    Research output: Contribution to journalArticle

    @article{436fe9d7d03040729d78bae3c8729e8e,
    title = "GCHAR: An efficient Group-based Context-aware human activity recognition on smartphone",
    abstract = "With smartphones increasingly becoming ubiquitous and being equipped with various sensors, nowadays, there is a trend towards implementing HAR (Human Activity Recognition) algorithms and applications on smartphones, including health monitoring, self-managing system and fitness tracking. However, one of the main issues of the existing HAR schemes is that the classification accuracy is relatively low, and in order to improve the accuracy, high computation overhead is needed. In this paper, an efficient Group-based Context-aware classification method for human activity recognition on smartphones, GCHAR is proposed, which exploits hierarchical group-based scheme to improve the classification efficiency, and reduces the classification error through context awareness rather than the intensive computation. Specifically, GCHAR designs the two-level hierarchical classification structure, i.e., inter-group and inner-group, and utilizes the previous state and transition logic (so-called context awareness) to detect the transitions among activity groups. In comparison with other popular classifiers such as RandomTree, Bagging, J48, BayesNet, KNN and Decision Table, thorough experiments on the realistic dataset (UCI HAR repository) demonstrate that GCHAR achieves the best classification accuracy, reaching 94.1636{\%}, and time consumption in training stage of GCHAR is four times shorter than the simple Decision Table and is decreased by 72.21{\%} in classification stage in comparison with BayesNet.",
    keywords = "Context awareness, Hierarchical classifier, Human Activity Recognition (HAR), Machine learning",
    author = "Liang Cao and Yufeng Wang and Bo Zhang and Qun Jin and Vasilakos, {Athanasios V.}",
    year = "2016",
    month = "12",
    day = "27",
    doi = "10.1016/j.jpdc.2017.05.007",
    language = "English",
    journal = "Journal of Parallel and Distributed Computing",
    issn = "0743-7315",
    publisher = "Academic Press Inc.",

    }

    TY - JOUR

    T1 - GCHAR

    T2 - An efficient Group-based Context-aware human activity recognition on smartphone

    AU - Cao, Liang

    AU - Wang, Yufeng

    AU - Zhang, Bo

    AU - Jin, Qun

    AU - Vasilakos, Athanasios V.

    PY - 2016/12/27

    Y1 - 2016/12/27

    N2 - With smartphones increasingly becoming ubiquitous and being equipped with various sensors, nowadays, there is a trend towards implementing HAR (Human Activity Recognition) algorithms and applications on smartphones, including health monitoring, self-managing system and fitness tracking. However, one of the main issues of the existing HAR schemes is that the classification accuracy is relatively low, and in order to improve the accuracy, high computation overhead is needed. In this paper, an efficient Group-based Context-aware classification method for human activity recognition on smartphones, GCHAR is proposed, which exploits hierarchical group-based scheme to improve the classification efficiency, and reduces the classification error through context awareness rather than the intensive computation. Specifically, GCHAR designs the two-level hierarchical classification structure, i.e., inter-group and inner-group, and utilizes the previous state and transition logic (so-called context awareness) to detect the transitions among activity groups. In comparison with other popular classifiers such as RandomTree, Bagging, J48, BayesNet, KNN and Decision Table, thorough experiments on the realistic dataset (UCI HAR repository) demonstrate that GCHAR achieves the best classification accuracy, reaching 94.1636%, and time consumption in training stage of GCHAR is four times shorter than the simple Decision Table and is decreased by 72.21% in classification stage in comparison with BayesNet.

    AB - With smartphones increasingly becoming ubiquitous and being equipped with various sensors, nowadays, there is a trend towards implementing HAR (Human Activity Recognition) algorithms and applications on smartphones, including health monitoring, self-managing system and fitness tracking. However, one of the main issues of the existing HAR schemes is that the classification accuracy is relatively low, and in order to improve the accuracy, high computation overhead is needed. In this paper, an efficient Group-based Context-aware classification method for human activity recognition on smartphones, GCHAR is proposed, which exploits hierarchical group-based scheme to improve the classification efficiency, and reduces the classification error through context awareness rather than the intensive computation. Specifically, GCHAR designs the two-level hierarchical classification structure, i.e., inter-group and inner-group, and utilizes the previous state and transition logic (so-called context awareness) to detect the transitions among activity groups. In comparison with other popular classifiers such as RandomTree, Bagging, J48, BayesNet, KNN and Decision Table, thorough experiments on the realistic dataset (UCI HAR repository) demonstrate that GCHAR achieves the best classification accuracy, reaching 94.1636%, and time consumption in training stage of GCHAR is four times shorter than the simple Decision Table and is decreased by 72.21% in classification stage in comparison with BayesNet.

    KW - Context awareness

    KW - Hierarchical classifier

    KW - Human Activity Recognition (HAR)

    KW - Machine learning

    UR - http://www.scopus.com/inward/record.url?scp=85021154566&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85021154566&partnerID=8YFLogxK

    U2 - 10.1016/j.jpdc.2017.05.007

    DO - 10.1016/j.jpdc.2017.05.007

    M3 - Article

    JO - Journal of Parallel and Distributed Computing

    JF - Journal of Parallel and Distributed Computing

    SN - 0743-7315

    ER -