CBARS: Cluster based classification for activity recognition systems

Zahraa Said Abdallah, Mohamed Medhat Gaber, Bala Srinivasan, Shonali Krishnaswamy

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    16 Citations (Scopus)


    Activity recognition focuses on inferring current user activities by leveraging sensory data available on today’s sensor rich environment. Supervised learning has been applied pervasively for activity recognition. Typical activity recognition techniques process sensory data based on point-by-point approaches. In this paper, we propose a novel Cluster Based Classification for Activity Recognition Systems, CBARS. The novel approach processes activities as clusters to build a robust classification framework. CBARS integrates supervised, unsupervised and active learning and applies hybrid similarity measures technique for recognising activities. Extensive experimental results using real activity recognition dataset have evidenced that our new approach shows improved performance over other existing state-of-the-art learning methods.
    Original languageEnglish
    Title of host publicationAdvanced Machine Learning Technologies and Applications
    Subtitle of host publicationFirst International Conference, AMLTA 2012, Cairo, Egypt, December 8-10, 2012, Proceedings
    EditorsAboul Ella Hassanien, Abdel-Badeeh M. Salem, Rabie Ramadan, Tai-hoon Kim
    Place of PublicationHeidelberg [Germany]
    Pages82 - 91
    Number of pages10
    ISBN (Electronic)9783642353260
    ISBN (Print)9783642353253
    Publication statusPublished - 2012
    EventInternational Conference on Advanced Machine Learning Technologies and Applications (AMLTA) 2012 - Cairo, Egypt
    Duration: 8 Dec 201210 Dec 2012
    Conference number: 1st (Conference Proceedings)

    Publication series

    NameCommunications in Computer and Information Science
    ISSN (Print)1865-0929
    ISSN (Electronic)1865-0937


    ConferenceInternational Conference on Advanced Machine Learning Technologies and Applications (AMLTA) 2012
    Abbreviated titleAMLTA 2012
    Internet address


    • Activity recognition
    • Cluster based classification
    • Hybrid similarity measure

    Cite this