amsys 19(18): e3

Research Article

Activity recognition evaluation via machine learning

Download647 downloads
  • @ARTICLE{10.4108/eai.23-3-2018.161436,
        author={A.N.A.  Rameka and A.M.  Connor and J.  Kruse},
        title={Activity recognition evaluation via machine learning},
        journal={EAI Endorsed Transactions on Ambient Systems},
        volume={6},
        number={18},
        publisher={EAI},
        journal_a={AMSYS},
        year={2019},
        month={11},
        keywords={Activity Recognition, Machine Learning, Internet of Things, Smart Floors, Smart Chairs, Smart Environments},
        doi={10.4108/eai.23-3-2018.161436}
    }
    
  • A.N.A. Rameka
    A.M. Connor
    J. Kruse
    Year: 2019
    Activity recognition evaluation via machine learning
    AMSYS
    EAI
    DOI: 10.4108/eai.23-3-2018.161436
A.N.A. Rameka1, A.M. Connor1,*, J. Kruse1
  • 1: Auckland University of Technology, Private Bag 92006, Wellesley Street, Auckland 1142, New Zealand
*Contact email: andrew.connor@aut.ac.nz

Abstract

With the proliferation of relatively cheap Internet of Things (IoT) devices, smart environments have been highlighted as an example of how the IoT can make our lives easier. Each of these ‘things’ produces data which can work in unison to react to its users. Machine learning makes use of this data to make inferences about our habits and activities, such as our buying preferences or likely commute destinations. However, this level of human inclusion within the IoT relies on indirect inferences from the usage of these devices or services. Activity recognition is already a widely researched area and could provide a more direct way of including humans within this system. This research explores the feasibility of using a cost effective, unobtrusive, single modality ground-based sensor matrix to track subtle pressure changes to predict user activity, in an effort to assess its ability to act as an intermediary interface between humans and digital systems such as the IoT.