Emerging Technologies for Developing Countries. First International EAI Conference, AFRICATEK 2017, Marrakech, Morocco, March 27-28, 2017 Proceedings

Research Article

Analysis and Effect of Feature Selection Over Smartphone-Based Dataset for Human Activity Recognition

  • @INPROCEEDINGS{10.1007/978-3-319-67837-5_20,
        author={Ilham Amezzane and Youssef Fakhri and Mohammed Aroussi and Mohamed Bakhouya},
        title={Analysis and Effect of Feature Selection Over Smartphone-Based Dataset for Human Activity Recognition},
        proceedings={Emerging Technologies for Developing Countries. First International EAI Conference, AFRICATEK 2017, Marrakech, Morocco, March 27-28, 2017 Proceedings},
        proceedings_a={AFRICATEK},
        year={2017},
        month={10},
        keywords={Human Activity Recognition Smartphone sensors Feature selection},
        doi={10.1007/978-3-319-67837-5_20}
    }
    
  • Ilham Amezzane
    Youssef Fakhri
    Mohammed Aroussi
    Mohamed Bakhouya
    Year: 2017
    Analysis and Effect of Feature Selection Over Smartphone-Based Dataset for Human Activity Recognition
    AFRICATEK
    Springer
    DOI: 10.1007/978-3-319-67837-5_20
Ilham Amezzane1,*, Youssef Fakhri1,*, Mohammed Aroussi1,*, Mohamed Bakhouya2,*
  • 1: Université Ibn Tofail
  • 2: International University of Rabat
*Contact email: ilhammaj@gmail.com, fakhri@uit.ac.ma, mohamed.elaroussi@ieee.org, Mohamed.bakhouya@uir.ac.ma

Abstract

The availability of diverse and powerful sensors that are embedded in modern smartphones has created exciting opportunities for developing context-aware services and applications. For example, Human activity recognition (HAR) is an important feature that could be applied to many applications and services, such as those in healthcare and transportation. However, recognizing relevant human activities using smartphones remains a challenging task and requires efficient data mining approaches. In this paper, we present a comparison study for HAR using features selection methods to reduce the training and classification time while maintaining significant performance. In fact, due to the limited resources of Smartphones, reducing the feature set helps reducing computation costs, especially for real-time continuous online applications. We validated our approach on a publicly available dataset to classify six different activities. Results show that Recursive Feature Elimination algorithm works well with Radial Basis Function Support Vector Machine and significantly improves model building time without decreasing recognition performance.