Wireless Mobile Communication and Healthcare. 6th International Conference, MobiHealth 2016, Milan, Italy, November 14-16, 2016, Proceedings

Research Article

Investigation of Sensor Placement for Accurate Fall Detection

Download
192 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-58877-3_30,
        author={Periklis Ntanasis and Evangelia Pippa and Ahmet \O{}zdemir and Billur Barshan and Vasileios Megalooikonomou},
        title={Investigation of Sensor Placement for Accurate Fall Detection},
        proceedings={Wireless Mobile Communication and Healthcare. 6th International Conference, MobiHealth 2016, Milan, Italy, November 14-16, 2016, Proceedings},
        proceedings_a={MOBIHEALTH},
        year={2017},
        month={6},
        keywords={Fall detection Fall classification Wearable sensors Sensor placement Machine learning Classification Accelerometers Gyroscopes},
        doi={10.1007/978-3-319-58877-3_30}
    }
    
  • Periklis Ntanasis
    Evangelia Pippa
    Ahmet Özdemir
    Billur Barshan
    Vasileios Megalooikonomou
    Year: 2017
    Investigation of Sensor Placement for Accurate Fall Detection
    MOBIHEALTH
    Springer
    DOI: 10.1007/978-3-319-58877-3_30
Periklis Ntanasis1,*, Evangelia Pippa1,*, Ahmet Özdemir2,*, Billur Barshan3,*, Vasileios Megalooikonomou1,*
  • 1: University of Patras
  • 2: Erciyes University
  • 3: Bilkent University
*Contact email: ntanasis@ceid.upatras.gr, pippa@ceid.upatras.gr, aturan@erciyes.edu.tr, billur@ee.bilkent.edu.tr, vasilis@ceid.upatras.gr

Abstract

Fall detection is typically based on temporal and spectral analysis of multi-dimensional signals acquired from wearable sensors such as tri-axial accelerometers and gyroscopes which are attached at several parts of the human body. Our aim is to investigate the location where such wearable sensors should be placed in order to optimize the discrimination of falls from other Activities of Daily Living (ADLs). To this end, we perform feature extraction and classification based on data acquired from a single sensor unit placed on a specific body part each time. The investigated sensor locations include the head, chest, waist, wrist, thigh and ankle. Evaluation of several classification algorithms reveals the waist and the thigh as the optimal locations.