2nd International ICST Conference on Pervasive Computing Technologies for Healthcare

Research Article

ADL Recognition Based on the Combination of RFID and Accelerometer Sensing

Download536 downloads
  • @INPROCEEDINGS{10.4108/ICST.PERVASIVEHEALTH2008.2795,
        author={Maja Stikic and T\~{a}m Huynh and Kristof Van Laerhoven and Bernt Schiele},
        title={ADL Recognition Based on the Combination of RFID and Accelerometer Sensing},
        proceedings={2nd International ICST Conference on Pervasive Computing Technologies for Healthcare},
        publisher={IEEE},
        proceedings_a={PERVASIVEHEALTH},
        year={2008},
        month={7},
        keywords={Acceleration Accelerometers Algorithm design and analysis Monitoring Performance evaluation RFID tags Radiofrequency identification Senior citizens Sensor systems Wearable sensors},
        doi={10.4108/ICST.PERVASIVEHEALTH2008.2795}
    }
    
  • Maja Stikic
    Tâm Huynh
    Kristof Van Laerhoven
    Bernt Schiele
    Year: 2008
    ADL Recognition Based on the Combination of RFID and Accelerometer Sensing
    PERVASIVEHEALTH
    ICST
    DOI: 10.4108/ICST.PERVASIVEHEALTH2008.2795
Maja Stikic1,*, Tâm Huynh2,*, Kristof Van Laerhoven2,*, Bernt Schiele2,*
  • 1: Fraunhofer IGD, Darmstadt, Germany
  • 2: Computer Science Department, TU Darmstadt, Germany
*Contact email: stikic@mis.tu-darmstadt.de, huynh@mis.tu-darmstadt.de, kristof@mis.tu-darmstadt.de, schiele@mis.tu-darmstadt.de

Abstract

The manual assessment of Activities of Daily Living (ADLs) is a fundamental problem in elderly care. The use of miniature sensors placed in the environment or worn by a person has great potential in effective and unobtrusive long term monitoring and recognition of ADLs. This paper presents an effective and unobtrusive activity recognition system based on the combination of the data from two different types of sensors: RFID tag readers and accelerometers. We evaluate our algorithms on non-scripted datasets of 10 housekeeping activities performed by 12 subjects. The experimental results show that recognition accuracy can be significantly improved by fusing the two different types of sensors. We analyze different acceleration features and algorithms, and based on tag detections we suggest the best tags’ placements and the key objects to be tagged for each activity.