4th International ICST Conference on Body Area Networks

Research Article

SmartFall: An Automatic Fall Detection System Based on Subsequence Matching for the SmartCane

Download314 downloads
  • @INPROCEEDINGS{10.4108/ICST.BODYNETS2009.5873,
        author={Mars Lan and Ani Nahapetian and Alireza Vahdatpour and Lawrence Au and William Kaiser and Majid Sarrafzadeh},
        title={SmartFall: An Automatic Fall Detection System Based on Subsequence Matching for the SmartCane},
        proceedings={4th International ICST Conference on Body Area Networks},
        publisher={ICST},
        proceedings_a={BODYNETS},
        year={2010},
        month={5},
        keywords={Wireless health fall detection subsequence matching geriatrics},
        doi={10.4108/ICST.BODYNETS2009.5873}
    }
    
  • Mars Lan
    Ani Nahapetian
    Alireza Vahdatpour
    Lawrence Au
    William Kaiser
    Majid Sarrafzadeh
    Year: 2010
    SmartFall: An Automatic Fall Detection System Based on Subsequence Matching for the SmartCane
    BODYNETS
    ICST
    DOI: 10.4108/ICST.BODYNETS2009.5873
Mars Lan1,*, Ani Nahapetian1,2,*, Alireza Vahdatpour1,*, Lawrence Au3,*, William Kaiser3,2,*, Majid Sarrafzadeh1,2,*
  • 1: Computer Science Department, University of California Los Angeles, Los Angeles, CA 90095
  • 2: Wireless Health Institute, University of California Los Angeles, Los Angeles, CA 90095
  • 3: Electrical Engineering Department, University of California Los Angeles, Los Angeles, CA 90095
*Contact email: marslan@cs.ucla.edu, ani@cs.ucla.edu, alireza@cs.ucla.edu, au@ee.ucla.edu, kaiser@ee.ucla.edu, majid@cs.ucla.edu

Abstract

Fall-induced injury has become a leading cause of death for the elderly. Many elderly people rely on canes as an assis- tive device to overcome problems such as balance disorder and leg weakness, which are believed to have led to many incidents of falling. In this paper, we present the design and the implementation of SmartFall, an automatic fall de- tection system for the SmartCane system we have developed previously. SmartFall employs subsequence matching, which di®ers fundamentally from most existing fall detection sys- tems based on multi-stage thresholding. The SmartFall sys- tem achieves a near perfect fall detection rate for the four types of fall conducted in the experiments. After augment- ing the algorithm with an assessment on the peak impact force, we have successfully reduced the false-positive rate of the system to close to zero for all six non-falling activities performed in the experiment.