Detecting falls using a fall indicator defined by a linear combination of kinematic measures

The objective of this study was to determine whether a novel fall detection model based on the statistical process control chart performed better when the fall indicator was defined by a linear combination of kinematic measures. To specify the fall indicator, an optimization procedure was performed in which the trial and error method was used to determine the relative weightings of the selected kinematic measures associated with the optimal fall detection performance. The highest sensitivity, highest specificity, and lowest sum of squared errors of the fall detection model obtained from this study were 97.3%, 99.2% and 0.00133 respectively. These findings suggested that using the fall indicator defined by a linear combination of kinematic measures can lead to improved fall detection performance compared to that defined by a single kinematic measure.

[1]  Billur Barshan,et al.  Detecting Falls with Wearable Sensors Using Machine Learning Techniques , 2014, Sensors.

[2]  Jean Meunier,et al.  Fall Detection from Human Shape and Motion History Using Video Surveillance , 2007, 21st International Conference on Advanced Information Networking and Applications Workshops (AINAW'07).

[3]  Shuwan Xue,et al.  Portable Preimpact Fall Detector With Inertial Sensors , 2008, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[4]  Francis E. H. Tay,et al.  Application of motion analysis system in pre-impact fall detection. , 2008, Journal of biomechanics.

[5]  Xinyao Hu,et al.  Differentiating slip-induced falls from normal walking and successful recovery after slips using kinematic measures , 2013, Ergonomics.

[6]  Majd Alwan,et al.  Falls, Fall Prevention, and Fall Detection Technologies , 2008 .

[7]  Jian Liu,et al.  Automatic individual calibration in fall detection – an integrative ambulatory measurement framework , 2013, Computer methods in biomechanics and biomedical engineering.

[8]  Donald Y. C. Lie,et al.  A fall detection study on the sensors placement location and a rule-based multi-thresholds algorithm using both accelerometer and gyroscopes , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[9]  Jian Liu,et al.  Development and Evaluation of a Prior-to-Impact Fall Event Detection Algorithm , 2014, IEEE Transactions on Biomedical Engineering.

[10]  G. Wu,et al.  Distinguishing fall activities from normal activities by velocity characteristics. , 2000, Journal of biomechanics.

[11]  A K Bourke,et al.  Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. , 2007, Gait & posture.

[12]  Toshiyo Tamura,et al.  A Wearable Airbag to Prevent Fall Injuries , 2009, IEEE Transactions on Information Technology in Biomedicine.

[13]  Xinyao Hu,et al.  An individual-specific fall detection model based on the statistical process control chart , 2014 .

[14]  Thurmon E Lockhart,et al.  Trunk angular kinematics during slip-induced backward falls and activities of daily living. , 2014, Journal of biomechanical engineering.