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

• New fall indicators in fall detection was proposed.
• The detection sensitivity and specificity were up to 97.3% and 99.2%, respectively.
• The proposed fall indicators can lead to improved fall detection performance.

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.