2017/11 Real-Time human gait segmentation based on adaptive tool using single-axis wearable gyroscope.


“Time-effective and versatile computational methodologies for the human gait analysis are essential to evaluate the gait performance for diagnosis and treatments purposes. This work proposes an adaptive tool for human gait events detection in real-time, based on the angular velocity recorded from one gyroscope placed on the instep of the foot and in a finite state machine using adaptive decision rules.
The tool was validated in the detection of 6 gait events performed by healthy subjects walking on a treadmill at different speeds (1.5 to 4.5 km/h) and slopes (0 to 10%). Results point out that the tool is highly accurate and time-effective for the detection of all events, as indicated by the values of accuracy, average delays and advances (Heel strike: 99.96%, -7.95 ms, and 9.85 ms; Foot-flat: 99.48%, -4.95 ms, and 9.35 ms; Middle Mid-Stance: 98.26%, -36.54 ms, and 16.38 ms; Heel-off: 98.87%, -22.71 ms, and 18.62 ms; Toe-off: 95.95%, -6.80 ms, 14.38 ms; Middle Mid-Swing: 96.06%, -3.45 ms; 0.15 ms, respectively). These findings suggest that the adaptive character of proposed tool, only dependent on a kinematic signal, is suitable for the real-time gait analysis in diverse real-life activities, including barefoot and footwear conditions.”