Robust Stride Detector from Ankle-Mounted Inertial Sensors for Pedestrian Navigation and Activity Recognition with Machine Learning Approaches.

In this paper, a stride detector algorithm combined with a technique inspired by zero velocity update (ZUPT) is proposed to reconstruct the trajectory of a pedestrian from an ankle-mounted inertial device. This innovative approach is based on sensor alignment and machine learning. It is able to detect 100% of both normal walking strides and more than 97% of atypical strides such as small steps, side steps, and backward walking that existing methods can hardly detect. This approach is also more robust in critical situations, when for example the wearer is sitting and moving the ankle or when the wearer is bicycling (less than two false detected strides per hour on average). As a consequence, the algorithm proposed for trajectory reconstruction achieves much better performances than existing methods for daily life contexts, in particular in narrow areas such as in a house. The computed stride trajectory contains essential information for recognizing the activity (atypical stride, walking, running, and stairs). For this task, we adopt a machine learning approach based on descriptors of these trajectories, which is shown to be robust to a large of variety of gaits. We tested our algorithm on recordings of healthy adults and children, achieving more than 99% success. The algorithm also achieved more than 97% success in challenging situations recorded by children suffering from movement disorders. Compared to most algorithms in the literature, this original method does not use a fixed-size sliding window but infers this last in an adaptive way.

Home-Based Monitor for Gait and Activity Analysis.

Current outcomes in neuromuscular disorder clinical trials include motor function scales, timed tests, and strength measures performed by trained clinical evaluators. These measures are slightly subjective and are performed during a visit to a clinic or hospital and constitute therefore a point assessment. Point assessments can be influenced by daily patient condition or factors such as fatigue, motivation, and intercurrent illness. To enable home-based monitoring of gait and activity, a wearable magneto-inertial sensor (WMIS) has been developed. This device is a movement monitor composed of two very light watch-like sensors and a docking station. Each sensor contains a tri-axial accelerometer, gyroscope, magnetometer, and a barometer that record linear acceleration, angular velocity, the magnetic field of the movement in all directions, and barometric altitude, respectively. The sensors can be worn on the wrist, ankle, or wheelchair to record the subject's movements during the day. The docking station enables data uploading and recharging of sensor batteries during the night. Data are analyzed using proprietary algorithms to compute parameters representative of the type and intensity of the performed movement. This WMIS can record a set of digital biomarkers, including cumulative variables, such as total number of meters walked, and descriptive gait variables, such as the percentage of the most rapid or longest stride that represents the top performance of patient over a predefined period of time.