Assisted Gait Phase Estimation Through an Embedded Depth Camera Using Modified Random Forest Algorithm Classification

• Published in: IEEE sensors journal Vol. 20; no. 6; pp. 3343 - 3355
• Main Authors: Pasinetti, Simone, Fornaser, Alberto, Lancini, Matteo, De Cecco, Mariolino, Sansoni, Giovanna
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.03.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cameras; Classification; Classifiers; Data collection; Depth sensing; Floors; Foot; Gait; gait analysis; Image classification; Legged locomotion; Machine learning; measurement; Orthoses; Radio frequency; Sensors; Three-dimensional displays; Uncertainty
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2019.2957667

The paper presents a novel method for the classification of gait phases for power gait orthosis users based on machine learning. The classification uses depth images collected from a Time of Flight camera embedded in the crutches employed for the assisted gait. The machine learning algorithm foresees an initial phase of data collection and processing, identifying the 3D points belonging to the foot and those belonging to the floor. From these, a feature set is computed analyzing the values of percentiles of distances of the foot from the floor, and passed to a modified version of Random Forest classifier, called Sigma-z Random Forest. The classifier considers the uncertainties associated to each feature set and provides both the classification of the gait phase (stance or swing) and an associated confidence value. In this work, we propose the use of the confidence value to improve the reliability of the gait phase classification, by applying an optimized threshold to the confidence value obtained for each new frame. The algorithm has been tested on different subjects and environments. An average classification accuracy of 87.3% has been obtained (+6.3% with respect to the standard random forest classifier), with a minor loss of unclassifiable frames. Results highlight that unclassifiable samples are usually associated to transitions between stance and swing.