Automated Detection of Instantaneous Gait Events Using Time Frequency Analysis and Manifold Embedding

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 21; no. 6; pp. 908 - 916
• Main Authors: Aung, Min S. H., Thies, Sibylle B., Kenney, Laurence P. J., Howard, David, Selles, Ruud W., Findlow, Andrew H., Goulermas, John Y.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2013; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Accelerometers; Accelerometry; Accuracy; Algorithms; Artificial Intelligence; Biomechanics; Classification; Classification algorithms; Continuous wavelet transforms; Equipment Design; Equipment Failure Analysis; Feature extraction; Foot; Gait; Gait - physiology; gait event detection; Heels; Humans; Legged locomotion; Micro-Electrical-Mechanical Systems - instrumentation; Monitoring, Ambulatory - methods; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; signal segmentation; Strikes; Walking; Wavelet transforms
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2013.2239313

Accelerometry is a widely used sensing modality in human biomechanics due to its portability, non-invasiveness, and accuracy. However, difficulties lie in signal variability and interpretation in relation to biomechanical events. In walking, heel strike and toe off are primary gait events where robust and accurate detection is essential for gait-related applications. This paper describes a novel and generic event detection algorithm applicable to signals from tri-axial accelerometers placed on the foot, ankle, shank or waist. Data from healthy subjects undergoing multiple walking trials on flat and inclined, as well as smooth and tactile paving surfaces is acquired for experimentation. The benchmark timings at which heel strike and toe off occur, are determined using kinematic data recorded from a motion capture system. The algorithm extracts features from each of the acceleration signals using a continuous wavelet transform over a wide range of scales. A locality preserving embedding method is then applied to reduce the high dimensionality caused by the multiple scales while preserving salient features for classification. A simple Gaussian mixture model is then trained to classify each of the time samples into heel strike, toe off or no event categories. Results show good detection and temporal accuracies for different sensor locations and different walking terrains.