Visible to the public Gait Phase Segmentation Using Weighted Dynamic Time Warping and K-Nearest Neighbors Graph Embedding

TitleGait Phase Segmentation Using Weighted Dynamic Time Warping and K-Nearest Neighbors Graph Embedding
Publication TypeConference Paper
Year of Publication2020
AuthorsChen, T., Lin, T., Hong, Y.- P.
Conference NameICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Date Publishedmay
Keywordsdiseases, Dynamic Time Warping, gait analysis, gait cycle, gait information, gait phase estimates, gait phase segmentation method, graph embedding, graph theory, image segmentation, inertial measurement units, k-nearest neighbors, k-nearest neighbors algorithm, k-nearest neighbors graph embedding, Measurement, nearest neighbor search, nearest neighbour methods, neural nets, neural network-based graph embedding scheme, Predictive Metrics, pubcrawl, self-collected IMU gait signals, weighted dynamic time warping algorithm
AbstractGait phase segmentation is the process of identifying the start and end of different phases within a gait cycle. It is essential to many medical applications, such as disease diagnosis or rehabilitation. This work utilizes inertial measurement units (IMUs) mounted on the individual's foot to gather gait information and develops a gait phase segmentation method based on the collected signals. The proposed method utilizes a weighted dynamic time warping (DTW) algorithm to measure the distance between two different gait signals, and a k-nearest neighbors (kNN) algorithm to obtain the gait phase estimates. To reduce the complexity of the DTW-based kNN search, we propose a neural network-based graph embedding scheme that is able to map the IMU signals associated with each gait cycle into a distance-preserving low-dimensional representation while also producing a prediction on the k nearest neighbors of the test signal. Experiments are conducted on self-collected IMU gait signals to demonstrate the effectiveness of the proposed scheme.
Citation Keychen_gait_2020