Time series classification using a modified LSTM approach from accelerometer-based data: A comparative study for gait cycle detection

• Published in: Gait & posture Vol. 74; pp. 128 - 134
• Main Authors: Tan, Hui Xing, Aung, Nway Nway, Tian, Jing, Chua, Matthew Chin Heng, Yang, Youheng Ou
• Format: Journal Article
• Language: English
• Published: England Elsevier B.V 01.10.2019
• Subjects: Accelerometry - methods; Algorithms; Databases, Factual; Female; Gait; Gait - physiology; Gait event detection; Humans; Inertial sensors; Long-short term memory models; LSTM; Male; Movement Disorders - diagnosis; Movement Disorders - rehabilitation; Walking; Gait event detection; Inertial sensors; LSTM; Gait; Long-short term memory models
• ISSN: 0966-6362; 1879-2219; 1879-2219
• DOI: 10.1016/j.gaitpost.2019.09.007

•A modified Long Short-Term Memory networks model was proposed.•Data from the MAREA database was used for the experiment.•Modifications include composite accelerations, extra hidden layers and oversampling.•The model performed better than the 6 other state-of-the-art gait models. Gait event detection (GED) is an important aspect in identifying and interpret a user’s gait to assess gait abnormalities and design intelligent assistive devices. There is a need to develop robust GED models that can accurately detect various gait instances in different scenarios and environments. This paper presents a novel method of detecting heel strikes (HS) and toe offs (TO) during the user’s gait cycle using a modified Long Short-Term Memory (LSTM) networks approach. The method was tested on a database from Movement Analysis in Real-world Environments using Accelerometers (MAREA) (n = 20 healthy subjects) that consisted of walking and running in indoor and outdoor environments with accelerometers positioned on waist, wrist and both ankles. Modifications include oversampling, composite accelerations and optimizing the LSTM network architecture were made. Performance of our modified model was found to be better than six state-of-the-art GED algorithms, with a median F1 score of 0.98 for Heel Strikes and 0.98 for Toe Offs in the scenario of steady walking in an indoor environment, and a median F1 score of 0.94 for Heel Strikes and 0.68 for Toe-offs in the scenario of walking and running in an outdoor environment. This paper highlights the potential of the single proposed model to be an alternative to the six GED models in gait detection under various conditions.