Prediction of Stability during Walking at Simulated Ship’s Rolling Motion Using Accelerometers

Abstract

Due to a ship’s extreme motion, there is a risk of injuries and accidents as people may become unbalanced and be injured or fall from the ship. Thus, individuals must adjust their movements when walking in an unstable environment to avoid falling or losing balance. A person’s ability to control their center of mass (COM) during lateral motion is critical to maintaining balance when walking. Dynamic balancing is also crucial to maintain stability while walking. The margin of stability (MOS) is used to define this dynamic balancing. This study aimed to develop a model for predicting balance control and stability in walking on ships by estimating the peak COM excursion and MOS variability using accelerometers. We recruited 30 healthy individuals for this study. During the experiment, participants walked for two minutes at self-selected speeds, and we used a computer-assisted rehabilitation environment (CAREN) system to simulate the roll motion. The proposed prediction models in this study successfully predicted the peak COM excursion and MOS variability. This study may be used to protect and save seafarers or passengers by assessing the risk of balance loss.

Machine Learning-Based Approach to Identifying Fall Risk in Seafarers Using Wearable Sensors

“…Furthermore, the ship's rolling motion may alter the COM motion and reduce dynamic stability during walking [77]. In a previous study [50], these gait features successfully predicted COM motion, which can be said to be effective in detecting fall risks and be closely related to dynamic stability. We also found that the mediolateral and anterior-posterior directional features were mainly selected.…”

“…Feature engineering in HAR encompasses various techniques, including feature stacking, feature space reduction, and the design of high-level HAR features [51][52][53]. We applied the least absolute shrinkage and selection operator (LASSO) to select a subset of relevant features, since the LASSO was the best feature selection method for identical data in the previous study [50]. In LASSO, the residual sum of squares of a vector of regression coefficients is minimized subject to a constraint on the L1-norm [54].…”