Detection of Gait Events Using Ear-Worn IMUs During Functional Movement Tasks

Abstract

Complex walking tasks such as turning or walking with head movements are frequently used to assess dysfunction in an individual's vestibular, nervous and musculoskeletal systems. Compared to other methods, wearable inertial measurement units (IMUs) allow quantitative analysis of these tasks in less restricted settings, allowing for a more scalable clinical measurement tool with better ecological validity. This study investigates the use of ear-worn IMUs to identify gait events during complex walking tasks, having collected data on 68 participants with a diverse range of ages and movement-related conditions. The performance of an existing gait event detection algorithm was compared with a new one designed to be more robust to lateral head movements. Our analysis suggests that while both algorithms achieve high initial contact sensitivity across all walking tasks, our new algorithm attains higher terminal contact sensitivity for turning and walking with horizontal head turns, resulting in more accurate estimates of stance and swing times. This provides scope to enable more detailed assessment of complex walking tasks during clinical testing and in daily life settings.

Keywords: earables; gait event detection; inertial sensor; temporal parameters.

Figure 2

The four walking tasks, labelled left to right as 1. Walk, 2. WalkV, 3. WalkH and 4. Turn. The arrows in 2. and 3. indicate the direction of head movement and the arrow in 4. indicates the route taken by the participant around the cone while turning.

Figure 1

(a) Three-dimensional printed IMU headset used for data collection. (b) Headset being worn.

Figure 3

Segmentation of the Turn activity from the TUG trial using thresholding of the yaw signal.

Figure 4

Demonstration of both algorithms applied on a gait cycle. (a) SI acceleration signal, where the grey areas illustrate the window defined by the TP-EAR algorithm for each cycle. (b) ML acceleration signal, where the coloured arrows show the IC laterality determined by the signed difference in the dominant ML signal.

Figure 5

Process followed by TP-EAR to identify IC and TC events for a given walking bout. The green (preprocessing) step is applied to the whole bout, then the blue (processing) and orange (output) steps are applied to each dominant SI peak, which is an estimator to the IC location. $f\left(t\right)$ is the windowed original SI acceleration signal. Laterality detection is then applied in the same way as for the Diao algorithm, demonstrated in Figure 4b.

Figure 6

Time differences between IMU-derived and ground truth stride time for (a) Typical and (b) Non-Typical participant groups.

Figure 7

Time differences between IMU-derived and ground truth stance time for (a) Typical and (b) Non-Typical participant groups.

Figure 7

Time differences between IMU-derived and ground truth stance time for (a) Typical and (b) Non-Typical participant groups.