Gait Parameter Estimation From a Miniaturized Ear-Worn Sensor Using Singular Spectrum Analysis and Longest Common Subsequence

Abstract

This paper presents a new approach to gait analysis and parameter estimation from a single miniaturized ear-worn sensor embedded with a triaxial accelerometer. Singular spectrum analysis combined with the longest common subsequence algorithm has been used as a basis for gait parameter estimation. It incorporates information from all axes of the accelerometer to estimate parameters including swing, stance, and stride times. Rather than only using local features of the raw signals, the periodicity of the signals is also taken into account. The hypotheses tested by this study include: 1) how accurate is the ear-worn sensor in terms of gait parameter extraction compared to the use of an instrumented treadmill; 2) does the ear-worn sensor provide a feasible option for assessment and quantification of gait pattern changes. Key gait events for normal subjects such as heel contact and toe off are validated with a high-speed camera, as well as a force-plate instrumented treadmill. Ten healthy adults walked for 20 min on a treadmill with an increasing incline of 2% every 2 min. The upper and lower limits of the absolute errors using 95% confidence intervals for swing, stance, and stride times were obtained as 35.5 ±3.99 ms, 36.9 ±3.84 ms, and 17.9 ±2.29 ms, respectively.

Return of functional mobility after an open tibial fracture

“…14 The software implemented allows an intermediary phase whereby each step detected can be checked manually. This feature of the software identified periodic changes in gait attributed to turning at the end of the corridor, which were subsequently removed.…”

An Overview of Smart Shoes in the Internet of Health Things: Gait and Mobility Assessment in Health Promotion and Disease Monitoring

“…These can be facilitated by simplistic approaches such as peak detection or zero-crossings [36], or sequential model-based approaches such as hidden Markov models [37]. Template-based approaches, such as longest common subsequence [38], Dynamic Time Warping [39], and the multi-dimensional subsequence Dynamic Time Warping approach (msDTW) [40] are also commonly used. The aforementioned methods are often chosen and optimized depending on the application context, as they vary in computational complexity for training, effectiveness, and generality.…”

Gait Analysis From a Single Ear-Worn Sensor: Reliability and Clinical Evaluation for Orthopaedic Patients

“…The accuracies of gait events estimated from the e-AR sensor by the proposed algorithms [12] [22] are assessed using an instrumented treadmill [12] and pressure insoles for walking in a corridor [22]. For initial detection of gait events, the method based on singular spectrum analysis (SSA) and longest common subsequent algorithm (LCSS) [12] with its extension [22] has been used.…”

“…For initial detection of gait events, the method based on singular spectrum analysis (SSA) and longest common subsequent algorithm (LCSS) [12] with its extension [22] has been used. This gait event detection algorithm is mainly based on the SSA algorithm in which the acceleration signals from different axes are converted into matrix forms by using delayed versions of the input accelerations.…”

“…These are listed in Table I ( [5], [8], [12]- [14], [16], [20]- [25]). For example, the ear-worn Activity Recognition (e-AR) sensor has been used in both experimental and clinical settings [5], [12], [22]- [25]. The sensor includes an accelerometer and the major advantage of the sensor is in its bio-inspired design and ease of consistence sensor placement.…”