# High-Knee-Flexion Posture Recognition Using Multi-Dimensional Dynamic Time Warping on Inertial Sensor Data

## TL;DR

This study develops a sensor-based system using motion data to recognize high-knee-flexion postures commonly seen in work environments.

## Contribution

A novel framework using multi-dimensional Dynamic Time Warping for posture recognition from inertial sensor data is proposed.

## Key findings

- The mDTW model achieved 82.3% accuracy in classifying postures from a testing dataset.
- The model showed improved performance (86% accuracy) after adjusting for classification group imbalances.
- The model struggled to distinguish between similar squatting postures and failed to recognize walking sequences.

## Abstract

Relating continuously collected inertial data to the activities or postures performed by the sensor wearer requires pattern recognition or machine-learning-based algorithms, accounting for the temporal and scale variability present in human movements. The objective of this study was to develop a sensor-based framework for the detection and measurement of high-flexion postures frequently adopted in occupational settings. IMU-based joint angle estimates for the ankle, knee, and hip were time and scale normalized prior to being input to a multi-dimensional Dynamic Time Warping (mDTW) distance-based Nearest Neighbour algorithm for the identification of twelve postures. Data from 50 participants were divided to develop and evaluate the mDTW model. Overall accuracies of 82.3% and 55.6% were reached when classifying movements from the testing and validation datasets, respectively, which increased to 86% and 74.6% when adjusting for imbalances between classification groups. The highest misclassification rates occurred between flatfoot squatting, heels-up squatting, and stooping, while the model was incapable of identifying sequences of walking based on a single stride template. The developed mDTW model proved robust in identifying high-flexion postures performed by participants both included and precluded from algorithm development, indicating its strong potential for the quantitative measurement of postural adoption in real-world settings.