Sensors and algorithms for locomotion intention detection of lower limb exoskeletons

Wang, Duojin; Gu, Xiaoping; Yu, Hongliu

doi:10.1016/j.medengphy.2023.103960

Cited by 8 publications

(1 citation statement)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the sensor fusion technique [27] for combining EMG and IMU sensor data is known to improve the performance of ML predictions [28]. While it is commonly used for assistive devices of the upper [29] and lower limbs [30], [31], sensor fusion has not been applied to trunk assistive devices. Therefore, this study aimed to utilize the sensor fusion technique with data from EMG and IMU sensors for trunk movement intention detection with the chair-mounted passive trunk orthosis (CMPTO).…”

Section: Introductionmentioning

confidence: 99%

Sensor Fusion and Machine Learning for Seated Movement Detection With Trunk Orthosis

Zahid Rao,

Shahid Siddique,

Danish Mujib

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Advanced assistive devices developed for activities of daily living use machine learning (ML) for motion intention detection using wearable sensors. Trunk assistive devices provide safety, balance, and independence for wheelchair-bound individuals who spend prolonged hours in sitting positions. We used ML for trunk movement intention detection with a trunk orthosis. Sensor fusion technique with four electromyography (EMG) and one inertial measurement unit (IMU) sensor signals are used to develop a three-level classification system. Forty participants engaged in seated trunk movement trials wearing the orthosis. The trials comprised 30 movements involving trunk flexion/extension, lateral bending, and axial rotation. The wrapper method was used to reduce essential EMG features. Ensemble (ES), k-nearest neighbors (KNN), and support vector machine ML classifiers were used. Twenty-six features (five EMG for each of four muscles and six for IMU) were used to develop ten individual ML models, resulting in an average accuracy of 95.44%. Eight models achieved the highest accuracy with the ES and two with KNN. The models were then cascaded to form a trunk motion detection system that achieved a test accuracy of 87.0%. The promising result of this study can be implemented for trunk motion recognition with active trunk orthosis.

show abstract