Hybrid Learning-based Balance Function Assessment of Stroke Patients with a Single Ear-Worn IMU

Abstract

Rehabilitation robotics has attracted increasing attention due to its ability to provide continuous, precise, and adaptive treatment programs for stroke patients during their recovery. Accurately assessing lower-limb motor function is crucial in effectively implementing robot-assisted rehabilitation. This study proposes a novel application of a hybrid learning framework that leverages a single-ear-worn inertial measurement unit (IMU) combined with deep learning techniques to predict the Berg Balance Scale (BBS) scores. Participants performed a 3-meter Timed Up and Go (TUG) test while wearing the e-AR sensor. The collected 6-axis IMU data were processed through a CNN-LSTM framework, where we integrated time-domain, frequency-domain, and static features to enhance the model’s regression performance. Experimental results demonstrate that our proposed method achieves a mean absolute error (MAE) of 1.074, surpassing previous studies’ reported results and outperforming traditional machine learning and conventional deep learning algorithms when applied to ear-worn sensor data. The proposed framework is simple to operate yet accurate, making it suitable for patients’ self-assessment even in a home environment.