A Combination of Feature Extraction and Feedforward Neural Network to Estimate Muscle Activity in Human Gait

Inertial Measurement Unit (IMU) has been widely recognized to be the practical alternative to capture and analyze human gait. However, due to its inherent characteristics, it can only measure the basic kinematics of the body segment it attached to. With the help of the machine learning, IMU can be used to determine the dynamic behavior of the major lower extremity muscle. This paper explores the use of feature-extracted IMU data and a neural network to estimate muscle activity during walking. IMU and Electromyogram (EMG) data were collected from fifty-eight healthy participants. Principal Component Analysis (PCA) and Tsfresh (Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests) were applied to extract the relevant features from the data. These features were then used to train the Feedforward Neural Network (FNN). A combination of Tsfresh and FNN yielded the best results with correlation coefficient $(r)$ of 95.73% and Root Mean Square Error (RMSE) of 11.20%. This research can potentially help reduce the number of sensors needed in gait analysis, allow for portable motion capture, and improve the accuracy and efficiency of the FNN model in estimating muscle activity.

I. Introduction

The application of wearable sensors, such as Inertial Measurement Unit (IMU) has gained significant traction in the human movement analysis. This sensor provides critical information about the body motion in various activities, including walking. Typical walking gait analysis involves the use of optical motion capture system, force plate and Electromyogram (EMG). However, these systems are bulky and require elaborate setup. Thus, performing gait analysis outside of the clinical or laboratory setting is difficult.