List of Publications

Abstract

The inertial measurement unit (IMU) has become more prevalent in gait analysis. However, it can only measure the kinematics of the body segment it is attached to. Muscle behaviour is an important part of gait analysis and provides a more comprehensive overview of gait quality. Muscle behaviour can be estimated using musculoskeletal modelling or measured using an electromyogram (EMG). However, both methods can be tasking and resource intensive. A combination of IMU and neural networks (NN) has the potential to overcome this limitation. Therefore, this study proposes using NN and IMU data to estimate nine lower extremity muscle activities. Two NN were developed and investigated, namely feedforward neural network (FNN) and long short-term memory neural network (LSTM). The results show that, although both networks were able to predict muscle activities well, LSTM outperformed the conventional FNN. This study confirms the feasibility of estimating muscle activity using IMU data and NN. It also indicates the possibility of this method enabling the gait analysis to be performed outside the laboratory environment with a limited number of devices.

Abstract

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.

Abstract

Gait analysis is the study of human locomotion. It plays an essential role in the diagnosis and rehabilitation of gait abnormalities, the study of physiological changes associated with ageing, and the treatment of injuries. Muscle activity is an important gait parameter that controls joint function during walking and provides valuable information about the gait quality. However, current techniques to measure muscle activity, such as electromyogram (EMG) and musculoskeletal modelling tools, have drawbacks. This study develops an artificial neural network (ANN) method to estimate eight lower extremity muscle activities using pelvis, hip, knee and ankle joint angles. It uses an online gait database that contains kinematic and kinetic gait parameters and lower limb EMG. Four training algorithms were explored and investigated. Despite the noticeable differences between the actual and the estimated muscle activities, e.g. gluteus maximus and bicep femoris, the results demonstrate the feasibility of the proposed method in determining the muscle behaviour during walking. The study also shows the potentials of machine learning to compensate for the lack of modality and to provide an insight on the dynamics of muscles in gait. Clinical Relevance- Gait analysis is important in clinical and rehabilitation settings. The proposed method has the potential in reducing the dependency on EMGs and can be an alternative to the musculoskeletal modelling tools in diagnosing, treating, and rehabilitating gait abnormalities.