Electronic Thesis and Dissertation Repository

Thesis Format



Master of Engineering Science


Biomedical Engineering


Ana Luisa Trejos


Musculoskeletal injuries can severely impact the ability to produce and control body motion. In order to regain function, rehabilitation is often required. Wearable smart devices are currently under development to provide therapy and assistance for people with impaired arm function. Electromyography (EMG) signals are used as an input to pattern recognition systems to determine intended movements.

However, there is a gap between the accuracy of pattern recognition systems in constrained laboratory settings, and usability when used for detecting dynamic unconstrained movements. Motion factors such as limb position, interaction force, and velocity, are known to have a negative impact on the pattern recognition. A possible solution lies in the use of data from other sensors along with the EMG signals, such as signals from accelerometers (ACC), in the training and use of classifiers in order to improve classification accuracy.

The objectives of this study were to quantify the impact of motion factors on ACC signals, and to use these ACC signals along with EMG signals for classifying categories of motion factors. To address these objectives, a dataset containing EMG and ACC signals while individuals performed unconstrained arm motions was studied. Analyses of the EMG and accelerometer signals and their use in training classification models to predict characteristics of intended motion were completed.

The results quantify how accelerometer features change with variations in arm position, interaction forces, and motion velocities. The results also show that the combination of EMG and ACC data have relatively increased the accuracy of motion intention detection. Velocity could be distinguished between stationary and moving with less than 10% error using a Decision Tree ensemble classifier.

Future work should expand on motion factors and EMG-ACC sensor fusion to identify interactions between a person and the environment, in order to guide tuning of control models working towards controlling wearable mechatronic devices during dynamic movements.

Summary for Lay Audience

Injuries to the bones, muscles and/or connective tissues of the body can severely limit the ability to perform daily life activities, such as dressing or pouring water into a glass. Rehabilitation is often required to recover from these injuries. Technology has been under development to provide solutions that help with the treatment. Wearable robotic devices offer a potential tool for providing physical therapy to the arm without the need of going to the clinic. These devices are controlled by measuring the electrical signals of the muscles in order to predict the subject’s intention to move the arm. However, these devices suffer from the limitation of not performing well when used during complex movements. Several factors, including the speed of the movement and external forces (for example, the increased weight when carrying a bag) decrease the capability to predict movement intention. One important suggestion is to incorporate signals from other sensors, such as accelerometers (devices that measure acceleration), that may provide additional information for the prediction. This work provides an analysis of accelerometer signals obtained during complex arm movements and demonstrates an increased prediction rate when using both muscle activity and acceleration information to predict arm movement intention. Motion intention could be distinguished between stationary and moving during arm movement with less than 10% error. This could be used to further improve the control of a wearable robotic device.