Tracking human hand motions has raised more attention due to the recent advancements of virtual reality (Rheingold, 1991) and prosthesis control (Antfolk et al., 2010). Surface electromyography (sEMG) has been the predominant method for sensing electrical activity in biomechanical studies, and has also been applied to motion tracking in recent years. While most studies focus on the classification of human hand motions within a predefined motion set, the prediction of continuous finger joint angles and wrist angles remains a challenging endeavor. In this research, a biomechanical knowledge-driven data fusion strategy is proposed to predict finger joint angles and wrist angles. This strategy combines time series data of sEMG signals and simulated muscle features, which can be extracted from a biomechanical model available in OpenSim (Delp et al., 2007). A support vector regression (SVR) model is used to firstly predict muscle features from sEMG signals and then to predict joint angles from the estimated muscle features. A set of motion data containing 10 types of motions from 12 participants was collected from an institutional review board approved experiment. A hypothesis was tested to validate whether adding the simulated muscle features would significantly improve the prediction performance. The study indicates that the biomechanical knowledge-driven data fusion strategy will improve the prediction of new types of human hand motions. The results indicate that the proposed strategy significantly outperforms the benchmark date-driven model especially when the users were performing unknown types of motions from the model training stage. The proposed model provides a possible approach to integrate the simulation models and data fusion models in human factors and ergonomics. / Master of Science / Hand motion tracking is a promising technique for the development of virtual reality and prosthesis. Identifying hand motions based on sensor data is the fundamental step to realize motion tracking. Among all the tracking techniques, surface electromyography (sEMG) is a type of electrical signals that has been proven useful in predicting hand motions in recent years, since sEMG signals can directly reflect muscle activities, and hand motions are controlled by muscle groups. While most studies focus on the classification of human hand motions within a predefined motion set, the prediction of continuous finger joint angles and wrist angles remains a challenging endeavor. In this research, a biomechanical knowledge-driven data fusion strategy was proposed to predict finger joint angles and wrist angles. More specifically, this strategy combined a statistical model with a biomechanical simulation model, and a hypothesis was tested to validate whether adding the biomechanical simulation model would significantly improve the prediction performance. A set of sEMG signals containing 10 types of motions from 12 participants was collected from an institutional review board approved experiment, in order to test the proposed strategy. The results indicate that the proposed strategy significantly outperforms the benchmark statistical models especially when users were performing unknown types of motions from the model training stage. The proposed strategy provides a possible approach to integrate the simulation models and data-driven models in human factors and ergonomics.
| Identifer | oai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/78289 |
| Date | 29 June 2017 |
| Creators | Wang, Anqi |
| Contributors | Industrial and Systems Engineering, Jin, Ran, Ellis, Kimberly P., Nussbaum, Maury A. |
| Publisher | Virginia Tech |
| Source Sets | Virginia Tech Theses and Dissertation |
| Detected Language | English |
| Type | Thesis |
| Format | ETD, application/pdf, application/pdf |
| Rights | In Copyright, http://rightsstatements.org/vocab/InC/1.0/ |
Page generated in 0.002 seconds