A Non-invasive Brain Computer Interface Decoder for Gait

Date

2020-05

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Brain Computer Interface (BCI) systems enable control of machines and computers using signals extracted from the brain, such as data recorded using electroencephalography (EEG). Naturally, this technology is expected to help people with disabilities, such as lost speech or motor impairment, by providing an alternative approach to interact with the world. Being able to walk is one of the most fundamental human functions, and BCIs could help those with walking impairment by providing direct control of an exoskeleton directly from brain signals. The most crucial part of building such a system is the neural decoding–i.e., the specific algorithm that trans- lates neural signals into movement signals. Developing an effective neural decoding model does not only provide accurate control of the device, but could also open a new path towards understanding the neural representation of gait. A wide variety of algorithms have been proposed for neural decodings, such as linear regression, kalman filters, and artificial neural networks. However, there is a lack of rigorous comparisons of different decoding models and parameter choices. Furthermore, it is unclear how well each of these models will generalize to new data from either new environments or different subjects. This dissertation thesis aims to investigate those issues by: 1) Benchmarking the proposed models and understanding the representation of the brain during gait and 2) Study ways to generalize the model. In the first specific aim, we showed that neural networks not only performed better than conventional methods when trained within a specific walking environment, but resulted in models that were robust to external disturbances such as channel distortion. In the second aim, we showed intra- subject decoding works in all the combinations (e.g., inter-subject decoding of different terrains, level ground walking only, treadmill walking, etc.), but inter- subject decoding only works for electromyography (EMG) to kinematics decoding. To deal with this problem, several methods were used to improve inter- subject decoding. Of these methods, transfer learning achieved the most promising results. The work in this dissertation contributes to a greater understanding of the decoding models and their performance/generalizability on non-invasive gait decoding.

Description

Keywords

EEG, Brain Computer Interface, Gait

Citation

Portions of this document appear in: S. Nakagome, T. P. Luu, Y. He, A. S. Ravindran, and J. L. Contreras-Vidal, “An empirical comparison of neural networks and machine learning algorithms for eeg gait decoding,” Scientific Reports, vol. 10, no. 1, pp. 1–17, 2020. And in: T. P. Luu, J. A. Brantley, S. Nakagome, F. Zhu, and J. L. Contreras-Vidal, “Electrocortical correlates of human level-ground, slope, and stair walking,” PLoS ONE, vol. 12, no. 11, 2017. And in: T. P. Luu, Y. He, S. Nakagome, K. Nathan, S. Brown, J. Gorges, and J. L. Contreras-Vidal, “Multi-trial gait adaptation of healthy individuals during visual kinematic perturbations,” Frontiers in Human Neuroscience, vol. 11, 2017. And in: T. P. Luu, S. Nakagome, Y. He, and J. L. Contreras-Vidal, “Real-time EEG-based brain-computer interface to a virtual avatar enhances cortical involvement in human treadmill walking,” Scientific Reports, vol. 7, no. 1, 2017. And in: T. P. Luu, Y. He, S. Brown, S. Nakagome, and J. L. Contreras-Vidal, “A closed-loop brain computer interface to a virtual reality avatar: Gait adaptation to visual kinematic perturbations,” in International Conference on Virtual Rehabilitation, ICVR, pp. 30–37, 2015. And in: Y. He, T. P. Luu, K. Nathan, S. Nakagome, and J. L. Contreras-Vidal, “A mobile brain-body imaging dataset recorded during treadmill walking with a brain-computer interface,” Scientific data, vol. 5, 2018. And in: J. A. Brantley, T. P. Luu, S. Nakagome, F. Zhu, and J. L. Contreras-Vidal, “Full body mobile brain-body imaging data during unconstrained locomotion on stairs, ramps, and level ground,” Scientific data, vol. 5, p. 180133, 2018. And in: S. Nakagome, T. P. Luu, J. A. Brantley, and J. L. Contreras-Vidal, “Prediction of EMG envelopes of multiple terrains over-ground walking from EEG signals using an Unscented Kalman Filter,” in 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017, vol. 2017-Janua, pp. 3175–3178, 2017. And in: J. A. Brantley, T. P. Luu, S. Nakagome, and J. L. Contreras-Vidal, “Prediction of lower-limb joint kinematics from surface EMG during overground locomotion,” in 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017, vol. 2017-Janua, pp. 1705–1709, 2017.