scholarly journals Directional Forgetting for Stable Co-Adaptation in Myoelectric Control

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2203 ◽  
Author(s):  
Dennis Yeung ◽  
Dario Farina ◽  
Ivan Vujaklija
Keyword(s):  
Myoelectric Control ◽  
Training Data ◽  
Recursive Least Squares ◽  
Forgetting Factor ◽  
Improve Performance ◽  
User Training ◽  
Satisfactory Performance ◽  
Concurrent User ◽  
User Learning ◽  
Electromyographic Signals

Conventional myoelectric controllers provide a mapping between electromyographic signals and prosthetic functions. However, due to a number of instabilities continuously challenging this process, an initial mapping may require an extended calibration phase with long periods of user-training in order to ensure satisfactory performance. Recently, studies on co-adaptation have highlighted the benefits of concurrent user learning and machine adaptation where systems can cope with deficiencies in the initial model by learning from newly acquired data. However, the success remains highly dependent on careful weighting of these new data. In this study, we proposed a function driven directional forgetting approach to the recursive least-squares algorithm as opposed to the classic exponential forgetting scheme. By only discounting past information in the same direction of the new data, local corrections to the mapping would induce less distortion to other regions. To validate the approach, subjects performed a set of real-time myoelectric tasks over a range of forgetting factors. Results show that directional forgetting with a forgetting factor of 0.995 outperformed exponential forgetting as well as unassisted user learning. Moreover, myoelectric control remained stable after adaptation with directional forgetting over a range of forgetting factors. These results indicate that a directional approach to discounting past training data can improve performance and alleviate sensitivities to parameter selection in recursive adaptation algorithms.

scholarly journals Long-Term BCI Training of a Tetraplegic User: Adaptive Riemannian Classifiers and User Training

2021 ◽  
Vol 15 ◽  
Author(s):  
Camille Benaroch ◽  
Khadijeh Sadatnejad ◽  
Aline Roc ◽  
Aurélien Appriou ◽  
Thibaut Monseigne ◽  
...  
Keyword(s):  
Video Game ◽  
Real Life ◽  
Assistive Technologies ◽  
Training Data ◽  
Future Research ◽  
Left Hand ◽  
User Training ◽  
Initial Sessions ◽  
User Learning

While often presented as promising assistive technologies for motor-impaired users, electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) remain barely used outside laboratories due to low reliability in real-life conditions. There is thus a need to design long-term reliable BCIs that can be used outside-of-the-lab by end-users, e.g., severely motor-impaired ones. Therefore, we propose and evaluate the design of a multi-class Mental Task (MT)-based BCI for longitudinal training (20 sessions over 3 months) of a tetraplegic user for the CYBATHLON BCI series 2019. In this BCI championship, tetraplegic pilots are mentally driving a virtual car in a racing video game. We aimed at combining a progressive user MT-BCI training with a newly designed machine learning pipeline based on adaptive Riemannian classifiers shown to be promising for real-life applications. We followed a two step training process: the first 11 sessions served to train the user to control a 2-class MT-BCI by performing either two cognitive tasks (REST and MENTAL SUBTRACTION) or two motor-imagery tasks (LEFT-HAND and RIGHT-HAND). The second training step (9 remaining sessions) applied an adaptive, session-independent Riemannian classifier that combined all 4 MT classes used before. Moreover, as our Riemannian classifier was incrementally updated in an unsupervised way it would capture both within and between-session non-stationarity. Experimental evidences confirm the effectiveness of this approach. Namely, the classification accuracy improved by about 30% at the end of the training compared to initial sessions. We also studied the neural correlates of this performance improvement. Using a newly proposed BCI user learning metric, we could show our user learned to improve his BCI control by producing EEG signals matching increasingly more the BCI classifier training data distribution, rather than by improving his EEG class discrimination. However, the resulting improvement was effective only on synchronous (cue-based) BCI and it did not translate into improved CYBATHLON BCI game performances. For the sake of overcoming this in the future, we unveil possible reasons for these limited gaming performances and identify a number of promising future research directions. Importantly, we also report on the evolution of the user's neurophysiological patterns and user experience throughout the BCI training and competition.

scholarly journals Deep Cross-User Models Reduce the Training Burden in Myoelectric Control

2021 ◽  
Vol 15 ◽  
Author(s):  
Evan Campbell ◽  
Angkoon Phinyomark ◽  
Erik Scheme
Keyword(s):  
Pattern Recognition ◽  
Computation Time ◽  
Myoelectric Control ◽  
Training Data ◽  
User Models ◽  
User Training ◽  
Pattern Recognition Systems ◽  
Previous State ◽  
Commercial Applications ◽  
Training Protocol

The effort, focus, and time to collect data and train EMG pattern recognition systems is one of the largest barriers to their widespread adoption in commercial applications. In addition to multiple repetitions of motions, including exemplars of confounding factors during the training protocol has been shown to be critical for robust machine learning models. This added training burden is prohibitive for most regular use cases, so cross-user models have been proposed that could leverage inter-repetition variability supplied by other users. Existing cross-user models have not yet achieved performance levels sufficient for commercialization and require users to closely adhere to a training protocol that is impractical without expert guidance. In this work, we extend a previously reported adaptive domain adversarial neural network (ADANN) to a cross-subject framework that requires very little training data from the end-user. We compare its performance to single-repetition within-user training and the previous state-of-the-art cross-subject technique, canonical correlation analysis (CCA). ADANN significantly outperformed CCA for both intact-limb (86.8–96.2%) and amputee (64.1–84.2%) populations. Moreover, the ADANN adaptation computation time was substantially lower than the time otherwise devoted to conducting a full within-subject training protocol. This study shows that cross-user models, enabled by deep-learned adaptations, may be a viable option for improved generalized pattern recognition-based myoelectric control.

Sign in / Sign up

Export Citation Format

Share Document