Linear Discriminant Analysis with Bayesian Risk Parameters for Myoelectric Control

Campbell, Evan; Phinyomark, Angkoon; Scheme, Erik

doi:10.1109/globalsip45357.2019.8969237

Cited by 20 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More commonly, overlapping window segmentation is used to increase the density of the decision stream by incrementing neighboring windows by a duration shorter than the window length, resulting in neighboring windows sharing common elements. When smaller increments are used, post-processing techniques can more readily be leveraged to improve the control outputs [42][43][44][45][46][47].…”

Section: Data Segmentationmentioning

confidence: 99%

“…Lorrain et al [118] also determined that an LDA classifier was the best candidate using the TDAR feature set for motion recognition in the presence of confounding factors with more than 6% improvement when factor-specific variability was introduced to the training set. This is likely because the use of a common (pooled) covariance promotes more general decision boundaries than other discriminative classifiers [42]. Conversely, the SVM classifier is known to perform well with the wavelet feature set [41,118], likely because it explicitly integrates structural risk minimization.…”

Section: Investigating the Limb Position Effectmentioning

confidence: 99%

See 1 more Smart Citation

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

Campbell

Phinyomark

Scheme

2020

Sensors

Self Cite

View full text Add to dashboard Cite

This manuscript presents a hybrid study of a comprehensive review and a systematic (research) analysis. Myoelectric control is the cornerstone of many assistive technologies used in clinical practice, such as prosthetics and orthoses, and human-computer interaction, such as virtual reality control. Although the classification accuracy of such devices exceeds 90% in a controlled laboratory setting, myoelectric devices still face challenges in robustness to variability of daily living conditions. The intrinsic physiological mechanisms limiting practical implementations of myoelectric devices were explored: the limb position effect and the contraction intensity effect. The degradation of electromyography (EMG) pattern recognition in the presence of these factors was demonstrated on six datasets, where classification performance was 13% and 20% lower than the controlled setting for the limb position and contraction intensity effect, respectively. The experimental designs of limb position and contraction intensity literature were surveyed. Current state-of-the-art training strategies and robust algorithms for both effects were compiled and presented. Recommendations for future limb position effect studies include: the collection protocol providing exemplars of at least 6 positions (four limb positions and three forearm orientations), three-dimensional space experimental designs, transfer learning approaches, and multi-modal sensor configurations. Recommendations for future contraction intensity effect studies include: the collection of dynamic contractions, nonlinear complexity features, and proportional control.

show abstract

Section: Data Segmentationmentioning

confidence: 99%

Section: Investigating the Limb Position Effectmentioning

confidence: 99%

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

Campbell

Phinyomark

Scheme

2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Data Segmentationmentioning

confidence: 99%

“…Lorrain et al [123] also determined that an LDA classifier was the best candidate using the TDAR feature set for motion recognition in the presence of confounding factors with more than 6% improvement when factor-specific variability was introduced to the training set. This is likely because the use of a common (pooled) covariance promotes more general decision boundaries than other non-parametric and/or discriminative classifiers [38]. Conversely, the SVM classifier is known to perform well with the wavelet feature set [37,123], likely because it explicitly integrates structural risk minimization.…”

Section: Investigating the Limb Position Effectmentioning

confidence: 99%

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

Campbell

Phinyomark

Scheme

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Myoelectric control is the cornerstone of many assistive technologies used in clinical practice, such as prosthetics and orthoses, and human-computer interaction, such as virtual reality control. Although the performance of such devices exceeds 90\% in controlled environments, myoelectric devices still face challenges in robustness to variability of daily living conditions. Within this survey, the intrisic physiological mechanisms limiting practical implementations of myoelectric devices were explored: the limb position effect and the contraction intensity effect. The degradation of electromyography (EMG) pattern recognition in the presence of these factors was demonstrated on six datasets, where performance was 13% and 20% lower in realistic environments compared to controlled environments for the limb position and contraction intensity effect, respectively. The experimental designs of limb position and contraction intensity literature were surveyed. Current state-of-the-art training strategies and robust algorithms for both effects were compiled and presented. Recommendations for future limb position effect studies include: the collection protocol providing exemplars of 6 positions (four limb positions and three forearm orientations), three-dimensional space experimental designs, transfer learning approaches, and multi-modal sensor configurations. Recommendations for future contraction intensity effect studies include: the collection of dynamic contractions, nonlinear complexity features, and proportional control.

show abstract

“…A linear discriminant analysis (LDA) classifier was adopted to classify these handcrafted feature sets due to its extensive use in EMG pattern recognition literature and low computational complexity (Campbell et al, 2019b ; Leone et al, 2019 ).…”

Section: Methodsmentioning

confidence: 99%

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

2021

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Linear Discriminant Analysis with Bayesian Risk Parameters for Myoelectric Control

Cited by 20 publications

References 23 publications

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

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

Contact Info

Product

Resources

About