Myoelectric feature extraction using temporal-spatial descriptors for multifunction prosthetic hand control

Khushaba, Rami N.; Al-Timemy, Ali H.; Al-Ani, Ahmed; Al-Jumaily, Adel

doi:10.1109/embc.2016.7591042

Cited by 11 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond these, the TSD set proposed by Khushaba et al [16] involves the extraction of TDD features estimating the signal's power spectrum. TDD features are extracted from each EMG channel, as well as the differences between each channel, representing how muscles' relationships change over time [14].…”

Section: A Feature Selection and Extractionmentioning

confidence: 99%

“…It is the concatenation of the correlation coefficients computed from the TDD features which forms the TSD set. These were computed with reference to the methods outlined by Khushaba et al [16].…”

Section: A Feature Selection and Extractionmentioning

confidence: 99%

“…With PCA, the data is projected onto orthogonal vectors within a new coordinate frame using eigenvector decomposition where successive components maximize variance, allowing one to explain the majority of the data's variance in a reduced number of dimensions [19]. One alternative technique is Spectral Regression (SR) [20], [21], whose potential has been shown by Khushaba et al when applied to the TSD set [16]. In contrast to PCA, SR's computation does not involve the eigen-decomposition of the feature matrix, instead decomposing the subspace learning into two-steps: graph embedding for response learning and regression for projective function learning [20].…”

Section: Dimensionality Reductionmentioning

confidence: 99%

See 2 more Smart Citations

An Exploration of the Optimal Feature-Classifier Combinations for Transradial Prosthesis Control

Douglas

Gover

Docherty

et al. 2022

2022 44th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

Within state-of-the-art gesture-based upper-limb myoelectric prosthesis control, gesture recognition commonly relies on the classification of features extracted from electromygraphic (EMG) data gathered from the amputee's residual forearm musculature. Despite best efforts in broadly maximizing gesture recognition accuracy, there does not yet exist a feature-classifier combination accepted as best-practice. In turn, this work hypothesizes that no single feature-classifier combination can consistently maximize accuracy across subjects, positing instead that control schemes should be personalized to the individual. To investigate this hypothesis, the study employed the 40-subject, 49gesture Ninapro DB2 to compare the performance of 7 different historic, more recent and state-of-the-art feature sets, in combination with 5 machine learning classifiers commonly seen within EMG-based pattern recognition literature. The results demonstrate the ability of Linear Discriminant Analysis (LDA) to marginally exceed other more computationally intensive classifiers in terms of mean accuracy, while the feature set which maximized the highest proportion of individuals' accuracies was shown to vary with both classifier choice and gesture count.

show abstract

Section: A Feature Selection and Extractionmentioning

confidence: 99%

Section: A Feature Selection and Extractionmentioning

confidence: 99%

Section: Dimensionality Reductionmentioning

confidence: 99%

See 1 more Smart Citation

An Exploration of the Optimal Feature-Classifier Combinations for Transradial Prosthesis Control

Douglas

Gover

Docherty

et al. 2022

2022 44th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

show abstract

“…Commonly applied pattern recognition methods in myocontrol often show disadvantages in terms of generalizability, intuitive control and robustness regarding "electrodes shift, varying force levels" [50] (e. g. overshooting) and others. To cope with these limitations, an extended kNN learning scheme seemed promising due to its simplicity, incrementality and good results in exemplary tests.…”

Section: Introductionmentioning

confidence: 99%

Prototype Reduction on sEMG Data for Instance-based Gesture Learning towards Real-time Prosthetic Control

Sziburis

Nowak

Brunelli

2021

Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies

View full text Add to dashboard Cite

This work presents the design, implementation and validation of learning techniques based on the kNN scheme for gesture detection in prosthetic control. To cope with high computational demands in instance-based prediction, methods of dataset reduction are evaluated considering real-time determinism to allow for the reliable integration into battery-powered portable devices.The influence of parameterization and varying proportionality schemes is analyzed, utilizing an eight-channel-sEMG armband. Besides offline cross-validation accuracy, success rates in real-time pilot experiments (online target achievement tests) are determined.Based on the assessment of specific dataset reduction techniques' adequacy for embedded control applications regarding accuracy and timing behaviour, Decision Surface Mapping (DSM) proves itself promising when applying kNN on the reduced set.A randomized, double-blind user study was conducted to evaluate the respective methods (kNN and kNN with DSM-reduction) against Ridge Regression (RR) and RR with Random Fourier Features (RR-RFF). The kNN-based methods performed significantly better (𝑝 < 0.0005) than the regression techniques. Between DSM-kNN and kNN, there was no statistically significant difference (significance level 0.05). This is remarkable in consideration of only one sample per class in the reduced set, thus yielding a reduction rate of over 99% while preserving success rate. The same behaviour could be confirmed in an extended user study.With 𝑘 = 1, which turned out to be an excellent choice, the runtime complexity of both kNN (in every prediction step) as well as DSM-kNN (in the training phase) becomes

show abstract

High Accuracy Multi-channel Surface EMG Acquisition System for Prosthetic Devices Control

Proaño-Guevara

Serpa-Andrade

2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Myoelectric feature extraction using temporal-spatial descriptors for multifunction prosthetic hand control

Cited by 11 publications

References 15 publications

An Exploration of the Optimal Feature-Classifier Combinations for Transradial Prosthesis Control

An Exploration of the Optimal Feature-Classifier Combinations for Transradial Prosthesis Control

Prototype Reduction on sEMG Data for Instance-based Gesture Learning towards Real-time Prosthetic Control

High Accuracy Multi-channel Surface EMG Acquisition System for Prosthetic Devices Control

Contact Info

Product

Resources

About