Analyzing the impact of class transitions on the design of pattern recognition-based myoelectric control schemes

Raghu, Shriram Tallam Puranam; MacIsaac, Dawn; Scheme, Erik

doi:10.1016/j.bspc.2021.103134

Cited by 5 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although LDA was the most promising baseline classifier, in line with findings from our previous study [13], it does not benefit as much from the rejection schemes, particularly DCIR and VoCIR, as compared to the LSTM and SVM. This can be attributed to the significant overlap in confidence value distributions of the LDA corresponding to the different types of decisions (correct, incorrect, and transitions).…”

Section: Discussionsupporting

confidence: 79%

“…The data collection protocol used in this study was similar to the one used in our previous work, with some added elements [13]. Each training record included a set of 6 ramp contractions starting from a neutral position and ending with a 3 s steady state contraction in Wrist Flexion (WF), Wrist Extension (WE), Wrist Pronation (WP), Wrist Supination (WS), Chuck Grip (CG), or Hand Open (HO).…”

Section: B Training and Testing Protocolmentioning

confidence: 99%

“…In a previous study [13], we highlighted that the lack of correlation between offline accuracy and usability may be due to the controlled conditions for offline tests, which do not represent the real-world device usage [14]. Most offline studies collect a set of separate motions (steady-state or ramp contractions) that are used to train and then test the sEMG-PR algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…Instability (INS) along with 6 transition region metrics -Offset Delay (T OF F SET ), Onset Delay (T ON SET ), Transition Duration (T T RAN SIT ION ), Instability (INS), Tertiary Class Error (TCE), and Percent No Movement (PNM), as described in our previous work[13]. To calculate the transition metrics, it was necessary to identify when each classifier moved in and out of steady-states.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Decision-Change Informed Rejection Improves Robustness in Pattern Recognition-Based Myoelectric Control

Raghu,

MacIsaac,

Scheme

2023

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Post-processing techniques have been shown to improve the quality of the decision stream generated by classifiers used in pattern-recognition-based myoelectric control. However, these techniques have largely been tested individually and on well-behaved, stationary data, failing to fully evaluate their trade-offs between smoothing and latency during dynamic use. Correspondingly, in this work, we survey and compare 8 different post-processing and decision stream improvement schemes in the context of continuous and dynamic class transitions: majority vote, Bayesian fusion, onset locking, outlier detection, confidence-based rejection, confidence scaling, prior adjustment, and adaptive windowing. We then propose two new temporally aware post-processing schemes that use changes in the decision and confidence streams to better reject uncertain decisions. Our decision-change informed rejection (DCIR) approach outperforms existing schemes during both steady-state and transitions based on error rates and decision stream volatility whether using a LDA or SVM classifier, or a deep LSTM model. These results suggest that added robustness can be gained by appropriately leveraging temporal context in myoelectric control.

show abstract

Section: Discussionsupporting

confidence: 79%

Section: B Training and Testing Protocolmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Decision-Change Informed Rejection Improves Robustness in Pattern Recognition-Based Myoelectric Control

Raghu,

MacIsaac,

Scheme

2023

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Within this paradigm, algorithms are typically trained to predict steady-state static contractions, whereby the underlying EMG of the gesture is not intentionally changing over time. With some exceptions [28], the signal is generally assumed to be stationary and any transient periods are not specifically modeled [26,29]. Due to the prevalence and the original emergence of EMG research for prosthesis control, most gesture recognition research, including confounding factors research, continues to focus on improving these systems [1].…”

Section: Continuous Controlmentioning

confidence: 99%

Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition

Eddy,

Campbell,

Bateman

et al. 2024

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Discrete myoelectric control-based gesture recognition has recently gained interest as a possible input modality for many emerging ubiquitous computing applications. Unlike the continuous control commonly employed in powered prostheses, discrete systems seek to recognize the dynamic sequences associated with gestures to generate event-based inputs. More akin to those used in general-purpose human-computer interaction, these could include, for example, a flick of the wrist to dismiss a phone call or a double tap of the index finger and thumb to silence an alarm. Moelectric control systems have been shown to achieve near-perfect classification accuracy, but in highly constrained offline settings. Real-world, online systems are subject to ``confounding factors'' (i.e., factors that hinder the real-world robustness of myoelectric control that are not accounted for during typical offline analyses), which inevitably degrade system performance, limiting their practical use. Although these factors have been widely studied in continuous prosthesis control, there has been little exploration of their impacts on discrete myoelectric control systems for emerging applications and use cases. Correspondingly, this work examines, for the first time, three confounding factors and their effect on the robustness of discrete myoelectric control: (1) limb position variability, (2) cross-day use, and a newly identified confound faced by discrete systems (3) gesture elicitation speed. Results from four different discrete myoelectric control architectures: (1) Majority Vote LDA, (2) Dynamic Time Warping, (3) an LSTM network trained with Cross Entropy, and (4) an LSTM network trained with Contrastive Learning, show that classification accuracy is significantly degraded (p<0.05) as a result of each of these confounds. This work establishes that confounding factors are a critical barrier that must be addressed to enable the real-world adoption of discrete myoelectric control for robust and reliable gesture recognition.

show abstract

Comparing online wrist and forearm EMG-based control using a rhythm game-inspired evaluation environment

Meredith,

Eddy,

Bateman

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective. The use of electromyogram (EMG) signals recorded from the wrist is emerging as a desirable input modality for human-machine interaction (HMI). Although forearm-based EMG has been used for decades in prosthetics, there has been comparatively little prior work evaluating the performance of wrist-based control, especially in online, user-in-the-loop studies. Furthermore, despite different motivating use cases for wrist-based control, research has mostly adopted legacy prosthesis control evaluation frameworks. Approach. Gaining inspiration from rhythm games and the Schmidt's law speed-accuracy tradeoff, this work proposes a new temporally constrained evaluation environment with a linearly increasing difficulty to compare the online usability of wrist and forearm EMG. Compared to the more commonly used Fitts' Law-style testing, the proposed environment may offer different insights for emerging use cases of EMG as it decouples the machine learning algorithm's performance from proportional control, is easily generalizable to different gesture sets, and enables the extraction of a wide set of usability metrics that describe a users ability to successfully accomplish a task at a certain time with different levels of induced stress. Main Results. The results suggest that wrist EMG-based control is comparable to that of forearm EMG when using traditional prosthesis control gestures and can even be better when using fine finger gestures. Additionally, the results suggest that as the difficulty of the environment increased, the online metrics and their correlation to the offline metrics decreased, highlighting the importance of evaluating myoelectric control in real-time evaluations over a range of difficulties. Significance. This work provides valuable insights into the future design and evaluation of myoelectric control systems for emerging HMI applications.

show abstract

Analyzing the impact of class transitions on the design of pattern recognition-based myoelectric control schemes

Cited by 5 publications

References 37 publications

Decision-Change Informed Rejection Improves Robustness in Pattern Recognition-Based Myoelectric Control

Decision-Change Informed Rejection Improves Robustness in Pattern Recognition-Based Myoelectric Control

Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition

Comparing online wrist and forearm EMG-based control using a rhythm game-inspired evaluation environment

Contact Info

Product

Resources

About