Decoding the grasping intention from electromyography during reaching motions

Batzianoulis, Iason; Krausz, Nili E.; Simon, Ann M.; Hargrove, Levi J.; Billard, Aude

doi:10.1186/s12984-018-0396-5

Cited by 55 publications

(55 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once they had executed the desired grip, they were required to perform a dynamic movement, thus covering with their (residual) arm the region of interest. This approach was followed because it has been previously shown that it can help alleviate the limb position effect [31] and improve decoding performance [14], [15]. One of the amputee participants performed bilateral mirrored movements as they found it was easier in that way to perform phantom limb muscle activations.…”

Section: Behavioural Taskmentioning

confidence: 99%

Multi-Grip Classification-Based Prosthesis Control With Two EMG-IMU Sensors

Krasoulis

Vijayakumar

Nazarpour

2020

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

In the field of upper-limb myoelectric prosthesis control, the use of statistical and machine learning methods has been long proposed as a means of enabling intuitive grip selection and actuation. Recently, this paradigm has found its way toward commercial adoption. Machine learning-based prosthesis control typically relies on the use of a large number of electrodes. Here, we propose an end-to-end strategy for multi-grip, classificationbased prosthesis control using only two sensors, comprising electromyography (EMG) electrodes and inertial measurement units (IMUs). We emphasize the importance of accurately estimating posterior class probabilities and rejecting predictions made with low confidence, so as to minimize the rate of unintended prosthesis activations. To that end, we propose a confidence-based error rejection strategy using grip-specific thresholds. We evaluate the efficacy of the proposed system with real-time pick and place experiments using a commercial multi-articulated prosthetic hand and involving 12 able-bodied and two transradial (i.e., below-elbow) amputee participants. Results promise the potential for deploying intuitive, classificationbased multi-grip control in existing upper-limb prosthetic systems subject to small modifications.

show abstract

Section: Behavioural Taskmentioning

confidence: 99%

Multi-Grip Classification-Based Prosthesis Control With Two EMG-IMU Sensors

Krasoulis

Vijayakumar

Nazarpour

2020

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…Dynamic 3D space experiments involve the transition between shoulder, elbow, and wrist joint angles while eliciting a target motion class [22,[143][144][145][146][147][148]. Generally, these protocols can be grouped into two subsets: reach-to-grasp, and activities of daily living (ADLs).…”

Section: Dynamic 3d Spacementioning

confidence: 99%

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

Campbell

Phinyomark

Scheme

2020

Sensors

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

“…The further development of assistive and training devices for persons with impaired hand function will probably also include other command systems than those used in the current version of the SEM Glove. Electromyography is already used in some exoskeletons, in refined prostheses for amputees, and in the development of a soft orthosis (42,43), and brainmachine interfaces may open new opportunities.…”

Section: "Well Yes It´s the Fine Hand Use That's My Problem But Itmentioning

confidence: 99%

Factors affecting the usability of an assistive soft robotic glove after stroke or multiple sclerosis

Palmcrantz¹,

Plantin²,

Borg³

2020

J Rehabil Med

View full text Add to dashboard Cite

To explore factors impacting on the usability of an assistive soft robotic glove in the home setting after stroke or multiple sclerosis. Twenty participants living with the effects of stroke or multiple sclerosis used the assistive glove in the home for 6 weeks. Perceived usability was reported in weekly telephone interviews and one semistructured interview. Functioning was clinically assessed. Perceived beneficial effects were a sustained and strong grip. Reported disadvantages were a lack of assistance in opening the hand, lack of wrist support, and the glove not being usable for fine hand use. The glove was found to be useful mainly by participants with moderate limitations in hand activity and an overall level of functioning that allowed participation in everyday life activities. This study identified a subgroup of participants, who found the glove useful in activities requiring a strong and prolonged grip but not for fine hand use, and highlights aspects for consideration in the further development of soft hand robotics for sustained use in a larger population living with a central nervous system lesion. Objective: To explore the usability and effects of an assistive soft robotic glove in the home setting after stroke or multiple sclerosis. Design: A mixed methods design. Methods: Participants with stroke (n = 10) or multiple sclerosis (n = 10) were clinically assessed, and instructed to use the glove in activities of daily living for 6 weeks. They reported their experience of using the glove via weekly telephone interviews and one semi-structured interview. Results: The soft robotic glove was used by participants in a wide variety of activities of daily living. Perceived beneficial effects while using the glove were a sustained and a strong grip. Disadvantages of using the glove were a lack of assistance in hand opening function and the glove not being usable for fine hand use. The glove was found to be useful by two-thirds of participants who completed the study, mainly by participants with moderate limitations in hand activity and an overall level of functioning that allowed participation in everyday life activities. Conclusion: This study identified a subgroup of participants, who found the glove useful in activities requiring a strong and prolonged grip but not fine hand use, and highlights aspects for consideration in the further development of soft hand robotics for sustained use in a larger population living with a central nervous system lesion.

show abstract

Decoding the grasping intention from electromyography during reaching motions

Cited by 55 publications

References 48 publications

Multi-Grip Classification-Based Prosthesis Control With Two EMG-IMU Sensors

Multi-Grip Classification-Based Prosthesis Control With Two EMG-IMU Sensors

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

Factors affecting the usability of an assistive soft robotic glove after stroke or multiple sclerosis

Contact Info

Product

Resources

About