Determining the optimal window length for pattern recognition-based myoelectric control: balancing the competing effects of classification error and controller delay
By L. Smith, Levi J. Hargrove, Blair A. Lock, Todd A. Kuiken. IEEE transactions on neural systems and rehabilitation engineering, 2010
432 citations recorded by the source corpus.
Pattern recognition-based control of myoelectric prostheses has shown great promise in research environments, but has not been optimized for use in a clinical setting. To explore the relationship between classification error, controller delay, and real-time controllability, 13 able-bodied subjects were trained to operate a virtual upper-limb prosthesis using pattern recognition of electromyogram (EMG) signals. Classification error and controller delay were varied by training different classifiers with a variety of analysis window lengths ranging from 50 to 550 ms and either two or four EMG input channels. Offline analysis showed that classification error decreased with longer window lengths ( p <; 0.01). Real-time controllability was evaluated with the target achievement control (TAC) test, which prompted users to maneuver the virtual prosthesis into various target postures. The results indicated that user performance improved with lower classification error (p <; 0.01 ) and was reduced with longer controller delay ( p <; 0.01), as determined by the window length. Therefore, both of these effects should be considered when choosing a window length; it may be beneficial to increase the window length if this results in a reduced classification error, despite the corresponding increase in controller delay. For the system employed in this study, the optimal window length was found to be between 150 and 250 ms , which is within acceptable controller delays for conventional multistate amplitude controllers.
Subfields: Biomedical Engineering, Cellular and Molecular Neuroscience
View Paper: https://www.semanticscholar.org/paper/0d95f50bff9996873bfdba1320db1c7097c8813c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
- Nawadita Parajuli
- Alexandre Campeau-Lecours
- U. Côté-Allard
- Clément M. Gosselin
- Ganesh R. Naik
- Alexandre Drouin
- Paolo Bifulco
- Mario Cesarelli
In Cellular and Molecular Neuroscience
- Nawadita Parajuli
- Alexandre Campeau-Lecours
- U. Côté-Allard
- Clément M. Gosselin
- Ganesh R. Naik
- Alexandre Drouin
- Paolo Bifulco
- Mario Cesarelli
Citations in the corpus
- Gesture recognition by instantaneous surface EMG images (2016, neutral): “At our sampling rate, 150 frames is equivalent to 150 ms, which is the window size suggested by several studies of pattern recognition based on prosthetic control 1,6,36 .”
- Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning (2018, background): “Even though more recent studies suggest that the latency should optimally be kept between 100-250 ms [31], [32], the performance of the classifier should take priority over speed [31], [33].”
- Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation (2019, background): “Thus, normally, the denser yet semi-class decisions are made through small segment increments that help to improve response time and accuracy [31].”
- Surface EMG-Based Inter-Session Gesture Recognition Enhanced by Deep Domain Adaptation (2017, background): “At our sampling rate, 150 frames is equivalent to 150 ms, which is the window size suggested by several studies of pattern recognition based on prosthetic control [11,71,72].”