Abstract
In the paper, we proposed an anticipatory pattern recognition method for an electromyogram (EMG) prosthetic hand control. To detect humans' motor intentions as fast as possible, we focused on the transient state of the EMG signals. We sampled the EMG signals from a human forearm, and extracted a feature vector every 50 ms. At each time window, the proposed pattern discriminator determined whether the measured EMG signals were in the transient state or not. In the case of the transient state, candidates of migratable prosthetic hand patterns were constrained by a prior knowledge regarding a transition probability among the hand patterns. Accordingly an appropriate hand pattern can be selected, otherwise an ongoing hand pattern was maintained. Online EMG pattern recognition experiments with the proposed anticipatory pattern recognition method demonstrated a significant improvement compared with the method without the anticipatory mechanism.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
