publication . Article . Other literature type . 2014

Movement Error Rate for Evaluation of Machine Learning Methods for sEMG-Based Hand Movement Classification

Arjan Gijsberts; Manfredo Atzori; Claudio Castellini; Henning Müller; Barbara Caputo;
Open Access
  • Published: 01 Jul 2014 Journal: IEEE Transactions on Neural Systems and Rehabilitation Engineering, volume 22, pages 735-744 (issn: 1534-4320, eissn: 1558-0210, Copyright policy)
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
There has been increasing interest in applying learning algorithms to improve the dexterity of myoelectric prostheses. In this work, we present a large-scale benchmark evaluation on the second iteration of the publicly released NinaPro database, which contains surface electromyography data for 6 DOF force activations as well as for 40 discrete hand movements. The evaluation involves a modern kernel method and compares performance of three feature representations and three kernel functions. Both the force regression and movement classification problems can be learned successfully when using a nonlinear kernel function, while the exp- χ 2 kernel outperforms the mo...
Persistent Identifiers
free text keywords: General Neuroscience, Biomedical Engineering, Computer Science Applications, Radial basis function kernel, Word error rate, Controllability, Machine learning, computer.software_genre, computer, Accelerometer, Classifier (linguistics), Artificial intelligence, business.industry, business, Kernel method, Kernel (statistics), Kernel (linear algebra), Computer science
Any information missing or wrong?Report an Issue