Classification of phases of hand grasp task by the extraction of miniature compound nerve action potentials (mCNAPs)
- Resource Type
- Conference
- Authors
- Sheshadri, Swathi; Kortelainen, Jukka; Rigosa, Jacopo; Cutrone, Annarita; Bossi, Silvia; Libedinsky, Camilo; Lahiri, Amitabha; Chan, Louiza; Chng, Keefe; Thakor, Nitish V.; Delgado-Martinez, Ignacio; Yen, Shih-Cheng
- Source
- 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER) Neural Engineering (NER), 2015 7th International IEEE/EMBS Conference on. :593-596 Apr, 2015
- Subject
- Aerospace
Grasping
Electrodes
Feature extraction
Accelerometers
Accuracy
Correlation
Support vector machines
- Language
- ISSN
- 1948-3546
1948-3554
Interfacing with the nervous system to restore functional motor activity is a promising therapy to augment the classical surgical approaches to treating peripheral nerve injuries. Despite the advances in electrode microelectronics engineering, the challenge of extracting information from injured nerves to help restore motor function remains unsolved. Here we used waveform feature extraction and clustering techniques to identify a discrete set of events in intraneural recordings of the median nerve in a non-human primate (NHP) during grasping tasks. This analysis allowed the classification of the different phases of hand grasping. The waveform features were found to be significantly different for each phase of grasping. Since these waveforms can be seen as the minimal signal components that result from the activation of a group of nerve fibers, we denominated them miniature compound nerve action potentials (mCNAPs). The correlation between mCNAPs and the different stages of movement can be utilized in the near future to design high-performance neuroprosthetic therapies.