Evaluation of Time-Domain Features of Sensory ENG Signals

In the development of closed-loop prostheses that record from the patient's own nerves to provide sensory feedback, it is first necessary to determine the features of sensory signals that may help to identify different sensations. The aim of this work was to investigate different time-domain features for separation of sensory electroneurographic signals. To do this, sensory signals were elicited in response to mechanical stimulation of the rat hindpaw and these signals were recorded from a cuff electrode array placed on the sciatic nerve. Thirteen features were extracted, including: mean absolute value, variance, waveform length and ten time-domain descriptors that were recently proposed for classification of electromyographic signals. These features were individually fed into a linear discriminant analysis classifier. The results showed that the best overall performing features were the mean absolute value and waveform length. Additionally, six of the ten time-domain descriptors showed a comparable performance to these two features. This indicates that these features could be used as a tool to aid our understanding of the sensory neural signals recorded and further improve classification results. Enhanced classification of electroneurographic signals will provide the opportunity to develop more efficacious sensory-motor prostheses in the future.