Towards optimizing the non-invasive sensory feedback interfaces in a neural prosthetic control

Objective. The somatotopic interface (SI) and non-somatotopic interface (NI) are commonly used to provide non-invasive sensory feedback. Nevertheless, differences between somatotopic and non-somatotopic feedbacks are rarely reported, and objective evaluations of the corresponding brain response are missing as well. Few studies have reported how to design the stimulation encoding strategy based on the two interfaces in sensory feedback. The objective of this study was to investigate the difference in sensory characteristics between SI and NI, and propose an optimal encoding method for non-invasive feedback interfaces.Approach. We recruited seven amputees and compared the tactile sensitivity to stimulated positions and intensities between SI (phantom finger area) and NI (upper arm) in a tactile discrimination task. Electroencephalography (EEG) evaluation task was subsequently conducted to objectively evaluate the stimulus-evoked brain response for SI and NI. Finally, the two kinds of tactile information (stimulated position and intensity) was applied to an object recognition task in a closed-loop prosthesis control system. Specifically, the object size was reflected by the prosthetic finger position through stimulated position encoding, and the object stiffness was reflected by the contact force of prosthetic fingers through stimulated intensity encoding. We compared the performance under four feedback conditions (combinations between two kinds of tactile information and two interfaces).Main results. Behavioral results showed that NI was more sensitive to position information while SI was more sensitive to intensity information. EEG results were consistent with behavioral results, showing a higher sensitivity of sensory alpha ERD and a stronger correlation between alpha ERD and discrimination accuracies for NI in the position discrimination, while the trend was opposite in the intensity discrimination. The feedback encoding allowed amputees to discriminate the size and stiffness of nine objects with the best performance of 62% overall accuracy (84% for size discrimination, 71% for stiffness discrimination) when position and intensity information was delivered on the NI and SI, respectively.Significance. Our results provided an instructive strategy for sensory feedback via non-invasive solutions.