• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1039-1049
• /
• 2020

Neural decoding is important to recognize the user's intention for controlling a neuro-prosthetic hand. This paper proposes a real-time decoding method for multi-channel peripheral neural activity. Peripheral nerve signals were measured from the median and radial nerves, and motion artifacts were removed based on locally fitted polynomials. Action potentials were then classified using a k-means algorithm. The firing rate of action potentials was extracted as a feature vector and its dimensionality was reduced by a self-organizing feature map. Finally, a multi-layer perceptron was used to classify hand motions. In monkey experiments, all processes were completed within a real-time constrain, and the hand motions were recognized with a high success rate.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.4
• /
• pp.279-285
• /
• 2016

Reliable recording and analysis of peripheral nerve activity is important to recognize the user's intention for controlling a neuro-prosthetic hand. In this paper, we present a peripheral nerve recording system that consisted of an intrafascicular multi-electrode array, an electrode insertion device, and a multi-channel neural amplifier. The 16 channel multi-electrode array was stably implanted into the sciatic nerve of the rat under anesthesia using the electrode insertion device. During passive movements and mechanical stimuli, muscle and cutaneous afferent signals were recorded with the multi-channel neural amplifier. Furthermore, we propose a spike sorting method to isolate individual neuronal unit. The muscle proprioceptive units were classified as muscle spindle afferents or Golgi tendon organ afferents, and the skin exteroceptive units were categorized as slow adapting afferents or fast adapting afferents. Experimental results showed that the proposed method could be applicable to record and analyze peripheral nerve activity in neuro-prosthetic systems.