Prediction of Arm Trajectory from the NeuralActivities of the Primary Motor Cortex Using a Modular Artificial Neural Network Model

摘要

First, we reconstructed 9 muscle tensions (filtered EMG signals) from 105 neurons in the arm region of the primary motor cortex, then estimated arm movement in four degrees of freedom in the shoulder and the elbow from the reconstructed 9 muscle tensions. The reconstructed arm movement showed good correlation with the actual arm movement.