Skip to Main Content
This paper presents a design and partial implementation of an embedded system as a part of neural-machine interface (NMI) for neural-controlled artificial legs. We have designed a circuit consisting of 30 analog inputs for sampling signals from 16 EMG (Electromyography) electrodes, a 6 degrees of freedom (DOFs) load cell, 5 force sensitive resistors (FSR), and 3 goniometers. The amplified signals are filtered and converted to digital information, which is stored in a RAM. A special pattern recognition algorithm is then executed on the embedded CPU in association with the flash memory that stores the prior training data to make real time decisions. A preliminary prototype with one analog channel has been built and MPC5566 microcontroller has been used to implement the pattern recognition algorithm to measure the execution time. Measurement results show the feasibility of real time processing of neural controlled artificial legs.