Classification of Action Potentials in MultiUnit Intrafascicular Recordings Using Neural Network Pattern-Recognition Techniques Article

Mirfakhraei, K, Horch, K. (1994). Classification of Action Potentials in MultiUnit Intrafascicular Recordings Using Neural Network Pattern-Recognition Techniques . IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 41(1), 89-91. 10.1109/10.277276

cited authors

  • Mirfakhraei, K; Horch, K

authors

abstract

  • Neural network pattern-recognition techniques were applied to the problem of identifying the sources of action potentials in multi-unit neural recordings made from intrafascicular electrodes implanted in cats. The network was a three-layer connectionist machine that used digitized action potentials as input. On average, the network was able to reliably separate 6 or 7 units per recording. As the number of units present in the recording increased beyond this iimit, the number separable by the network remained roughly constant. The results demonstrate the utility of neural networks for classifying neural activity in multi-unit recordings. © 1994, IEEE

publication date

  • January 1, 1994

published in

Digital Object Identifier (DOI)

start page

  • 89

end page

  • 91

volume

  • 41

issue

  • 1