Physical Sciences and Mathematics Commons^™

The Afit Multielectrode Array For Neural Recording And Simulation: Design, Testing, And Encapsulation, James R. Reid Jr

Theses and Dissertations

A two-dimensional, X-Y addressable, multiplexed array of 256 electrodes (16 x 16) has been fabricated using conventional semiconductor processing techniques. The individual electrodes are 16O microns x 160 microns, approximating the size of the cortical columns; the overall array size is 3910 microns x 3910 microns. The array has been fitted to a chronically implantable package and tested for several days in a simulated neural environment. EEG-like data were collected successfully from individual electrodes in the array. This array improves on a previous design of a 16 electrode (4 x 4) array that was chronically implanted on the cortex of …

Classification Of Patterns In Eeg Recordings : A Comparison Of Back-Propagation Networks Vs. Predictive Autoencoder Networks, Brian Armieri

Theses

Recent research exploring the use of neural networks for electro-encephalogram (EEG) pattern classification has found that a three-layer back-propagation network could be successfully trained to identify high voltage spike-and-wave spindle (HVS) patterns caused by epileptic seizures (Jando et. al., in press). However, there is no reason to predict that back-propagation is the best possible network architecture for EEG classification. A back-propagation neural network and a predictive autoencoder neural network were compared to determine which network was better at correct classifying both HVS and non-HVS patterns.

Both networks were able to classify 88%-89% of all patterns using a limited set of …