Digital Commons Network^™

Using Reconstructability Analysis To Select Input Variables For Artificial Neural Networks, Stephen Shervais, Martin Zwick

Systems Science Faculty Publications and Presentations

We demonstrate the use of Reconstructability Analysis to reduce the number of input variables for a neural network. Using the heart disease dataset we reduce the number of independent variables from 13 to two, while providing results that are statistically indistinguishable from those of NNs using the full variable set. We also demonstrate that rule lookup tables obtained directly from the data for the RA models are almost as effective as NNs trained on model variables.

Handgrip Pattern Recognition, Zong Chen

Dissertations

There are numerous tragic gun deaths each year. Making handguns safer by personalizing them could prevent most such tragedies. Personalized handguns, also called "smart" guns, are handguns that can only be fired by the authorized user. Handgrip pattern recognition holds great promise in the development of the smart gun.

Two algorithms, static analysis algorithm and dynamic analysis algorithm, were developed to find the patterns of a person about how to grasp a handgun. The static analysis algorithm measured 160 subjects' fingertip placements on the replica gun handle. The cluster analysis and discriminant analysis were applied to these fingertip placements, and …