On the classification of single evoked potentials using a quadratic classifier
β Scribed by Jorge I. Aunon; Clare D. McGillem
- Publisher
- Elsevier Science
- Year
- 1982
- Weight
- 882 KB
- Volume
- 14
- Category
- Article
- ISSN
- 0010-468X
No coin nor oath required. For personal study only.
β¦ Synopsis
Classification of single evoked potentials using a quadratic classifier is described. The technique chooses features (voltages at the sampling points) using a forward sequential feature selection technique. Classification accuracies for a two class problem ranged from 93-99~ for training and testing wifh mhe same data and from 89-96'Z for training and testing with differ,:nt data.
π SIMILAR VOLUMES
Twelve normal subjects, and six color blind (three protanopes and three deuteranopes) individuals were used in this study. Visual evoked potentials (50-150 msec post-stimulus) were recorded in response to three stimuli: (a) three horizontal, achromatic bars alternating in luminosity between bright a