Feature Saliency in Artificial Neural Networks with Application to Modeling Workload

Abstract

This dissertation research extends the current knowledge of feature saliency in artificial neural networks (ANN). Feature saliency measures allow for the user to rank order the features based upon the saliency, or relative importance, of the features. Selecting a parsimonious set of salient input features is crucial to the success of any ANN model. In this research, several methodologies were developed using the Signal to Noise Ratio (SNR) Feature Screening Method and its associated SNR Saliency Measure for selecting a parsimonious set of salient features to classify pilot workload in addition to air traffic controller workload. Candidate features were derived from electroencephalography (EEG), electrocardiography (EKG), electro-oculography (EOG), and respiratory gauges. In addition, a new saliency measure was developed that can account for time in Elman Recurrent Neural Networks (RNN). This Partial Derivative Based Spatial Temporal Saliency Measure is used via a Spatial Temporal Feature Screening Method for selecting a parsimonious set of salient features in both time and space. Finally, a technique for investigating the memory capacity of an Elman RNN was developed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1998
Accession Number
ADA358600

Entities

People

  • Kelly A. Greene

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Cognition
  • Cognitive Workload
  • Computational Science
  • Computers
  • Data Science
  • Dimensionality Reduction
  • Experimental Design
  • Health Services
  • Information Processing
  • Information Science
  • Knowledge Management
  • Neural Networks
  • Psychology
  • Recurrent Neural Networks
  • Statistical Algorithms
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Computational Modeling and Simulation

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Space