Advancing Proper Dataset Partitioning and Classification of Visual Search and the Vigilance Decrement Using EEG Deep Learning Algorithms
Abstract
Electroencephalography (EEG) classification of visual search and vigilance tasks has vast potential in its benefits. In future human-machine teaming systems, EEG could act as the tool for operator state assessment, enabling AI teammates to know when to assist the operator in these tasks. These future augmented cognition systems have the potential to lead to increased safety of operations, better training systems for our operators, and improved operational effectiveness. This dissertation investigates EEG models built to utilize any individuals EEG signals, i.e. cross-participant models, in the areas of: 1. Dataset partitioning for proper training and validation, Classification of the efficiency of an operators search, Classification of whether an operator is in a vigilance decrement during a vigilance type task. First, the necessity of proper dataset partitioning for EEG cross-participant models is demonstrated both mathematically and empirically using publicly available datasets, with empirical results demonstrating that improper partitioning of datasets can lead to error rates underestimated between 35 percent and 3900 percent. Next, the results of a conducted visual search experiment are presented, in which EEG signals were captured while participants performed a visual search task, and various techniques were tested to mitigate inefficient search to efficient search. Efficient search was found to be on average faster than inefficient search, resulting in a 13 percent speed up, and also more accurate, with a 61 percent reduction in error rate. Two techniques (the nudge and hint) were found to be effective in mitigation of inefficient search, resulting in a 169 percent increase of efficient searches.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2021
- Accession Number
- AD1150037
Entities
People
- Alexander J. Kamrud
Organizations
- Air Force Institute of Technology