Deep Models for Engagement Assessment With Scarce Label Information

Feng Li; Guangfan Zhang; Wei Wang; Roger Xu; Tom Schnell; Jonathan Wen; Frederic McKenzie; Jiang Li

doi:10.1109/THMS.2016.2608933

Back

Deep Models for Engagement Assessment With Scarce Label Information

Journal article

Peer reviewed

Deep Models for Engagement Assessment With Scarce Label Information

Feng Li, Guangfan Zhang, Wei Wang, Roger Xu, Tom Schnell, Jonathan Wen, Frederic McKenzie and Jiang Li

IEEE transactions on human-machine systems, Vol.47(4), pp.598-605

10/21/2016

DOI: 10.1109/THMS.2016.2608933

Files and links (1)

url

https://arxiv.org/pdf/1610.06815View

Open Access

Abstract

Task engagement is defined as loadings on energetic arousal (affect), task motivation, and concentration (cognition). It is usually challenging and expensive to label cognitive state data, and traditional computational models trained with limited label information for engagement assessment do not perform well because of overfitting. In this paper, we proposed two deep models (i.e., a deep classifier and a deep autoencoder) for engagement assessment with scarce label information. We recruited 15 pilots to conduct a 4-h flight simulation from Seattle to Chicago and recorded their electroencephalograph (EEG) signals during the simulation. Experts carefully examined the EEG signals and labeled 20 min of the EEG data for each pilot. The EEG signals were preprocessed and power spectral features were extracted. The deep models were pretrained by the unlabeled data and were fine-tuned by a different proportion of the labeled data (top 1%, 3%, 5%, 10%, 15%, and 20%) to learn new representations for engagement assessment. The models were then tested on the remaining labeled data. We compared performances of the new data representations with the original EEG features for engagement assessment. Experimental results show that the representations learned by the deep models yielded better accuracies for the six scenarios (77.09%, 80.45%, 83.32%, 85.74%, 85.78%, and 86.52%), based on different proportions of the labeled data for training, as compared with the corresponding accuracies (62.73%, 67.19%, 73.38%, 79.18%, 81.47%, and 84.92%) achieved by the original EEG features. Deep models are effective for engagement assessment especially when less label information was used for training.

Computer Science - Computer Vision and Pattern Recognition

Details

Title: Subtitle: Deep Models for Engagement Assessment With Scarce Label Information
Creators: Feng Li - Old Dominion University
Guangfan Zhang - Intelligent Automation, Inc., Rockville, MD, USA
Wei Wang - Intelligent Automation, Inc., Rockville, MD, USA
Roger Xu - Intelligent Automation, Inc., Rockville, MD, USA
Tom Schnell
Jonathan Wen - Georgia Institute of Technology
Frederic McKenzie - Old Dominion University
Jiang Li - Old Dominion University
Resource Type: Journal article
Publication Details: IEEE transactions on human-machine systems, Vol.47(4), pp.598-605
DOI: 10.1109/THMS.2016.2608933
ISSN: 2168-2291
eISSN: 2168-2305
Grant note: DOI: 10.13039/100000104, name: NASA, award: NNX10CB27C
Language: English
Date published: 10/21/2016
Academic Unit: Neurology; Electrical and Computer Engineering; Occupational and Environmental Health; Industrial and Systems Engineering; Public Policy Center (Archive)
Record Identifier: 9984186972702771

Metrics

15 Record Views

20 Times Cited - Web of Science