MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Doctoral Theses
  • View Item
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Doctoral Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Wearable and automotive systems for affect recognition from physiology

Author(s)
Healey, Jennifer Anne
Thumbnail
DownloadFull printable version (9.357Mb)
Other Contributors
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Advisor
Rosalind W. Picard.
Terms of use
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582
Metadata
Show full item record
Abstract
Novel systems and algorithms have been designed and built to recognize affective patterns in physiological signals. Experiments were conducted for evaluation of the new systems and algorithms in three types of settings: a highly constrained laboratory setting, a largely unconstrained ambulatory environment, and a less unconstrained automotive environment. The laboratory experiment was designed to test for the presence of unique physiological patterns in each of eight different emotions given a relatively motionless seated subject, intentionally feeling and expressing these states. This experiment generated a large dataset of physiological signals containing many day-to-day variations, and the proposed features contributed to a success rate of 81% for discriminating all eight emotions and rates of up to 100% for subsets of emotion based on similar emotion qualities. New wearable computer systems and sensors were developed and tested on subjects who walked, jogged, talked, and otherwise went about daily activities. Although in the unconstrained ambulatory setting, physical motion often overwhelmed affective signals, the systems developed in this thesis are currently useful as activity monitors, providing an image diary correlated with physiological signals. Automotive systems were used to detect physiological stress during the natural but physically driving task. This generated a large database of physiological signals covering over 36 hours of driving. Algorithms for detecting driver stress achieved a recognition rates of 96% using stress ratings based on task conditions for validation and 89% accuracy using questionnaires analysis for validation. Further results in which metrics of stress from video tape annotations of the drive were correlated with physiological features showed highly significant correlations (up to r = .77 for over 4000 samples). Together, these three experiments show a range of success in recognizing affect from physiology, showing high recognition rates in somewhat constrained conditions and highlighting the need for more automatic context sensing in unconmore automatic context sensing in unconstrained conditions. The recognition rates obtained thus far lend support to the hypothesis that many emotional differences can be automatically discriminated in patterns of physiological changes.
Description
Thesis (Ph.D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2000.
 
Includes bibliographical references (p. 152-158).
 
Date issued
2000
URI
http://hdl.handle.net/1721.1/9067
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Publisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.

Collections
  • Doctoral Theses

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.