IEEE Consumer Electronics Magazine - October 2016 - 54

Table 6. A technology comparison
convenience chart.
sensor technology for stress Detection
EEg

ECg

Highly
wearable
Highly
accurate

✓

PPg

gsr

✓

✓
✓

✓

Low
cost

✓

Low
maintenance

✓

Highly
unobtrusive

✓

aFEa

ABOUT THE AUTHORS

✓
✓

✓

aFea includes eye tracking
aFea: automated facial expression analysis.

skin conductance, and HR, a combination of these sensor
sources would likely be best for accurately detecting stress.
Companies such as iMotions, Inc. have developed systems
that integrate multiple methods of measurement in a single
platform [93]. For example, they have integrated physiological sensors with AFEA and eye-tracking software to better
assess affective states. The central benefit of such a platform
is that it allows researchers to perform full experiments within
a single environment. Stimuli can be generated and integrated
into a test just as well as the response is recorded. This allows
investigators to make stronger correlations of facial expression
recognition and eye activity with proven biological metrics.
iMotions' biometric research platform integrates some of the
most popular and highly validated measurement systems offered
by Biopac Systems, Empatica, Shimmer Sensors, Emotient,
Affectiva, Emotiv, Tobii, and ABM. Such a system allows for
full integration of GSR, EEG, EMG, ECG, BVP, eye tracking,
and facial expression recognition all in a single platform for
analysis. Table 6 shows the technology available for affective
computing and stress detection.

FINAL ASSESSMENT AND AREAS
FOR FUTURE RESEARCH
Affective computing is a growing field. As it grows, so will
the robustness of stress-detection systems. Much of the technology used within affective computing can be directly
applied to stress detection, especially more contemporary
noninvasive technologies, such as facial expression, gesture
recognition, and eye tracking. These modes of affective computing, coupled with VR technology, could be revolutionary
in the assessment and intervention of stress.
Many commercially and readily available devices come
equipped with much of the sensing capabilities used for stress
detection and affective computing as a whole. Popular products ranging from fitness bands (e.g., BASIS Peak, Microsoft
54 IEEE Consumer Electronics Magazine

Band) that contain GSR, PPG, and temperature sensors to
smartphones with a PPG sensor and camera (e.g., Samsung
Galaxy S6) can be used in detecting stress. Given this proposal for use, corresponding research must evaluate the apps that
accompany these smart bands and smart watches [94]-[96].
Comparing commercially available products such as BASIS
Peak [94] and Samsung Galaxy S Health [97] apps against
gold standards in ECG, GSR, etc. may reveal corresponding
results. Consumers aware of such rankings can be better aided
in the decision-making process when choosing a product.

OCTOBER 2016

Shalom Greene (shalom.greene@uky.edu) earned his B.S.
degree in computer engineering technology from the Rochester Institute of Technology, New York. He is currently an
M.S. student in electrical and computer engineering at the
University of Kentucky, Lexington.
Himanshu Thapliyal (hthapliyal@uky.edu) earned his
Ph.D. degree in computer science and engineering from the
University of South Florida, Tampa. He received the Best
Ph.D. Dissertation Award at the 2012 IEEE Computer Society
Annual Symposium on VLSI. From 2012 to 2014, he worked
as a designer of processor test solutions at Qualcomm, where
he received the Qualcomm QualStar Award for contributions to
memory built-in self-tests. He is an assistant professor with the
Department of Electrical and Computer Engineering, University of Kentucky, Lexington. He is a Member of the IEEE.
Allison Caban-Holt (amcaba2@uky.edu) earned her
Ph.D. degree in clinical psychology from the University of
Tennessee, Knoxville. She is with the Sanders-Brown Center
on Aging and is an assistant professor of behavioral science
at the University of Kentucky, Lexington.

REFERENCES
[1] R. W. Picard. (1995, Nov.). Affective computing. M.I.T Media Laboratory,
Cambridge, MA. [Online]. Available: http://hd.media.mit.edu/tech-reports/
TR-321.pdf
[2] R. W. Picard, "Affective Computing for Human-Computer
Interfaces," in Proc. HCI, Munich, Germany, 1999, pp. 829-833.
[3] R. W. Picard, "Affective computing: Challenges," Int. J. HumanComputer Stud., vol. 59, no. 1, pp. 55-64, 2003.
[4] E. Harmon Jones, T. F. Price, and P. A. Gable, "The influence of
affective states on cognitive broadening/narrowing: Considering the
importance of motivational intensity," Social Pers. Psychol. Compass,
vol. 6, no. 4, pp. 314-327, 2012.
[5] American Physiological Association. Stress: The different kinds of
stress. [Online]. Available: http://www.apa.org/helpcenter/stress-kinds.aspx
[6] American Physiological Association. How stress affects your health.
[Online]. Available: http://www.apa.org/helpcenter/stress.aspx
[7] D. S. Krantz, K. S. Whittaker, and D. S. Sheps, "Psychosocial risk factors for coronary artery disease: Pathophysiologic mechanisms," in Heart
and Mind: The Practice of Cardiac Psychology. Washington, D.C.: APA,
2011.
[8] T. Pickering, "Mental stress as a causal factor in the development of
hypertension and cardiovascular disease," Curr. Hypertension Rep.,
vol. 3, no. 3, pp. 249-254, June 2001.
[9] H. Monnikes, J. Tebbe, M. Hildebrandt, P. Arck, E. Osmanogiou, M.
Rose, B. Klapp, B. Weidenmann, and I. Heymann-Monnikes. "Role of
stress in functional gastrointestinal disorders," Dig. Dis., vol. 19, no. 3,
pp. 201-211, 2001.

http://hd.media.mit.edu/tech-reports/ http://www.apa.org/helpcenter/stress-kinds.aspx http://www.apa.org/helpcenter/stress.aspx

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - October 2016