TY - JOUR
T1 - Personalized mental stress detection with self-organizing map
T2 - From laboratory to the field
AU - Tervonen, Jaakko
AU - Puttonen, Sampsa
AU - Sillanpää, Mikko J.
AU - Hopsu, Leila
AU - Homorodi, Zsolt
AU - Keränen, Janne
AU - Pajukanta, Janne
AU - Tolonen, Antti
AU - Lämsä, Arttu
AU - Mäntyjärvi, Jani
N1 - Publisher Copyright:
© 2020 Elsevier Ltd
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/9
Y1 - 2020/9
N2 - Stress has become a major health concern and there is a need to study and develop new digital means for real-time stress detection. Currently, the majority of stress detection research is using population based approaches that lack the capability to adapt to individual differences. They also use supervised learning methods, requiring extensive labeling of training data, and they are typically tested on data collected in a laboratory and thus do not generalize to field conditions. To address these issues, we present multiple personalized models based on an unsupervised algorithm, the Self-Organizing Map (SOM), and we propose an algorithmic pipeline to apply the method for both laboratory and field data. The performance is evaluated on a dataset of physiological measurements from a laboratory test and on a field dataset consisting of four weeks of physiological and smartphone usage data. In these tests, the performance on the field data was steady across the different personalization levels (accuracy around 60%) and a fully personalized model performed the best on the laboratory data, achieving accuracy of 92% which is comparable to state-of-the-art supervised classifiers. These results demonstrate the feasibility of SOM in personalized mental stress detection both in constrained and free-living environment.
AB - Stress has become a major health concern and there is a need to study and develop new digital means for real-time stress detection. Currently, the majority of stress detection research is using population based approaches that lack the capability to adapt to individual differences. They also use supervised learning methods, requiring extensive labeling of training data, and they are typically tested on data collected in a laboratory and thus do not generalize to field conditions. To address these issues, we present multiple personalized models based on an unsupervised algorithm, the Self-Organizing Map (SOM), and we propose an algorithmic pipeline to apply the method for both laboratory and field data. The performance is evaluated on a dataset of physiological measurements from a laboratory test and on a field dataset consisting of four weeks of physiological and smartphone usage data. In these tests, the performance on the field data was steady across the different personalization levels (accuracy around 60%) and a fully personalized model performed the best on the laboratory data, achieving accuracy of 92% which is comparable to state-of-the-art supervised classifiers. These results demonstrate the feasibility of SOM in personalized mental stress detection both in constrained and free-living environment.
KW - Behavior
KW - Clustering
KW - Machine learning
KW - Personalization
KW - Stress detection
KW - Unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85089018565&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2020.103935
DO - 10.1016/j.compbiomed.2020.103935
M3 - Article
AN - SCOPUS:85089018565
SN - 0010-4825
VL - 124
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 103935
ER -