Naturalistic Recognition of Activities and Mood Using Wearable Electronics

• Published in: IEEE transactions on affective computing Vol. 7; no. 3; pp. 272 - 285
• Main Authors: Zhu, Zack, Satizabal, Hector F., Blanke, Ulf, Perez-Uribe, Andres, Troster, Gerhard
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Accelerometers; activity recognition; Automation; Context; Context recognition; Devices; Electronics; Emotion recognition; Labeling; Mathematical models; Mood; mood inference; Moods; Patients; Recognition; Sensors; Wearable; wearable computing
• ISSN: 1949-3045; 1949-3045
• DOI: 10.1109/TAFFC.2015.2491927

Automatic recognition of user context is essential for a variety of emerging applications, such as context-dependent content delivery, telemonitoring of medical patients, or quantified life-logging. Although not explicitly observable as, e.g., activities, an important aspect towards understanding user context lies in the affective state of mood.While significant work has been done to assess mood, most approaches require the use of  customized sensors and controlled laboratory settings.In this work, we engineer a recognition pipeline to recognize daily activities from commercially popularized wearable electronics. In turn, we use predicted activities to learn a regression model capable of assessing user mood.Using only commercially popularized wearable devices, we enable the potential for seamless deployment to the general public.Conducting a real-world study with a prototype system, we collect and evaluate data from 18 users, who provide over 93 user-days of labelled activity data.Regressing for mood based on predicted daily activities, we are able to infer mood angles with a mean absolute error of <inline-formula> <tex-math notation="LaTeX">0.24\pi</tex-math> <inline-graphic xlink:type="simple" xlink:href="zhu-ieq1-2491927.gif"/> </inline-formula> radians on the Circumplex Model of Affect.Comparing with benchmark approaches, our approach outperforms with statistical significance and is validated for robustness against noise from activity misclassification.