Building Cognition-Aware Systems: A Mobile Toolkit for Extracting Time-of-Day Fluctuations of Cognitive Performance

Dingler, Tilman; Schmidt, Albrecht und Machulla, Tonja (September 2017): Building Cognition-Aware Systems: A Mobile Toolkit for Extracting Time-of-Day Fluctuations of Cognitive Performance. In: Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies : IMWUT, Bd. 1, Nr. 3: 47:1-47:15

Abstract

People’s alertness fluctuates across the day: at some times we are highly focused while at others we feel unable to concentrate. So far, extracting fluctuation patterns has been time and cost-intensive. Using an in-the-wild approach with 12 participants, we evaluated three cognitive tasks regarding their adequacy as a mobile and economical assessment tool of diurnal changes in mental performance. Participants completed the five-minute test battery on their smartphones multiple times a day for a period of 1-2 weeks. Our results show that people’s circadian rhythm can be obtained under unregulated non-laboratory conditions. Along with this validation study, we release our test battery as an open source library for future work towards cognition-aware systems as well as a tool for psychological and medical research. We discuss ways of integrating the toolkit and possibilities for implicitly measuring performance variations in common applications. The ability to detect systematic patterns in alertness levels will allow cognition-aware systems to provide in-situ assistance in accordance with users’ current cognitive capabilities and limitations.

• Dokumententyp: Zeitschriftenartikel
• EU Funded Grant Agreement Number: 683008
• EU-Projekte: Horizon 2020 > ERC Grants > ERC Consolidator Grant > ERC Grant 683008: AMPLIFY - Amplifying Human Perception Through Interactive Digital Technologies
• Publikationsform: Submitted Version
• Keywords: alertness, circadian rhythm, cognition-aware systems
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISSN: 2474-9567
• Ort: New York, NY, USA
• Sprache: Englisch