Dissertation
Workload-aware systems and interfaces for cognitive augmentation
Vorschaubild nicht verfügbar
Volltext URI
Dokumententyp
Text/Dissertation
Zusatzinformation
Datum
2020
Autor:innen
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Quelle
Verlag
Ludwig-Maximilians-Universität München, Fakultät für Mathematik, Informatik und Statistik
Zusammenfassung
In today's society, our cognition is constantly influenced by information intake, attention switching, and task interruptions. This increases the difficulty of a given task, adding to the existing workload and leading to compromised cognitive performances. The human body expresses the use of cognitive resources through physiological responses when confronted with a plethora of cognitive workload. This temporarily mobilizes additional resources to deal with the workload at the cost of accelerated mental exhaustion.
We predict that recent developments in physiological sensing will increasingly create user interfaces that are aware of the user’s cognitive capacities, hence able to intervene when high or low states of cognitive workload are detected. In this thesis, we initially focus on determining opportune moments for cognitive assistance. Subsequently, we investigate suitable feedback modalities in a user-centric design process which are desirable for cognitive assistance. We present design requirements for how cognitive augmentation can be achieved using interfaces that sense cognitive workload.
We then investigate different physiological sensing modalities to enable suitable real-time assessments of cognitive workload. We provide empirical evidence that the human brain is sensitive to fluctuations in cognitive resting states, hence making cognitive effort measurable. Firstly, we show that electroencephalography is a reliable modality to assess the mental workload generated during the user interface operation. Secondly, we use eye tracking to evaluate changes in eye movements and pupil dilation to quantify different workload states. The combination of machine learning and physiological sensing resulted in suitable real-time assessments of cognitive workload. The use of physiological sensing enables us to derive when cognitive augmentation is suitable.
Based on our inquiries, we present applications that regulate cognitive workload in home and work settings. We deployed an assistive system in a field study to investigate the validity of our derived design requirements. Finding that workload is mitigated, we investigated how cognitive workload can be visualized to the user. We present an implementation of a biofeedback visualization that helps to improve the understanding of brain activity. A final study shows how cognitive workload measurements can be used to predict the efficiency of information intake through reading interfaces. Here, we conclude with use cases and applications which benefit from cognitive augmentation.
This thesis investigates how assistive systems can be designed to implicitly sense and utilize cognitive workload for input and output. To do so, we measure cognitive workload in real-time by collecting behavioral and physiological data from users and analyze this data to support users through assistive systems that adapt their interface according to the currently measured workload. Our overall goal is to extend new and existing context-aware applications by the factor cognitive workload. We envision Workload-Aware Systems and Workload-Aware Interfaces as an extension in the context-aware paradigm. To this end, we conducted eight research inquiries during this thesis to investigate how to design and create workload-aware systems.
Finally, we present our vision of future workload-aware systems and workload-aware interfaces. Due to the scarce availability of open physiological data sets, reference implementations, and methods, previous context-aware systems were limited in their ability to utilize cognitive workload for user interaction. Together with the collected data sets, we expect this thesis to pave the way for methodical and technical tools that integrate workload-awareness as a factor for context-aware systems.