Judith S. Heinisch

Christoph Anderson, Judith Simone Heinisch, Shohreh Deldari et al.

Pervasive and ubiquitous computing facilitates immediate access to information in the sense of always-on. Information such as news, messages, or reminders can significantly enhance our daily routines but are rendered useless or disturbing when not being aligned with our intrinsic interruptibility preferences. Attention management systems use machine learning to identify short-term opportune moments, so that information delivery leads to fewer interruptions. Humans' intrinsic interruptibility preferences - established for and across social roles and life domains - would complement short-term attention and interruption management approaches. In this article, we present our comprehensive results towards social role-based attention and interruptibility management. Our approach combines on-device sensing and machine learning with theories from social science to form a personalized two-stage classification model. Finally, we discuss the challenges of the current and future AI-driven attention management systems concerning privacy, ethical issues, and future directions.

Judith S. Heinisch, Christoph Anderson, Klaus David

Inferring emotions from physiological signals has gained much traction in the last years. Physiological responses to emotions, however, are commonly interfered and overlapped by physical activities, posing a challenge towards emotion recognition in the wild. In this paper, we address this challenge by investigating new features and machine-learning models for emotion recognition, non-sensitive to physical-based interferences. We recorded physiological signals from 18 participants that were exposed to emotions before and while performing physical activities to assess the performance of non-sensitive emotion recognition models. We trained models with the least exhaustive physical activity (sitting) and tested with the remaining, more exhausting activities. For three different emotion categories, we achieve classification accuracies ranging from 47.88% - 73.35% for selected feature sets and per participant. Furthermore, we investigate the performance across all participants and of each activity individually. In this regard, we achieve similar results, between 55.17% and 67.41%, indicating the viability of emotion recognition models not being influenced by single physical activities.