WorkLifeSens - Sensor-based Worklife Assistance Systems
In an increasingly dynamic work environment, it is important to understand job selection criteria for talent and job seekers. There are numerous studies on the relevance of salary, status symbols, and hygiene factors. But these studies typically refer to a static point in time and offer only limited possibilities for individualized recommendations for action. However, the ubiquitous digitization of business and society has vastly improved our ability to collect, transmit, and transform data, and we are seeing an increasing number of wearables that offer new opportunities to collect a variety of data from individuals. The proliferation of self-measurement and self-reflection offerings in our personal lives is steadily increasing and already suggests the use of related technologies in the work environment. By collecting and analyzing individual data based on wearable devices and continuous self-reporting, it is possible to get a more accurate picture of individual factors influencing productivity, satisfaction and well-being of talents and job seekers. Artificial Intelligence (AI) methods can be used to develop appropriate hardware-software solutions.
The project "WorkLifeSens", funded by the Baden-Württemberg Ministry of Economics, designs, develops, and evaluates an AI-based hardware-software solution consisting of an assistance system prototype and sensor technology. The solution enables talents and job seekers to collect physiological data (e.g. heart rate data) with self-report data on cognitive states (e.g., mental workload). Self-reflection should be supported and concrete recommendations for action should be given. The overarching goal of WorkLifeSens is to get a more accurate picture of individual factors (e.g., productivity, satisfaction, and well-being) of talents and job seekers.
The WorkLifeSens project is coordinated by the IISM and carried out in cooperation with the Campusjäger GmbH and movisens GmbH. The project partners are contributing their expertise in various areas (e.g., AI, sensor technology, and assistance systems). The figure below summarizes the main work packages of the respective project partners.
- Rissler, R.; Nadj, M.; Li, M. X.; Knierim, M. T.; Maedche, A. (2018). “Got Flow? Using Machine Learning on Physiological Data to Classify“. CHI 2018 Proceedings.
- Morana, S., Kroenung, J., Schacht, S., and Maedche, A. (2019). "Designing Process Guidance Systems", Journal of the Association for Information Systems (JAIS), 20(5), 499-535.
- Adam, M. T. P, Gimpel, H., Maedche, A., and Riedl, R. (2016), “Design Blueprint for Stress-Sensitive Adaptive Enterprise Systems“, Business & information systems engineering (BISE), 59 (4), 277-291.
- Maedche, A., Morana, S., Schacht, S., Werth, D., and Krumeich, J. (2016). “Advanced User Assistance Systems“, Business & information systems engineering (BISE), 58 (5), 367–370.
- Toreini, P.; Langner, M.; Maedche, A. (2019). Using Eye-Tracking for Visual Attention Feedback. Information Systems and Neuroscience – NeuroIS Retreat 2019. Ed.: F. D. Davis, 261–270, Springer International Publishing, Cham. doi:10.1007/978-3-030-28144-1_29