For most companies, the most significant cost is labor. To reduce these labor costs, employers aim to maximize employee efficiency. An important item to guarantee efficiency is scheduling, both on personal and on group level. Scheduling of meetings and work is currently mostly done based on availability of people. However, studies have shown that also other parameters can play a crucial role. For example, productivity peaks could be taken into account. According to research our brain can only focus 90-120 min continuously. To maximize productivity employees should find a working pattern that allows them to plan their most demanding tasks during their most productive hours and try to avoid multitasking. However, there are no tools available to measure what are the most productive times of an employee, or even of an entire organization.
Physiological signals such as heart rate (HR) and skin conductance (SC) have shown to be correlated with stress, emotions and other mental factors. With the use of high-quality and low power wearables, these signals can now be measured continuously in daily life and work settings. Combining these signals with phone/computer based context information, such as calendars, location, etc. could provide work schedules based on mental ability and flow to optimize employee efficiency and satisfaction at the work place.
This PhD will focus on the research towards a model that can link physiological signals, mental state and context information towards an optimal work schedule. The main part of the PhD will consist of data collection and data analysis. The outcome should be a model that can advise employees on scheduling and optimal planning according to their availability and mental state. The PhD will consist of interdisciplinary research, where collaboration with psychologists, sociologists and data scientists is crucial.
Required background: bio-engineering, biomedical engineering, computer science, with background in data science
Type of work: 40% data collection, 60% data analysis
Supervisor: Chris Van Hoof
Daily advisor: Elena Smets
The reference code for this PhD position is SE1712-32. Mention this reference code on your application form.