Finland’s VTT exploring AI-based methods to detect work stress

The effort makes use of data from motion detectors and environmental quality sensors installed at the workplace to monitor factors such as employee movement and working conditions. The data is then modelled with algorithms to identify anomalous behavioural patterns and measure the stress levels of employees.

Johanna Kallio, a senior scientist at VTT, reminded that stress can even affect the way employees use digital devices and that such changes can be monitored with software installed on the device.

“The state of stress may manifest itself, for example, as an atypical keystroke rhythm or duration of application use,” she elaborated.

VTT is presently developing a next-generation organisational barometer in an attempt to usher in a transition from annual and biannual wellbeing surveys to continuous wellbeing monitoring at workplaces. The findings of continuous monitoring, it believes, can be used as the basis for creating tools for supporting both the workplace culture and individual coping in a timely fashion.

The tools are being developed in co-operation with business partners such as Granlund, Haltian Empathic Building, Helvar, Hintsa Performance, Martela and UniqAir.

Continuous monitoring of stress levels, however, is challenging especially as scores of employees have been consigned to work from their home due to the coronavirus pandemic.

The Finnish Institute of Occupational Health and VTT are consequently set to launch a pilot project to develop methods for monitoring wellbeing at work regardless of location. Nixu, a Finnish provider of cybersecurity services, has been brought on to the project to ensure the methods are safe and the employees have the ability to manage the data.

Altogether, the project has been granted 10 million euros in funding. Also contributing to it are a consortium in Spain and Portugal, and partners in Austria and South Korea.