Well-being @ Work

SWELL (Smart Reasoning Systems for Well-being at Work and at Home)

Objectives: WP3 aims at developing person centric inferencing techniques with a focus on the well-being at work scenario. The core of this WP are two PhD projects that address two different determinants of well-being: ‘empowerment’ and ‘workload management’.

Well-being and productivity of knowledge workers is a largely unexplored research area. Sensor based techniques for the recognition of human behaviour and state are developing rapidly. WP3 will create a link between the social sciences and sensor bases human activity recognition in order to support knowledge workers to improve their well-being.

Task 3.1: Empowering the user. This task will focus on the development of user centric inference techniques based on topical preferences and interaction preferences. Preferences can be gleaned from online (and local) behavior and information access and production, Inference techniques and secure privacy aware (WP4) preference sharing can be used to guide resource discovery helping knowledge workers to avoid the duplication of work and optimize their planning.

Task 3.2: Controlling the workload. This task will focus on the development of user centric inference techniques that reason about the actual and optimal workload of a knowledge worker. Using various types of sensors, a low level data stream will be interpreted in terms of task level actions, user goals and cognitive load. Proof-of-concept strategies will be developed and evaluated where the inferred information will be used to help the user to mitigate high workload situations.

Both tasks will start with capturing the datastreams of sensors and communication protocols and ground truth information that reflect the activity of a reasonable size of subjects (knowledge workers at one or more associated P7 partners). Data will be cleaned and anonomized with the aim to share (part of the) data with the research community. The data will be used to train and evaluated the activity recognition models. Empowerment and workload controlling assistants (well-working e-coaches) will be based on inference techniques exploiting this data, potentially in the context of peer groups. E-coaches will be evaluated in cooperation with WP6.

WP Leader: