The Fishualization feedback board shows visualizations of the state or mood of an entire team of knowledge workers. One avatar (fish) is shown for each employee. Each avatar has three degrees of freedom that are controlled by aggregated sensor measurements of an individual team member. The movements and position are controlled by activity level, a measure for focus, and mental energy. ‘Plants’ at the bottom of the screen represent a group of tasks of the same type, for example, writing e-mail, editing document, browsing, or preparing presentation. Activity level, focus and mental energy are derived by combining multiple sensor data streams.
The main ICT challenge addressed in the feedback board is the analysis and interpretation of heterogeneous multi-scale sensor data to estimate the parameters for a model that assesses the workload, mental and physical fitness of a worker taking into account personal norms. The initial model relies mostly on computer interaction, identification of tasks, context switches and cloud storage of sensor data (CommonSense framework) but will be combined with affect and physical aspects; for example using analysis of facial expressions (FaceReader) or analysis of e-mail sentiments (SWELL e-mail plugin).
Recent TNO research indicates that out of the Dutch workforce 1 million have burn-out complaints and that stress is the main reasons for 7% of sick leaves. The goal of the Fishualization system is to enable employees to gain insights into their working habits to reduce stress and increase productivity. There are no sensing based personal coaching products on the market that combine multiple sensors and look at both mental and physical fitness. SWELL partners are Almende/Sense OS, and Noldus Information Technology.
Sensor-based reasoning and decision making is a paradigm that can also be deployed in smart cities or smart ‘X’ contexts. However, the SWELL/Fishualization platform has the largest potential in other person-related monitoring & coaching situations, such as self- management of people with chronic diseases, or e-learning systems.
Deployment of the Fishualization system in a pilot at work needs to be approved by company management and works council. The Fishualization system has been designed with proper anonymity and data protection guidelines. All stored sensor data is owned by the respective users. Avatars cannot be identified at first sight.