Duration: From 01/01/2019 to 31/12/2021

BIONIC is a European research project aiming to develop an unobtrusive, autonomous and privacy preserving platform for real-time risk alerting and continuous persuasive coaching, enabling the design of workplace interventions adapted to the needs and fitness levels of specific ageing workforce. Gamification strategies adapted to the needs and wishes of the elderly workers will ensure optimal engagement for prevention and self-management of musculoskeletal health in any working/living environment.

Loosely integrated IMUs fitted into everyday or work clothing with dynamic monitoring of overall body posture will significantly promote the wide adoption of motion tracking wearables, eliminating the need to attach sensing devices firmly to the body, thus affecting comfort and possibly impeding movement during work or everyday physical activity. The usability of kinematic data (e.g. body postures) will be significantly enriched with the addition of kinetic, physiological and environmental sensor data related to the situation of the workers and their surroundings. Depending on the specific chronic musculoskeletal disorders (MSDs) condition, body-part specific BSN modules (e.g. belts or bandages for monitoring lower back and knee chronic MSD) will be developed. Detailed monitoring of these body parts will be based on innovative localized bio-mechanical models.

A major key innovation relates to the concept of AI on a chip, which is embedding predictive Artificial Intelligence algorithms in the BSN. Raw data pre-processing at the source prevents immense flows of data being transmitted to remote gateways. The combination of ML algorithms with a model-based estimation will allow for deducing relevant and interpretable parameters for efficient real-time, in-field and long-term personalized risk/physical strain and recovery assessment from individual sensor data. Moreover, from a methodological point of view, another key innovation relies in the combination of data-driven and model-based estimation/detection algorithms for continuous intelligent sensor auto-calibration and correction, which will enable ease of use and loose coupling of sensors on every day and work clothing.