How do electric bikes affect the route choice of cyclists? A case study of Greater Helsinki

Abstract

Industry 5.0 targets a resilient, sustainable and human-centric European industry. A key initiative to reach this target is adopting a human-centric approach to digital technologies, which places the well-being of the worker at the center. As workload peaks/lows contribute to lower employee wellbeing, predictive employee workload analytics can empower management to undertake proactive prevention. For this purpose, we develop a real-time machine learning framework to predict and explain future workload. Our feature importance analysis demonstrates the value of human-machine interactions and partner workload exposure. The proposed 2-stage framework, inspired by deep Tobit models, is developed and implemented in an environment with a variable and imbalanced workload: the digital control rooms for railway traffic management of Infrabel, Belgium’s railway infrastructure company. The related application is tailored towards the managers, for whom it provides real-time and explainable insights.