Data-driven, sensor-based taxonomy for environmental life cycle assessment of pallets

Pallets are one of the most important load carriers for international supply chains. Yet, continuously tracking activities such as Driving, Lifting or Standing along their life cycle is hardly possible. This contribution is the first to propose a taxonomy for sensor-based activity recognition of pallets. Different types of acceleration sensors are deployed in three logistical scenarios for creating a benchmark dataset. A random forest classifier is deployed for supervised learning. The results demonstrate that automated, sensor-based life cycle assessment based on the proposed taxonomy is feasible. All data and corresponding videos are published in the SPARL dataset