RFID Data Monitoring and Cleaning Using Tensor Calculus

In current trends of supply chains governance, RFID is a promising infrastructure-less technology. Nevertheless the unreliability of RFID data streams and the relevant amount of generated data in a supply chain pose significant challenges of monitoring and cleaning (i.e. to be processed on the fly). Current approaches provide hard-coded solutions, with high consumption of resources; moreover, these exhibit very limited flexibility dealing with multidimensional queries, at various levels of granularity and complexity. In this paper we propose a general model for RFID data monitoring and cleaning based on the first principles of linear algebra, in particular on tensorial calculus. Leveraging our abstract algebraic framework, our technique allows quick decentralized on-line processing and logic analysis, according to needs and requirements of supply chain actors. Experimental results show how our approach can process analysis and maintenance of RFID data efficiently.