Machine Learning Interpretability and Its Impact on Smart Campus Projects
This is an incremental application of existing interpretability methods to a new domain (smart campuses).
The paper addresses the need for machine learning interpretability in smart campus projects, such as optimizing energy efficiency and safety at the University of Northampton, but does not provide specific results or numbers.
Machine learning (ML) has shown increasing abilities for predictive analytics over the last decades. It is becoming ubiquitous in different fields, such as healthcare, criminal justice, finance and smart city. For instance, the University of Northampton is building a smart system with multiple layers of IoT and software-defined networks (SDN) on its new Waterside Campus. The system can be used to optimize smart buildings energy efficiency, improve the health and safety of its tenants and visitors, assist crowd management and way-finding, and improve the Internet connectivity.