Heating, Ventilation, and Air Conditioning (HVAC) systems account for 40% to 50% of energy usage in commercial buildings, so controlling them while preserving occupants' comfort matters. State-of-the-art solutions use pervasive systems with sensors or smart devices to gauge individual thermal sensations, but assessing those methods is hard: real-world experiments are expensive, limited in access, and often overlook occupant and regional diversity.
Co-zyBench is a benchmark tool that takes a Digital Twin (DT) approach to evaluating personalized thermal comfort systems.
GenAIPABench assesses the effectiveness of GenAIPAs across multiple dimensions including accuracy, relevance, and consistency, using a curated set of privacy-related questions and metrics. The benchmark aims to advance the development of AI privacy assistants by providing a standard evaluation framework.
Framework aimed at discovering, collecting, and analyzing privacy policies of smart devices using NLP and ML algorithms, to provide insights to users, policy authors, and regulators.
SmartSPEC is a smart space simulator and data generator that creates customizable smart space datasets using semantic models of spaces, people, events and sensors. We employ ML-based approaches to characterize and learn attributes of the embedded people and events in a sensorized space and apply an event-driven simulation strategy to generate realistic simulated data about the space (events, trajectories, sensor datasets, etc.).
The SmartSPEC architecture consists of two main components: