Quantitative Metrics for Smart Spaces

This paper introduces novel quantitative metrics for evaluating the performance of occupant identification and tracking models in multi-building smart spaces. We evaluate two state transition system models: the Centralized State Transition System (CSTS) and the Distributed State Transition System (DSTS). Both are probabilistic models characterized by events, state transition functions, and states. Events abstract biometric recognition, transition functions capture state changes, and states provide the foundation for information retrieval. To systematically compare these models, we introduce two figures of merit, for comparing event-level and state-level behavior, respectively. Experimental results indicate that CSTS outperforms DSTS in their figures of merit, demonstrating greater accuracy, however, DSTS remains a viable alternative in scenarios where building-specific structure and reduced state update complexity offer advantages. Our findings emphasize that both models have their strengths, and also that different scenarios may require different metrics for a more nuanced understanding of system performance and comparison.