Three R’s of Cyber-Physical Spaces Vivek Menon ∗ , Bharat Jayaraman † , Venu Govindaraju † ∗ Amrita Vishwa Vidyapeetham, † University at Buffalo (SUNY) ABSTRACT Recognition, reasoning and retrieval are three fundamental operations in a cyber-physical space that is capable of identifying and tracking the movements of people and answering questions about their whereabouts. We show that a state transition system effectively abstracts the three R’s: events abstract recognition, transition function abstracts the reasoning, and states abstract the information necessary for performing retrieval. We provide quantitative metrics for the performance of a cyber-physical space by refining the standard information-theoretic measures of precision and recall. This article also presents performance improvements from integrating spatio-temporal reasoning with biometric-based recognition. KEYWORDS Cyber-physical spaces, State Transition System, Biometric Recognition, Spatio-temporal Rea- soning, Information Retrieval, Performance Metrics. I NTRODUCTION A cyber-physical space is a physical space embedded with intelligence and interfaced with humans in a natural way using vision, speech, gestures, and touch, rather than the traditional keyboard and mouse. The key to realizing this paradigm is identifying and tracking people in the space. The ability to identify and track people and answer questions about their whereabouts is critical to many applications [1]. The scenarios range from environments in which most of the individuals are known or pre-registered (health-care monitoring) to environments where most of the individuals are unknown (homeland security). We highlight below two scenarios from real-life incidents. 1 Digital Object Indentifier 10.1109/MC.2011.59 0018-9162/$26.00 2011 IEEE This article has been accepted for publication in Computer but has not yet been fully edited. Some content may change prior to final publication.