Michael H. Coen

Learn More
This paper describes design criteria for creating highly embedded, interactive spaces that we call Intelligent Environments. The motivation for building these systems is to bring computation into the real, physical world to support what is traditionally considered non-computational activity. We describe an existing prototype space, known as the Intelligent(More)
Intelligent Environments (IEs) have specific computational properties that generally distinguish them from other computational systems. They have large numbers of hardware and software components that need to be interconnected. Their infrastructures tend to be highly distributed, reflecting both the distributed nature of the real world and the IEs’ need for(More)
This paper describes the design and implementation of a natural language interface to a highly interactive space known as the Intelligent Room. We introduce a data structure called a recognition forest, which simplifies incorporation of non-linguistic contextual information about the human-level events going on in the Intelligent Room into its speech(More)
This paper presents a self-supervised framework for perceptual learning based upon correlations in different sensory modalities. We demonstrate this with a system that has learned the vowel structure of American English – i.e., the number of vowels and their phonetic descriptions – by simultaneously watching and listening to someone speak. It is highly(More)
We present a novel methodology for building highly integrated multimodal systems. Our approach is motivated by current cognitive and behavioral theories of sensory perception in animals and humans. We argue that perceptual integration in multimodal systems needs to happen at the lowest levels of the individual perceptual processes. Rather than treating each(More)
BACKGROUND Prediction of subsequent school-age asthma during the preschool years has proven challenging. OBJECTIVE To confirm in a post hoc analysis the predictive ability of the modified Asthma Predictive Index (mAPI) ina high-risk cohort and a theoretical unselected population. We also tested a potential mAPI modification with a 2-wheezing episode(More)