Erik Thomsen, a principal scientist at Charles River Analytics, was invited to deliver the opening keynote at the Ontological Approaches to Sensor Data Analysis conference, which took place at the University of Buffalo from May 19-20, 2016. Thomsen discussed Composable Event Frames for the Integrated Analysis of Sensor Data and Natural Language, as part of the conference’s focus on how ontologies can support analysis of sensor data.
“Sensors exist as parts of larger systems that have the ability to reason about sensor outputs, to decide upon courses of action to be taken, and to engage control processes that will initiate these courses of action,” explained Thomsen. “Our ontology-based composable event frame approach to designing a system of this sort incorporates the ability to merge sensor information with information generated in natural language and to reason about the resulting ensemble.”
One of the motivating scenarios for composable event frames discussed in Thomsen’s talk stems from Charles River’s research in building adaptive software under DARPA’s Building Resource Adaptive Software Systems (BRASS) program. As part of the BRASS team, Charles River is incorporating advances in machine learning and probabilistic modeling to address the challenge of building adaptable software systems that can sense, understand, learn from, and adapt to changes in the computational environment in which they are deployed. Read more about the BRASS effort.