The architecture of the Movement + Meaning NEP will be based on the well established YARP middleware which has a broad international user community, and which enables modularity, easy integration of new components, real-time distributed low-latency communication, adherence to established libraries and standards, and low threshold deployment and maintenance. The middleware functional elements include processing components for data acquisition and system control, multi-domain database that enables storage of motion data and semantic tags, and a service ontology database. Processing components mediate between inputs into the system and output generated by the system and can include: forward and feedback controllers, machine learning modules, cognitive architectures, artificial neural networks and psychological models. These components are being developed by the users of the middleware and include the researchers of the SSHRC MovingStories multi-institution research partnership, a research initiative that is under development from 2013-2017 (www.movingstories.ca). MovingStories explores the computational modeling of complex intelligent behaviour and action and that links movement digital semantic representation with computational representation.
The m+m middleware has the potential to greatly expand productivity of movement-based research, enabling researchers to have access to valuable digital movement resources which will in turn increase collaboration and new knowledge. In addition the m+m concurrent RPIs with Credo Interactive Inc and H+Technologies will ensure an accelerated production and dissemination of tools for movement generation and analysis. The m+m NEP will enable researchers to construct meaningful semantic models for movement that can interpret human movement data, construct machine-learning models for movement recognition and movement analytics, represent semantic properties of movement behaviours for virtual avatars in online games and online performance, and map movement data as a controller for online distributed performance and as input to search engines that can recognize and tag existing movement databases.