Abstract
The concept of the cloud-to-thing continuum addresses advancements made possible by the widespread adoption of cloud, edge, and IoT resources. It opens the possibility of combining classical symbolic AI with advanced machine learning approaches in a meaningful way. In this paper, we present a thing registry and an agent-based orchestration framework, which we combine to support semantic orchestration of IoT use cases across several federated cloud environments. We use the concept of virtual sensors based on machine learning (ML) services as abstraction, mediating between the instance level and the semantic level. We present examples of virtual sensors based on ML models for activity recognition and describe an approach to remedy the problem of missing or scarce training data. We illustrate the approach with a use case from an assisted living scenario.
Highlights
The concept of the cloud-to-thing continuum [1] addresses advancements made possible by the widespread adoption of cloud, edge, and IoT resources
To illustrate the utilization of sensor information at different levels, we present a number of virtual sensors in the form of machine learning (ML) services from the domain of human activity recognition
We only considered the human-triggered appliances, as they can be used as a proxy for the identification of human activity or lack thereof
Summary
The concept of the cloud-to-thing continuum [1] addresses advancements made possible by the widespread adoption of cloud, edge, and IoT resources. With the widespread use of IoT devices, connected and feeding large amounts of data to the internet, there is an opportunity to process these data with the most advanced artificial intelligence techniques to provide value-added services. For the integration of heterogeneous services and IoT devices, various semantic standards and technologies have been applied to solve interoperability problems [2] This has, on the one hand, the advantage that additional tools can be used and deployed based on the standards. On the meta-level, agent-based orchestrations combine the available sensor information to develop value-added services and applications. A use case developer, may start with federated clouds and explore services and devices all the way down to local environments Core components where both opposing directions converge are the thing registry and an agent-based orchestration framework, which we combine to support semantic orchestration of IoT use cases in federated cloud environments.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
