Inter-space Learning

Query-Aware Adaptive Windowing for Spatiotemporal Complex Video Event Processing for Internet of Multimedia Things

Today, our built environment is not only producing large amounts of data, but –driven by the Internet of Things (IoT) paradigm– it is also starting to talk back and communicate with its inhabitants and the surrounding systems and processes. In order to unleash the power of IoT enabled environments, spaces need to be trained and configured for space-specific properties and semantics.

The major enabling technologies for creating smart building services are IoT and cognitive computing. While deploying IoT infrastructure during the construction and renovation processes is rather a straightforward practice, the implementation of cognitive components that benefit from generated data of IoT infrastructure is a complicated task that should be elaborated based on the specific attributes of target services and smart buildings.

This research investigates the potential of communication and reuse of cognitive knowledge between smart environments for a seamless and automatic transfer of services and machine learning models by means of technologies such as knowledge graphs, transfer learning, blockchain, and linked dataspaces.


Amin Anjomshoaa

Dr Edward Curry

Institution: NUI Galway


Relevant Publications

[3] Amin Anjomshoaa, Edward Curry, "A Transfer Learning Framework for IoT-enabled Environments", In Proceedings of the International Conference on Internet-of-Things Design and Implementation, ACM, New York, NY, USA, pp. 275-276, 2021. [bib] [pdf] [doi]
[2] Amin Anjomshoaa, Edward Curry, "Transfer Learning in Smart Environments", In Machine Learning and Knowledge Extraction, vol. 3, no. 2, pp. 318-332, 2021. [bib] [pdf] [doi]
[1] Amin Anjomshoaa, Edward Curry, "Inter-space Machine Learning in Smart Environments", Chapter in Cross Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE 2020), pp. 535-549, 2020. [bib] [pdf] [doi]
Powered by bibtexbrowser