Digital Library of the European Council for Modelling and Simulation

Title:	Modelling Interleaved Activities Using Language Models
Authors:	Eoin Rogers, Robert J. Ross, John D. Kelleher
Published in:	2020). ECMS 2020 Proceedings Edited by: Mike Steglich, Christian Muller, Gaby Neumann, Mathias Walther, European Council for Modeling and Simulation. DOI: http://doi.org/10.7148/2020 ISSN: 2522-2422 (ONLINE) ISSN: 2522-2414 (PRINT) ISSN: 2522-2430 (CD-ROM) ISBN: 978-3-937436-68-5 ISBN: 978-3-937436-69-2(CD) Communications of the ECMS , Volume 34, Issue 1, June 2020, United Kingdom
Citation format:	Eoin Rogers, Robert J. Ross, John D. Kelleher (2020). Modelling Interleaved Activities Using Language Models, ECMS 2020 Proceedings Edited By: Mike Steglich, Christian Mueller, Gaby Neumann, Mathias Walther European Council for Modeling and Simulation. doi: 10.7148/2020-0183
DOI:	https://doi.org/10.7148/2020-0183
Abstract:	We propose a new approach to activity discovery, based on the neural language modelling of streaming sensor events. Our approach proceeds in multiple stages: we build binary links between activities using probability distributions generated by a neural language model trained on the dataset, and combine the binary links to produce complex activities. We then use the activities as sensor events, allowing us to build complex hierarchies of activities. We put an emphasis on dealing with interleaving, which represents a major challenge for many existing activity discovery systems. The system is tested on a realistic dataset, demonstrating it as a promising solution to the activity discovery problem.
Full text: