Context prediction is a promoting research topic with a lot of challenges and opportunities. Indeed, with the constant evolution of context-aware systems, context prediction remains a complex task due to the lack of formal approach. In this paper, we propose a new approach to enhance context prediction using a probabilistic temporal logic and model checking. The probabilistic temporal logic PCTL is used to provide an efficient expressivity and a reasoning based on temporal logic in order to fit with the dynamic and non-deterministic nature of the system’s environment. Whereas, the probabilistic model checking is used for automatically verifying that a probabilistic system satisfies a property with a given likelihood. Our new approach allows a formal expressivity of a multidimensional context prediction. Tested on real data our model was able to achieve 78% of the future activities prediction accuracy.
Using probabilistic temporal logic PCTL and model checking for context prediction
About the Author: Darine Ameyed
Darine Ameyed, Ph.D. in engineering, Software and Information Technologies (ÉTS-2017). She received an M.Msc applied IA ( Columbia university US-2019). She obtained her M.Sc. in Digital Art and Technology from the University Rennes 2 (U.R.2) (University of Upper Brittany, France) in 2010. She earned her M.Sc. Multimedia Engineering from the University Paris Est Marne la Vallée (U.P.E.M) (University of Paris 11, France) in 2008. She received a B.Sc. in computer science and Management from the Institut Supérieur de Gestion (I.S.G) (University of Tunis, Tunisia) in 2005. She is currently a research associate at Synchromédia lab, École Technologie Supérieure (ÉTS), Montreal. Also, an expert in United for smart and sustainable cities (U4SSC)-International Telecommunication Union- ITU-UN. She has been a scientific program and project manager at CIRODD (2015-2019), Co-founder and CEO of NyX-R (2015-2018), a tech advisor for tech and science-based startups. On the other hand, she has a long multidisciplinary academic and industrial career in Canada, Europe, and Africa in the areas of software engineering, mobile computing, ERP system management, art, and entrepreneurship. Her research interests include Predictive Modeling, Context-Aware System, Ambient Intelligence (AmI), C-IoT, Human-Centered Computing, Machine Learning, Activity Recognition, Human-Machine Interaction (HMI), Data security and privacy in IoT platforms and computational sustainability.