Combining Machine Learning With Inductive Logic Learning To Detect Deviations From Daily Routines In Ambient Intelligent Environments

Benjamin Duppe, Michael Meiser, Alexander Anisimov, André Antakli, Muhammad Muaz, Ingo Zinnikus

In: WI-IAT21. IEEE/WIC/ACM International Conference on Web Intelligence (WI-2021) December 14-17 Melbourne Australia ACM Press 2021.


The availability of sensor technology in home and building automa-tion offers new opportunities for AI applications. Machine learning(ML) methods can recognize device patterns and profiles based onsensor data and make energy-relevant predictions. At a higher level,the detected patterns can in turn be used to learn activity patterns.In this paper, we present a hybrid approach to augment ML-basedoutputs with inductive logic-based learning techniques. We presentevaluation results and illustrate an application to agent-supportedcritical situation detection in the assisted living domain.


Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence