Behaviour Recognition on Noisy Data-streams Constrained by Complex Prior Knowledge

Abstract : Complex Event Processing (CEP) consists of the analysis of data-streams in order to extract particular patterns and behaviours described, in general, in a logical formalism. In the classical approach, data of a stream – or events – are supposed to be the complete and perfect observation of the system producing these events. However, in many cases, the means for collecting such data, such as sensors, are not infallible and may miss the detection of a particular event or on the contrary produce. In this thesis, we have studied the possible models of representation of uncertainty and, thus, to offer the CEP a robustness to this uncertainty as well as the necessary tools to allow the recognition of complex behaviours based on the chronicle formalism. In this perspective, three approaches have been considered. The first one is based on Markov logical networks to represent the structure of the chronicles under a set of logical formulas of a confidence value. We show that this model, although widely applied in the literature, is inapplicable for a realistic application with regard to the dimensions of such a problem. The second approach is based on techniques from the SAT community to enumerate all possible solutions of a given problem and thus to produce a confidence value for the recognition of a chronicle expressed, again, under a logical structure. Finally, we propose a last approach based on the Markov chains to produce a set of samples explaining the evolution of the model in agreement with the observed data. These samples are then analysed by a recognition system to count the occurrences of a particular chronicle.
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download
Contributor : Romain Rincé <>
Submitted on : Wednesday, January 16, 2019 - 12:42:51 PM
Last modification on : Friday, May 17, 2019 - 11:36:45 AM


Files produced by the author(s)


  • HAL Id : tel-01983311, version 1


Romain Rincé. Behaviour Recognition on Noisy Data-streams Constrained by Complex Prior Knowledge. Modeling and Simulation. Université de nantes, 2018. English. ⟨tel-01983311⟩



Record views


Files downloads