Online temporal reasoning for event and data streams processing

Abstract

Online fuzzy expert systems can be used to process data and event streams, providing a powerful way to handle their uncertainties and their inaccuracy. Moreover, human experts can decide how to process the streams with rules close to natural language. However, to extract high level information from these streams, they need at least to describe the temporal relations between the data or the events.In this paper, we propose a straightforward way to design temporal operators which relies on the mathematical definition of some base operators and then their combination into more sophisticated operators to assess precedence, periodicity or persistence. We also introduce the concept of expiration of temporal expressions on online fuzzy expert systems, that is to say the capacity to change the values of outputs whereas the inputs have not changed.

A fuzzy expert system architecture for data and event stream processing

“…Among the sophisticated relations we have implemented, temporal operators [23] and those which derived from them need a special attention when applied on 225 event streams. The particularity of event streams is that the system is noticed of events irregularly.…”

“…In addition, in real-world applications, it is possible to have very large rule bases which require a great amount of processor time [21]. Moreover, to describe the relations between the data or the events, more sophisticated operators are needed for temporal [22,23], spatial [24,25] or even spatio-temporal [26] reasoning. These operators imply a higher computational cost.…”

“…The motivation of our work is to provide an efficient fuzzy 70 expert system in operational contexts. To enable human experts to author more complex rules, our system is able to efficiently assess complex fuzzy relations [23]. To ensure it can interface easily with the various information systems of our partners, we chose to avoid specific architectures (like GPU) and to develop a software for data and event stream processing on regular CPU platforms.…”

“…where l is a number of samples used [23] and most of spatial operators are 215 at least in O(n × m) where n × m is the dimension of the image [24].…”

“…To implement efficiently expiration, which affects only some temporal operators [23], the values of expirable expression operands are stored in memory regarding a temporal scope to allow partial recalculation. Indeed, it is necessary to find a good compromise between efficiency, scalability and flexibility regarding our industrial partners and our needs to experiment new operators and inference 345 methods.…”