Distributed Localized Contextual Event Reasoning Under Uncertainty

Abstract

Abstract-We focus on Internet of Things (IoT) environments where sensing and computing devices (nodes) are responsible to observe, reason, report and react to a specific phenomenon. Each node (e.g., an unmanned vehicle or an autonomous device) captures context from data streams and reasons on the presence of an event. We propose a distributed predictive analytics scheme for localized context reasoning under uncertainty. Such reasoning is achieved through a contextualized, knowledge-driven clustering process, where the clusters of nodes are formed according to their belief on the presence of the phenomenon. Each cluster enhances its localized opinion about the presence of an event through consensus realized under the principles of Fuzzy Logic (FL). The proposed FLdriven consensus process is further enhanced with semantics adopting Type-2 Fuzzy Sets to handle the uncertainty related to the identification of an event. We provide a comprehensive experimental evaluation and comparison assessment with other schemes over real data and report on the benefits stemmed from its adoption in IoT environments.

Autonomous Proactive Data Management in Support of Pervasive Edge Applications

“…The IoT and the EC infrastructures are smoothly combined to create a layered architecture where data and services can be allocated in any place. IoT devices can monitor a specific phenomenon collecting the corresponding data [7][8][9][10] reporting them in streams [11] towards the Cloud back end. Streams processing is adopted when real time decisions should be made while the processing of data at rest is utilized for long term decisions.…”

A Proactive Statistical Model Supporting Services and Tasks Management in Pervasive Applications

“…Apart from the allocation of resources, another challenge is the management of data present at the discussed layers. The collected data that may be reported by a high number of streams, e.g., the evolution of a certain phenomenon (e.g., fire, air contamination) [16], [17], [18], streams generated by autonomous nodes (e.g., unmanned vehicles) [19] and so on and so forth. Upon these streams, we can easily support the extraction of knowledge, the detection of events or any other processing [20].…”

An EKF based overlapping coalition formation game for cooperative wireless network navigation

“…By considering of the mentioned limitations, an EKF based OCF game algorithm is proposed to get the efficient cooperative link strategies in this paper. Nowadays, extensive estimation methods, such as EKF [22, 23], minimum mean square estimator (MMSE)[24], maximum likehood estimation (MLE)[25], particle filter (PF) [26], have been used to obtain real‐time state information in wireless network navigation. Among those methods, the EKF has been widely used for tracking in GNSS receiver [27], multiple mobile robot system, dynamic state estimation [28] and cooperative localisation algorithms [29].…”