Rule-Based Distributed and Agent Systems

Bǎdicǎ, Costin; Braubach, Lars; Paschke, Adrian

doi:10.1007/978-3-642-22546-8_3

Cited by 15 publications

(3 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several semantic models exist for IoT device discovery and uniform data format. Semantic technologies are largely leveraged in the web domain and extend the Web with machine interpretable meaning, thus enabling data integration and sharing, and interoperability amongst interconnected machines [27]. A well established Semantic Web standard is the Web Ontology Language (OWL), developed by the World Wide Web Consortium (W3C).…”

Section: The Oma Lwm2m Protocolmentioning

confidence: 99%

Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

Campolo

Genovese

Molinaro

2021

JSAN

View full text Add to dashboard Cite

Several Internet of Things (IoT) applications are booming which rely on advanced artificial intelligence (AI) and, in particular, machine learning (ML) algorithms to assist the users and make decisions on their behalf in a large variety of contexts, such as smart homes, smart cities, smart factories. Although the traditional approach is to deploy such compute-intensive algorithms into the centralized cloud, the recent proliferation of low-cost, AI-powered microcontrollers and consumer devices paves the way for having the intelligence pervasively spread along the cloud-to-things continuum. The take off of such a promising vision may be hurdled by the resource constraints of IoT devices and by the heterogeneity of (mostly proprietary) AI-embedded software and hardware platforms. In this paper, we propose a solution for the AI distributed deployment at the deep edge, which lays its foundation in the IoT virtualization concept. We design a virtualization layer hosted at the network edge that is in charge of the semantic description of AI-embedded IoT devices, and, hence, it can expose as well as augment their cognitive capabilities in order to feed intelligent IoT applications. The proposal has been mainly devised with the twofold aim of (i) relieving the pressure on constrained devices that are solicited by multiple parties interested in accessing their generated data and inference, and (ii) and targeting interoperability among AI-powered platforms. A Proof-of-Concept (PoC) is provided to showcase the viability and advantages of the proposed solution.

show abstract

Section: The Oma Lwm2m Protocolmentioning

confidence: 99%

Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

Campolo

Genovese

Molinaro

2021

JSAN

View full text Add to dashboard Cite

show abstract

“…Thabtah et al (2006) proposed a new associative classification method called Multi-class Classification based on Association Rules (MCAR), which takes advantage of vertical format representation and uses an efficient technique for discovering frequent items. Bǎdicǎ et al (2011) surveyed several major approaches using rules in multi-agent systems and distributed agent architectures which run rule engines at their core. Gupta et al (1988) exploited very fine-grained parallelism to achieve significant speed-ups, which is also distinct from other parallel implementations in that they parallelize a highly optimized C-based implementation of OPS5.…”

Section: Related Workmentioning

confidence: 99%

A Novel Approach to Distributed Rule Matching and Multiple Firing Based on MapReduce

Dong

Cheng

Cao

et al. 2018

Journal of Database Management

View full text Add to dashboard Cite

In order to solve the poor performance problem of massive rules reasoning, as well as the inconsistency problem of working memory in distributed rule matching, this article presents the formal definition of interference relations between rules, and proposes a novel approach to distributed rule matching and multiple firing based on MapReduce. This approach adopts the way of access request control to detect and exclude interference rules, then selects several rule instantiations to perform multiple firing and concurrent execution, thus reducing the number of inference cycles effectively. By detecting the interferences between rules, this method selects and executes compatible rule sets, and avoids the inconsistency problem of system working memory. In order to verify the validity of the authors' approach, this article developes a production system based on MapReduce, and applied this approach in the master server of a distributed production system. The experimental results show that their method can promote the performance of massive rules reasoning effectively.

show abstract

“…The current trend in event detection focuses on the use of increasingly sophisticated techniques such as artificial intelligence, data mining, or fuzzy logic [16]. This results in a lack of interest in threshold-based detection techniques, which are widely used in industry, distributed control networks, alarm systems, or in the early stages of more complex computational methods, such as rule-based systems or complex event processing [4].…”

Section: Introductionmentioning

confidence: 99%

Data Communication Optimization for the Evaluation of Multivariate Conditions in Distributed Scenarios

et al. 2019

View full text Add to dashboard Cite

The current technological landscape is characterized by the massive and efficient interconnection of heterogeneous devices. Sensor networks (SNs) are key elements of this paradigm; they support the local loop, the collection and early manipulation of information. Among the applications of SNs, event detection is a well-explored topic in which strategies such as collaboration, self-organization, and others have been developed in depth. In this topic, the simplest and also most used event concept approach is the threshold-based event, which is usually integrated as part of the local sensor process. This paper addresses a different perspective by discussing the evaluation of multivariate Boolean conditions with distributed variables. We propose a new algorithm (Data Retaining Algorithm for Condition Evaluation, DRACE) that reduces packet traffic while preserving time accuracy in event calculation on an adaptive approach. To facilitate understanding of DRACE, a case study is presented in the context of a logical simile titled The Problem of a Proper Defense. The algorithm supports parameters that affects the compromise between accuracy and traffic savings. To analyze its performance, 9000 executions of the algorithm have been performed. 9 configurations tested on a repository of 1000 triads of signals randomly generated. Focusing on the most accurate configuration, 99% of executions are error-free, and the number of packets is reduced by 40% on average, being between 30 and 50% in 68% of cases. INDEX TERMS Wireless sensor networks, event detection, information filtering.

show abstract

Rule-Based Distributed and Agent Systems

Cited by 15 publications

References 57 publications

Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

A Novel Approach to Distributed Rule Matching and Multiple Firing Based on MapReduce

Data Communication Optimization for the Evaluation of Multivariate Conditions in Distributed Scenarios

Contact Info

Product

Resources

About