Intelligent Decision-Making in the Physical Environment

Lillis, David; Russell, Seán; Carr, Dominic; Collier, Rem W.; O’Hare, Gregory M. P.

doi:10.1007/978-3-319-03647-2_18

Cited by 2 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three broad categories of evaluation have resulted from this endeavor. 21 In this scenario, the data gathered by SIXTH-connected devices provides the intelligent software agents with an abstraction of their physical environment. An extension to SIXTH to develop cyber adaptors for the gathering of data from online resources such as Twitter and Facebook is described in the work of Murdoch.…”

Section: Evaluation and Future Workmentioning

confidence: 99%

“…Existing work includes running Agent Factory Micro Edition directly on sensor motes to provide in-network intelligence, 19 using Agent Factory Micro Edition on the middleware gateway to react to sensor data 20 and also in the use of intelligent agents for the autonomic management of the sensor middleware itself. 21 In some cases, it is important for intelligence to be incorporated toward the edges of the network, on or near the nodes themselves. This includes handling issues such as coping with limited bandwidth, battery preservation, and dealing with computationally restricted devices.…”

Section: Sixth Sensor Middlewarementioning

confidence: 99%

“…In addition to its integration with SNoMAC, SIXTH has also been linked with an intelligent agent-oriented programming runtime platform. 21 In this scenario, the data gathered by SIXTH-connected devices provides the intelligent software agents with an abstraction of their physical environment. In each of these situations, SIXTH has been demonstrated to adapt easily to new data sources and additional subsystems.…”

Section: Evaluation and Future Workmentioning

confidence: 99%

“…To augment these abilities, efforts have been invested in augmenting SIXTH's core benefits with intelligent, agent‐driven, sensor network deployments. Existing work includes running Agent Factory Micro Edition directly on sensor motes to provide in‐network intelligence, using Agent Factory Micro Edition on the middleware gateway to react to sensor data and also in the use of intelligent agents for the autonomic management of the sensor middleware itself . In some cases, it is important for intelligence to be incorporated toward the edges of the network, on or near the nodes themselves.…”

Section: The Snomac Prototypementioning

confidence: 99%

“…This approach is similar to the usage of GSN as the basis for the MOSDEN middleware for Android. In addition to its integration with SNoMAC, SIXTH has also been linked with an intelligent agent‐oriented programming runtime platform . In this scenario, the data gathered by SIXTH‐connected devices provides the intelligent software agents with an abstraction of their physical environment.…”

Section: Evaluation and Future Workmentioning

confidence: 99%

See 4 more Smart Citations

Semantic network management for next‐generation networks

Matheus¹,

Boran²,

Carr

et al. 2018

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

To accommodate the proliferation of heterogeneous network models and protocols, the use of semantic technologies to enable an abstract treatment of networks is proposed. Network adapters are employed to lift network specific data into a semantic representation. Semantic reasoning integrates the disparate network models and protocols into a common data model by making intelligent inferences from low-level network and device details. Automatic discovery of new devices, monitoring of device state, and invocation of device actions in a generic fashion that is agnostic of network types is enabled. A prototype system called SNoMAC is described that employs the proposed approach operating over UPnP, TR-069, and heterogeneous sensors. These sensors are integrated by means of a sensor middleware named SIXTH that augments the capabilities of SNoMAC to allow for intelligent management and configuration of a wide variety of sensor devices. A major benefit of this approach is that the addition of new models, protocols, or sensor types merely involves the development of a new network adapter based on an ontology. Additionally, the semantic representation of the network and associated data allows for a variety of client interfaces to facilitate human input to the management and monitoring of the system.By the year 2021, the Internet of Things (IoT) is expected to encompass 3.5 times as many connected devices as there are people on Earth. 1 In addition to the sheer volume of devices, there is the added complexity of dealing with the unchecked proliferation of new network data models and protocols. To deal with these issues, network and active media applications will not only require high performance and scalability but will also need the means for quickly and dynamically evolving to accommodate the changing universe of devices. Doing this effectively necessitates a new approach for integrating network models and protocols that facilitates the intelligent management of devices across layers and at various levels of abstraction. This allows devices to be handled generically as collections while maintaining the specifics necessary to monitor and control them individually. This paper advocates an approach to solving this problem that leverages the benefits afforded by semantic web technologies, combined with the advantages of intelligent middleware. This automates much of the organization and integration of heterogeneous devices and provides a platform upon which a wide variety of applications can be built.Semantic web technologies enable the definition of formal data models called "ontologies" that provide a number of conceptual and computational benefits. This includes data model alignment, heterogeneous data integration, built-in data abstraction mechanisms, automated inferencing, dynamic meta-modeling, and automatic consistency checking. These ontologies form the base upon which semantic tools such as SPARQL, 2 SWRL, 3 and OWL, 4 or a hybrid of these, can make intelligent inferences about both devices themselves and their networ...

show abstract

Section: Evaluation and Future Workmentioning

confidence: 99%

Section: Sixth Sensor Middlewarementioning

confidence: 99%

Section: Evaluation and Future Workmentioning

confidence: 99%

Section: The Snomac Prototypementioning

confidence: 99%

Section: Evaluation and Future Workmentioning

confidence: 99%

See 3 more Smart Citations