Back to search

National Technical University of Athens (NTUA)

Χρήση γνωσιακών πρακτόρων με επίγνωση πλαισίου για τη δημιουργία κοινωνικού διαδικτύου των πραγμάτων

Abstract

dc:description

The concept of an Internet of Things (IoT) is already mature, enough to start evolving towards an Internet of Everything (IoE), over which humans, objects and virtual items can be inter- connected. For this to be feasible though, there is the need for a framework which not only supports the interconnection between the entities of this Internet, but also allows the meaningful interaction between them. In particular, the smart IoE entities should be able to exchange data and information in order to fulfill their owners’ needs. A solution to this problem constitutes Social Internet of Things (SIoT), which is the convergence of Social Networks and Internet of Things, and enables the creation of social relations between the smart objects. This thesis introduces a distributed SIoT platform that consists of cognitive software agents, which represent the IoE entities. These software agents have as goal to fulfill human needs. As a result, they consist of multiple software components capable of: (a) extracting context information from raw data, and (b) managing cognitively the social relations based on their needs, which are produced by analyzing their goals. The aforementioned components are based, respectively, in the following state-of-the-art technologies: (a) a Deep Learning model for human activity recognition, and (b) a cognitive decentralized mechanism, which utilizes the Semantic Web technologies and the Publish-Subscribe pattern. Furthermore, in order to materialize the proposed SIoT solution, two software tools were developed. The first one is called Sem-SHUI and constitutes the user’s interface (e.g., the User Agent) with the SIoT ecosystem, since it is capable of sending direct orders or injecting semantic rules that will alter the behavior of the software agents. The second one is an agent-based SIoT simulator, called ASSIST, and displays the SIoT ecosystem, i.e., the existing SIoT Agents and all the formed relationships between them. Moreover, ASSIST enables the developers to change the semantic rules concerning the service discovery and the network navigability.Finally, to test the proposed Deep Learning architecture, we used two public available HAR datasets, showing that the proposed model outperforms other state-of-the-art Deep Learning human activity recognition methods. The presented SIoT solution was examined by taking into consideration three use cases, utilizing the developed SIoT tools.

Degree

thesis:*
Grantor dc:publisher
National Technical University of Athens (NTUA)
Year dc:date
2018

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Kasnesis, Panagiotis
  • Κασνέσης, Παναγιώτης

Subjects

dc:subject × 20

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/42673

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Kasnesis, Panagiotis; Κασνέσης, Παναγιώτης. Χρήση γνωσιακών πρακτόρων με επίγνωση πλαισίου για τη δημιουργία κοινωνικού διαδικτύου των πραγμάτων. National Technical University of Athens (NTUA), 2018. http://hdl.handle.net/10442/hedi/42673