Towards Distributed Learning in Internet of Things. Air Quality Monitoring Use Case

Lazrak, Noussair; Fernández-Breis, Jesualdo Tomás; Zahir, Jihad; Mousannif, Hajar

doi:10.1007/978-3-030-32213-7_12

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Challenges in achieving interoperability among IoT devices and a proposed solution leveraging ontologies and machine learning were the focus of another relevant study [57]. The authors argued that the heterogeneity of IoT devices and the lack of a standard communication protocol between them make it difficult to share data and extract useful insights from it.…”

Section: Related Workmentioning

confidence: 99%

SEDIA: A Platform for Semantically Enriched IoT Data Integration and Development of Smart City Applications

Lymperis,

Goumopoulos

2023

Future Internet

View full text Add to dashboard Cite

The development of smart city applications often encounters a variety of challenges. These include the need to address complex requirements such as integrating diverse data sources and incorporating geographical data that reflect the physical urban environment. Platforms designed for smart cities hold a pivotal position in materializing these applications, given that they offer a suite of high-level services, which can be repurposed by developers. Although a variety of platforms are available to aid the creation of smart city applications, most fail to couple their services with geographical data, do not offer the ability to execute semantic queries on the available data, and possess restrictions that could impede the development process. This paper introduces SEDIA, a platform for developing smart applications based on diverse data sources, including geographical information, to support a semantically enriched data model for effective data analysis and integration. It also discusses the efficacy of SEDIA in a proof-of-concept smart city application related to air quality monitoring. The platform utilizes ontology classes and properties to semantically annotate collected data, and the Neo4j graph database facilitates the recognition of patterns and relationships within the data. This research also offers empirical data demonstrating the performance evaluation of SEDIA. These contributions collectively advance our understanding of semantically enriched data integration within the realm of smart city applications.

show abstract

Section: Related Workmentioning

confidence: 99%