Machine learning in the Internet of Things: A semantic-enhanced approach

@article{Ruta2019MachineLI,
  title={Machine learning in the Internet of Things: A semantic-enhanced approach},
  author={Michele Ruta and Floriano Scioscia and Giuseppe Loseto and Agnese Pinto and Eugenio Di Sciascio},
  journal={Semantic Web},
  year={2019},
  volume={10},
  pages={183-204}
}
Novel Internet of Things (IoT) applications and services rely more and more on an intelligent understanding of the environment from data gathered via heterogeneous sensors and micro-devices. Though increasingly effective, Machine Learning (ML) techniques generally do not go beyond classification of events with opaque labels, lacking meaningful representation and explanation of taxonomies. This paper proposes a framework for a semantic-enhanced data mining on sensor streams, amenable to resource… 

Figures and Tables from this paper

Survey on IoT Data Analytics with Semantic Approaches
TLDR
This study identifies the opportunity resulting from the convergence of the Semantic Web and IoT data analytics, and takes a broad view of current IoT analytics work whereSemantic Web approaches aim to solve the semantic interoperability by exploring recent studies in IoT systems.
Automatic Knowledge Extraction to Build Semantic Web of Things Applications
TLDR
This work designed knowledge extraction for the WoT to automatically identify the most important topics from literature ontologies of three different IoT application domains to utilize domain-specific knowledge encoded within IoT publications.
A Review of Semantic Sensor Technologies in Internet of Things Architectures
TLDR
The explored trends show that ontologies will play an even more essential role in interlinked IoT systems as interoperability and the generation of controlled linkable data sources should be based on semantically enriched sensory data.
Osmotic Cloud-Edge Intelligence for IoT-Based Cyber-Physical Systems
TLDR
A Cloud-Edge AI microservice architecture based on Osmotic Computing principles is proposed, enabling training and inference on the Edge, Cloud, or both, exploiting computational resources opportunistically to reach the best prediction accuracy.
Machine learning and data analytics for the IoT
TLDR
This paper critically review how IoT-generated data are processed for machine learning analysis and highlights the current challenges in furthering intelligent solutions in the IoT environment and proposes a framework to enable IoT applications to adaptively learn from other IoT applications.
How to Understand Better "Smart Vehicle"? Knowledge Extraction for the Automotive Sector Using Web of Things
TLDR
The innovative Knowledge Extraction for the Automotive Sector (KEAS) methodology analyzes what are the most popular terms required to build a smart car and provides a set of keyphrase that are synonyms to smart cars to find domain-specific knowledge.
Reinforcement Learning Concepts Ministering Smart City Applications Using IoT
TLDR
This chapter studies and infers machines learning from data and observations, self-learning for robots, learning culture, humanity, emotions and ethics, (self)-learning affect services and the authors' lives in future cities, and risks to humanity and cities.
Internet of Everything (IoE) Taxonomies: A Survey and a Novel Knowledge-Based Taxonomy
TLDR
This present work represents the most comprehensive taxonomy that provides the orchestration of intelligence in network connections concerning knowledge processes, type of IoE enablers, observation characteristics, and technological capabilities in IoE applications.
A multiplatform reasoning engine for the Semantic Web of Everything
A Framework for Context-Dependent Augmented Reality Applications Using Machine Learning and Ontological Reasoning
TLDR
A framework that combines machine learning services for object recognition with ontological reasoning for determining the current situation of a user based on sensor data and deriving according actions for information display is described.
...
...

References

SHOWING 1-10 OF 78 REFERENCES
A Practical Evaluation of Information Processing and Abstraction Techniques for the Internet of Things
TLDR
A survey of the requirements and solutions and challenges in the area of information abstraction and an efficient workflow to extract meaningful information from raw sensor data based on the current state-of-the-art in this area are provided.
Towards a Semantic Web of Things: A Hybrid Semantic Annotation, Extraction, and Reasoning Framework for Cyber-Physical System
TLDR
The semantic Web of Things (SWoT) framework for CPS ( SWoT4CPS) is proposed, which provides a hybrid solution with both ontological engineering methods by extending SSN and machine learning methods based on an entity linking (EL) model.
Resource Annotation, Dissemination and Discovery in the Semantic Web of Things: A CoAP-Based Framework
  • M. Ruta, F. Scioscia, G. Loseto
  • Computer Science
    2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing
  • 2013
TLDR
A novel SWoT framework is proposed, based on a backward-compatible extension of the Constrained Application Protocol (CoAP), supporting non-standard inference services for semantic matchmaking, that allows retrieval and logic-based ranking of annotated resources.
Automated discovery and integration of semantic urban data streams: The ACEIS middleware
Semantic Framework of Internet of Things for Smart Cities: Case Studies
TLDR
A semantic framework that integrates the IoT with machine learning for smart cities is proposed and retrieves and models urban data for certain kinds of IoT applications based on semantic and machine-learning technologies.
A Mobile Matchmaker for the Ubiquitous Semantic Web
TLDR
Mini-ME is presented, a novel mobile inference engine designed from the ground up for the Semantic Web of Things SWoT and implements both standard subsumption, satisfiability, classification and non-standard abduction, contraction, covering inference services for moderately expressive knowledge bases.
Mining the Semantic Web
TLDR
It is argued that machine learning research has to offer a wide variety of methods applicable to different expressivity levels ofSemantic Web knowledge bases: ranging from weakly expressive but widely available knowledge bases in RDF to highly expressive first-order knowledge bases, this paper surveys statistical approaches to mining the Semantic Web.
Context-aware Distributed Complex Event Processing Method for Event Cloud in Internet of Things
TLDR
A high performance distributed context-aware CEP architecture and method that can support fuzzy context in CEP and have acceptable performance and scalability is proposed for internet of things.
Sensor-based Linked Open Rules (S-LOR): An Automated Rule Discovery Approach for IoT Applications and its use in Smart Cities
TLDR
An automated rule discovery approach for IoT device data (S-LOR: Sensor-based Linked Open Rules) and its use in smart cities and its main capability is demonstrated in the context of enabling semantics-based reasoning mechanisms and tools according to application-demand and user requirements.
A Semantics-based Approach to Machine Perception
TLDR
This dissertation presents a semantics-based machine perception framework to address issues of too much data and not enough knowledge, and efficient algorithms for the machine perception inference tasks to enable interpretation of sensor data on resource-constrained devices, such as smart phones.
...
...