Semantic Models in IoT and eHealth Applications

Front Cover
Semantic Models in IoT and eHealth Applications
Copyright
Contents
Contributors
Acknowledgments
1 Semantic modeling for healthcare applications: an introduction
1.1 Introduction
1.2 Literature review
1.3 Background
1.3.1 Semantic web and terminology
1.3.2 Web-of-Things
1.3.3 Semantic Web-of-Things
1.3.4 IoT-based semantic models
1.3.4.1 General-purpose IoT semantic models
SSN/SOSA
SAREF ontology
Time
QUDT
1.3.4.2 Domain-specific IoT-based semantic models
1.4 Semantic modeling of data
1.4.1 Semantic annotation
1.4.2 Semantic linking
1.4.2.1 Construction of a semantic model
1.4.3 Semantic representation
1.5 Conclusions
References
2 Role of IoT and semantics in e-Health
2.1 Introduction
2.2 Internet of Things in the healthcare industry
2.2.1 Characteristics of IoT ontology and challenges in e-Health
2.2.2 Characteristics of IoT in the healthcare industry
2.2.3 Challenges of the IoT in e-Health
2.3 Middleware architectures for the IoT in e-Health
2.3.1 An overview of IoT middleware solutions
2.3.2 Middleware solutions in healthcare
2.4 Semantic interoperability of objects in e-Health
2.5 Interoperability in healthcare
2.5.1 Interoperability levels
2.5.2 Turnista's model
2.5.3 Semantic web
2.5.4 OpenEHR archetype
2.6 Conclusion
References
3 Evaluation and visualization of healthcare semantic models
3.1 Introduction and motivation
3.2 Role of visualization: background
3.2.1 Visualization concept and its cognitive capacity
3.2.2 Visualization in ICT, healthcare, and biomedical sectors
3.2.3 Basics of visualization
3.2.4 Visualization of semantic models
3.2.5 Visualization of ontology and semantic model in healthcare and (bio)medical sectors
3.2.5.1 Task-dependency of visualization
3.2.5.2 Visualization of semantic models: classification by the visualization technique
3.3 Requirement of evaluation
3.3.1 Taxonomy of the evaluation
3.3.1.1 Recommenders
3.3.1.2 Ontology evaluation tool
3.3.1.3 Ontology visualization
3.3.1.4 Briefly on other approaches
3.3.1.5 Feature-based evaluation of ontology visualization tools
3.3.1.6 Taxonomy of evaluation techniques
3.3.2 How to make a choice of a visualization tool
3.4 Discussion
3.5 Conclusion
Acknowledgments
References
4 Role of connected objects in healthcare semantic models
4.1 Introduction
4.2 The EHR ecosystem
4.2.1 OpenEHR
4.2.2 Health level seven international (HL7)
4.2.3 ISO 13606
4.2.4 Semantic models in healthcare
4.3 Connected objects in healthcare
4.3.1 Internet of things
4.3.2 Semantic sensor network
4.3.3 M2M
4.3.4 oneM2M
4.3.5 Smart appliances reference ontology
4.4 Semantic-based connected objects in e-Health
4.4.1 Semantic integration of IoT and EHR systems
4.4.2 Data-centric e-Health perspective
4.4.2.1 Modeling
4.4.2.2 Preprocessing
4.4.2.3 Persistence
4.5 Concluding remarks
References
5 The security and privacy aspects in semantic web enabled IoT-based healthcare information systems
5.1 Introduction and motivation
5.2 Security and privacy requirements in IoT
5.2.1 Security and privacy challenges in IoT
5.2.2 IoT security attacks and threats
5.3 Security and privacy concerns in IoT-based healthcare systems
5.4 Semantic web based solutions for security and privacy
5.5 Semantic web based solutions for the security and privacy aspects in the IoT ecosystem
5.5.1 Security oriented solutions
5.5.2 Privacy oriented solutions
5.6 Challenges and future directions for the security and privacy concerns in IoT-based healthcare systems
5.7 Conclusions
References
6 Knowledge-based system as a context-aware approach for the Internet of medical connected objects
6.1 Introduction
6.2 Knowledge-based system in health
6.3 Context modeling using knowledge graphs
6.4 Knowledge graphs
6.5 Integrated domain model
6.6 Discussion and conclusions
References
7 Toward a knowledge graph for medical diagnosis: issues and usage scenarios
7.1 Introduction
7.2 Related work
7.3 A knowledge graph for medical diagnosis
7.4 Issues for ontology alignment
7.4.1 Alignment between DOID and SYMP ontologies
7.4.2 Issues for ICD-10 and DOID-SYMP alignment
7.5 Usage scenarios for the medical diagnosis knowledge graph
7.5.1 Electronic health records interoperability
7.5.2 Automatic reasoning in telemedicine
7.5.3 Medical insurance management
7.6 Conclusion
References
8 A naturopathy knowledge graph and recommendation system to boost the immune system
8.1 Introduction
8.2 Related work: food knowledge graphs and recommendation systems
8.2.1 Food knowledge graphs: ontologies and data sets
8.2.2 Food recommender systems
8.2.3 Food information extraction with natural language processing: named-entity recognition
8.2.4 Shortcomings of the literature study
8.3 Naturopathy knowledge graph and recommendation system to boost immune system: knowledge-based immune system suggestion
8.3.1 Collecting food ontologies: LOV4IoT-food ontology catalog
8.3.2 Naturopathy knowledge graph: extracting and integrating food ontologies and data sets
8.3.3 Knowledge-based immune system suggestion: ontology-based food recommendation to boost the immune system
8.3.4 Evaluation
8.4 Conclusion and future work
8.5 Disclaimer
8.A Demonstrators
References
9 SAREF4EHAW-compliant knowledge discovery and reasoning for IoT-based preventive health and well-being
9.1 Introduction
9.2 Related work: ontology-based IoT project catalog for health
9.2.1 Ontology-based IoT project catalog for health with LOV4IoT-health
9.2.2 Standards: ISO and ETSI SmartM2M
9.2.2.1 ETSI SmartM2M SAREF4EHAW for e-Health/Aging-well
9.2.2.2 ISO 13606-5:2010 health informatics – electronic health record communication standards
9.2.3 Health knowledge graphs
9.3 Knowledge discovery and reasoning for preventive health and well-being
9.3.1 ETSI SmartM2M SAREF-compliant semantic sensor health dictionary
9.3.2 Ontology visualization for preventive health and well being
9.3.3 Semi-automatic knowledge extraction from preventive health and well being ontologies
9.3.3.1 Extracting specific terms from ontology code
9.3.3.2 Extracting knowledge from scientific publications
9.3.3.3 Usage of semiautomatic extraction within reasoning demonstrators
9.3.4 Knowledge discovery and reasoning for preventive health and well-being (S-LOR health)
9.3.5 Keeping track of provenance metadata
9.4 End-to-end knowledge-based health and well-being use cases
9.5 Key contributions and lessons learned
9.6 Conclusion and future work
Acknowledgments
9.A IoT-based ontologies for health
9.A.1 Ambient assisted-living (AAL)/ remote monitoring for health ontologies using IoT technologies
9.A.2 Disease-related ontologies
9.A.2.1 Cardiology-related ontologies
9.A.2.2 Diabetes and diet-related ontologies
9.A.2.3 Dementia models, ontologies or KGs: Parkinson's, Alzheimer's, etc.
9.A.3 Electronic Health Records (EHR) ontologies
9.A.4 Wearable ontologies
9.A.5 Ontologies from European projects: ACTIVAGE and HEARTFAID
9.A.6 Other ontologies
References
10 Reasoning over personalized healthcare knowledge graph: a case study of patients with allergies and symptoms
10.1 Introduction
10.2 Related work
10.3 A reasoner for personalized health knowledge graph
10.4 Implementation, results, and evaluation
10.4.1 Implementation
10.4.2 KAO ontology evaluation
10.5 Discussions and extensions for future work
10.6 Conclusion
Acknowledgments
10.A Listings: code example
10.B Tutorials: SPARQL queries and End-to-End Scenarios
References
Web references
11 Integrated context-aware ontology for MNCH decision support
11.1 Introduction
11.2 Related works
11.3 Preposition-enabled spatial ontology: PeSONT
11.3.1 Concept extraction
11.3.2 Term formalization
11.3.3 Location visualization
11.4 PeSONT documentation
11.5 Discussion
11.6 Conclusions
Acknowledgments
References
12 IntelliOntoRec: a knowledge infused semiautomatic approach for ontology formulation in healthcare and medical science
12.1 Introduction
12.2 Related works
12.3 Proposed model
12.3.1 Phase 1
12.3.2 Transformer architecture
12.3.3 Phase 2
12.3.4 Phase 3
12.4 Implementation
12.5 Results
12.6 Conclusion
References
Index
Back Cover