54
J. R. Prasad et al.
a knowledge base to solve complicated issues. Inside the knowledge-based systems
the most common application fields are: Question-Answering and Semantic Knowledge Retrieval. In Question-Answering Schemes in the Agricultural Sector, users
are informed about agricultural problems such as crops, plant diseases and insect
invasion etc. In agriculture, information retrieval systems are usually configured to
retrieve specific information about crops, pests, etc. Expansion of the keyword and
knowledge management areas in information retrievals was supported by ontology.
The agricultural realm is rapidly using remote sensing to gather data from farms
such as temperature and soil pH. Users can use that information to infer future crop
health. The semantic sensor web is the application of semantic Web technologies to
remote sensing domain. By exploiting the large sensor web, sensor web applications
can query and draw inferences. It can help farmers by providing real-time input into
decision-making systems. crop planning and production and food production are the
most popular area of decision support system. Usually the crop production programs
provide farmers with actionable knowledge that they may use to minimize crop
damage. An ontology is created using aggregated information about crops, pests,
diseases, land preparation, growing and harvesting methods that converts this information into actionable information. Decisions on food production support systems
used to: control, manage, or assist direct food production. Semantic web technologies had the role of acting as a knowledge base or assisting in the integration of data
sources. Expert systems typically infer a disease based on crop sample observations.
In these systems an ontology works as a base of knowledge from which to make
inferences [19].
6.5 Semantic Web in Healthcare
Huge amounts of data are generated on a regular basis in hospitals, clinics and other
medical institutions. Patients’ medical reports, their data monitoring and monitoring
needs to be properly managed in order to cater for better medical facilities, enhanced
healthcare services and biomedical products. While there is an overwhelming volume
of data available, it is fragmented and distributed. IOT and sematic web technologies play important role in addressing the key challenge of handling the interoperability in health related data. Internet of Things (IoT) applications residing on the
Web are the next logical development. Various ontologies are developed in healthcare domain which can be accessed from bioportal. E.g. Medical Dictionary for
Regulatory Activities Terminology (MedDRA) (MEDDRA), Current Procedural
Terminology (CPT), SNOMED CT etc. [20]. Multi-agent software systems such
as AOIS, MASE, MET4, Karthika, and Cancer Search Engine promote the exchange
of knowledge across diverse user groups linked via the Web [21]. Examples of
IOT-Semantic web-based healthcare applications are Smart Appliances REFerence
for Health (SAREF4Health), Health and Alarm Ontology, and Integrated Health
Management Technology (TIHM) etc.
J. R. Prasad et al.
a knowledge base to solve complicated issues. Inside the knowledge-based systems
the most common application fields are: Question-Answering and Semantic Knowledge Retrieval. In Question-Answering Schemes in the Agricultural Sector, users
are informed about agricultural problems such as crops, plant diseases and insect
invasion etc. In agriculture, information retrieval systems are usually configured to
retrieve specific information about crops, pests, etc. Expansion of the keyword and
knowledge management areas in information retrievals was supported by ontology.
The agricultural realm is rapidly using remote sensing to gather data from farms
such as temperature and soil pH. Users can use that information to infer future crop
health. The semantic sensor web is the application of semantic Web technologies to
remote sensing domain. By exploiting the large sensor web, sensor web applications
can query and draw inferences. It can help farmers by providing real-time input into
decision-making systems. crop planning and production and food production are the
most popular area of decision support system. Usually the crop production programs
provide farmers with actionable knowledge that they may use to minimize crop
damage. An ontology is created using aggregated information about crops, pests,
diseases, land preparation, growing and harvesting methods that converts this information into actionable information. Decisions on food production support systems
used to: control, manage, or assist direct food production. Semantic web technologies had the role of acting as a knowledge base or assisting in the integration of data
sources. Expert systems typically infer a disease based on crop sample observations.
In these systems an ontology works as a base of knowledge from which to make
inferences [19].
6.5 Semantic Web in Healthcare
Huge amounts of data are generated on a regular basis in hospitals, clinics and other
medical institutions. Patients’ medical reports, their data monitoring and monitoring
needs to be properly managed in order to cater for better medical facilities, enhanced
healthcare services and biomedical products. While there is an overwhelming volume
of data available, it is fragmented and distributed. IOT and sematic web technologies play important role in addressing the key challenge of handling the interoperability in health related data. Internet of Things (IoT) applications residing on the
Web are the next logical development. Various ontologies are developed in healthcare domain which can be accessed from bioportal. E.g. Medical Dictionary for
Regulatory Activities Terminology (MedDRA) (MEDDRA), Current Procedural
Terminology (CPT), SNOMED CT etc. [20]. Multi-agent software systems such
as AOIS, MASE, MET4, Karthika, and Cancer Search Engine promote the exchange
of knowledge across diverse user groups linked via the Web [21]. Examples of
IOT-Semantic web-based healthcare applications are Smart Appliances REFerence
for Health (SAREF4Health), Health and Alarm Ontology, and Integrated Health
Management Technology (TIHM) etc.