Show simple item record

dc.contributor.authorYu, Hong Qingen
dc.contributor.authorZhao, Xiaen
dc.contributor.authorZhen, Xinen
dc.contributor.authorDong, Fengen
dc.contributor.authorLiu, Enjieen
dc.contributor.authorClapworthy, Gordon J.en
dc.date.accessioned2015-01-18T11:23:48Z
dc.date.available2015-01-18T11:23:48Z
dc.date.issued2014-08
dc.identifier.citationH Q Yu, X Zhao, X Zhen, F Dong, E Liu, G J Clapworthy, (2014) 'Healthcare-event driven semantic knowledge extraction with hybrid data repository'. 4th International Conference on Innovative Computing Technology (INTECH 2014), University of Bedfordshire, Luton 13-15 August.en
dc.identifier.doi10.1109/INTECH.2014.6927774
dc.identifier.urihttp://hdl.handle.net/10547/338510
dc.description.abstractIn this paper, we introduce a Healthcare-Event (H-event) based knowledge extraction approach on a hybrid data repository. The repository collects (with individual user's permission) dynamic and large volume healthcare related data from various resources such as wearable sensors, social media Web APIs and our application itself. The proposed extraction approach relies on two data processing processes. One is the data integration process to dynamically retrieving the large data using public data service APIs. The first process also generates a set of big knowledge bases and stored in NoSQL storage. This paper will focus on the second extraction process that is the H-Event based ontological knowledge extraction for detecting and monitoring user's healthcare related situations, such as medical symptoms, treatments, conditions and daily activities from the NoSQL knowledge bases. The second process can be seen as post-processing step to detect more explicit healthcare knowledge about personalised health conditions and represent the knowledge using RDF formats in a semantic triple repository to enhance further data analytics.
dc.description.sponsorshipThis work is supported in part by the European Commission under Grant FP7-ICT-9-5.2-VPH-600929 within the MyHealthAvatar project.en
dc.language.isoenen
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6927774en
dc.subjectapplication program interfacesen
dc.subjectdata integrationen
dc.subjecthealth careen
dc.subjectknowledge acquisitionen
dc.subjectH-eventen
dc.subjectNoSQL knowledge basesen
dc.subjectNoSQL storageen
dc.subjectdata integration processen
dc.subjectdata processingen
dc.subjecthealthcare-event driven semantic knowledge extractionen
dc.subjecthybrid data repositoryen
dc.subjectmedical symptomsen
dc.subjectontological knowledge extractionen
dc.subjectpersonalised health conditionsen
dc.subjectpublic data service APIen
dc.subjectsemantic triple repositoryen
dc.subjectsocial media Web APIen
dc.subjectwearable sensorsen
dc.subjectbiomedical monitoringen
dc.subjectdata miningen
dc.subjectknowledge based systemsen
dc.subjectmedical servicesen
dc.subjectmonitoringen
dc.subjectresource description frameworken
dc.subjectsemanticsen
dc.titleHealthcare-event driven semantic knowledge extraction with hybrid data repositoryen
dc.typeConference papers, meetings and proceedingsen
dc.contributor.departmentUniversity of Bedfordshireen
html.description.abstractIn this paper, we introduce a Healthcare-Event (H-event) based knowledge extraction approach on a hybrid data repository. The repository collects (with individual user's permission) dynamic and large volume healthcare related data from various resources such as wearable sensors, social media Web APIs and our application itself. The proposed extraction approach relies on two data processing processes. One is the data integration process to dynamically retrieving the large data using public data service APIs. The first process also generates a set of big knowledge bases and stored in NoSQL storage. This paper will focus on the second extraction process that is the H-Event based ontological knowledge extraction for detecting and monitoring user's healthcare related situations, such as medical symptoms, treatments, conditions and daily activities from the NoSQL knowledge bases. The second process can be seen as post-processing step to detect more explicit healthcare knowledge about personalised health conditions and represent the knowledge using RDF formats in a semantic triple repository to enhance further data analytics.


This item appears in the following Collection(s)

Show simple item record