{"?xml":{"@version":"1.0"},"edm:RDF":{"@xmlns:dc":"http://purl.org/dc/elements/1.1/","@xmlns:edm":"http://www.europeana.eu/schemas/edm/","@xmlns:wgs84_pos":"http://www.w3.org/2003/01/geo/wgs84_pos","@xmlns:foaf":"http://xmlns.com/foaf/0.1/","@xmlns:rdaGr2":"http://rdvocab.info/ElementsGr2","@xmlns:oai":"http://www.openarchives.org/OAI/2.0/","@xmlns:owl":"http://www.w3.org/2002/07/owl#","@xmlns:rdf":"http://www.w3.org/1999/02/22-rdf-syntax-ns#","@xmlns:ore":"http://www.openarchives.org/ore/terms/","@xmlns:skos":"http://www.w3.org/2004/02/skos/core#","@xmlns:dcterms":"http://purl.org/dc/terms/","edm:WebResource":[{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:DOC-V1PFS9XD/5235acb8-970c-452c-a343-d4b9c8ae413b/PDF","dcterms:extent":"4346 KB"},{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:DOC-V1PFS9XD/cbb3606f-b550-4bc3-97cd-b50a7c4ca4e0/TEXT","dcterms:extent":"30 KB"}],"edm:TimeSpan":{"@rdf:about":"1993-2025","edm:begin":{"@xml:lang":"en","#text":"1993"},"edm:end":{"@xml:lang":"en","#text":"2025"}},"edm:ProvidedCHO":{"@rdf:about":"URN:NBN:SI:DOC-V1PFS9XD","dcterms:isPartOf":[{"@rdf:resource":"https://www.dlib.si/details/URN:NBN:SI:spr-PGKNDR0J"},{"@xml:lang":"sl","#text":"Uporabna informatika (Ljubljana)"}],"dcterms:issued":"2003","dc:creator":["Kokol, Peter","Povalej Bržan, Petra","Završnik, Jernej"],"dc:format":[{"@xml:lang":"sl","#text":"letnik:11"},{"@xml:lang":"sl","#text":"številka:3"},{"@xml:lang":"sl","#text":"str. 131-137"}],"dc:identifier":["ISSN:1318-1882","COBISSID_HOST:8301334","URN:URN:NBN:SI:doc-V1PFS9XD"],"dc:language":"sl","dc:publisher":{"@xml:lang":"sl","#text":"Slovensko društvo Informatika"},"dc:subject":[{"@xml:lang":"en","#text":"attributes"},{"@xml:lang":"en","#text":"classification models"},{"@xml:lang":"sl","#text":"gradnja klasifikacijskih modelov"},{"@xml:lang":"en","#text":"inteligent systems"},{"@xml:lang":"sl","#text":"inteligentni sistemi"},{"@xml:lang":"sl","#text":"medicina"},{"@xml:lang":"en","#text":"medicine"},{"@xml:lang":"en","#text":"reliability of intelligent systems"},{"@xml:lang":"sl","#text":"vhodni atributi"},{"@xml:lang":"sl","#text":"zanesljivost inteligentnih sistemov"}],"dcterms:temporal":{"@rdf:resource":"1993-2025"},"dc:title":{"@xml:lang":"sl","#text":"Dve plati uporabe inteligentnih sistemov v medicini|"},"dc:description":[{"@xml:lang":"sl","#text":"Intelligent systems have been of ten successfully applied on various fields such as business, economy, medicine, etc. They have been used for classification, diagnosing, prediction, knowledge discovery, etc. The efficiency of intelligent systems analysis very much depends on a type, format and quality of data gathered. However, the existence of appropriate relationships among attributes and outcomes and of course the selection of the right methodology is also crucial. In this paper we focused on the reliability of intelligent systems applied on a real-world problems where the benefits and drawbacks of such an analysis can be seen. With the aim of finding the most reliable solutions, different approaches for classification model construction were used. Nonetheless, the construction of reliable classification model for non-invasive determination of a blood cholesterol level proved to be unsuccessful mostly because of the lack of relationships among the attributes and the decisions. On the other hand, the use of intelligent systems analysis was very successful and reliable for diagnosing mitral valvule prolapse"},{"@xml:lang":"sl","#text":"Inteligentni sistemi se vse pogosteje uporabljajo na različnih področjih človekovega delovanja (npr. ekonomija, medicina, gospodarstvo ipd.), kjer se pogosto izkažejo kot zelo uporabna orodja. Uporabljamo jih za klasifikacijo, diagnosticiranje, predikcijo, iskanje povezav med različnimi dejavniki, odkrivanje novega znanja ipd. Na učinkovitost uporabe inteligentnih sistemov vpliva množica različnih dejavnikov (npr.: kvaliteta baze podatkov, relacije med vhodnimi in izhodnimi atributi, izbira metodologije inteligentnega sistema, vrsta in oblika podatkov ipd.), na katere imamo lahko v celotnem procesu inteligentne analize večji oz. manjši vpliv. V pričujočem prispevku smo se osredotočili na zanesljivost inteligentnih sistemov na realnih primerih s področja odločanja in diagnosticiranja, ki pokažeta prednosti in slabosti takšne analize. V procesu iskanja najkvalitetnejše rešitve smo preizkusili mnogo različnih pristopov gradnje klasifikacijskega modela (klasični, hibridni in multimetodni). Kljub vloženemu trudu se je iskanje kvalitetnega klasifikacijskega modela za neinvazivno določanje ravni holesterola v krvi izkazalo za neuspešno, saj zbrani parametri pri zbiranju podatkov (vhodni atributi) očitno niso dajali zadostne informacije o ravni holesterola v krvi. Nasprotno pa se je uporaba inteligentnih sistemov za pomoč pri diagnosticiranju prolapsa mitralne valvule (PMV) izkazala kot zelo učinkovita in zanesljiva"}],"edm:type":"TEXT","dc:type":[{"@xml:lang":"sl","#text":"znanstveno časopisje"},{"@xml:lang":"en","#text":"journals"},{"@rdf:resource":"http://www.wikidata.org/entity/Q361785"}]},"ore:Aggregation":{"@rdf:about":"http://www.dlib.si/?URN=URN:NBN:SI:DOC-V1PFS9XD","edm:aggregatedCHO":{"@rdf:resource":"URN:NBN:SI:DOC-V1PFS9XD"},"edm:isShownBy":{"@rdf:resource":"http://www.dlib.si/stream/URN:NBN:SI:DOC-V1PFS9XD/5235acb8-970c-452c-a343-d4b9c8ae413b/PDF"},"edm:rights":{"@rdf:resource":"http://rightsstatements.org/vocab/InC/1.0/"},"edm:provider":"Slovenian National E-content Aggregator","edm:intermediateProvider":{"@xml:lang":"en","#text":"National and University Library of Slovenia"},"edm:dataProvider":{"@xml:lang":"sl","#text":"Slovensko društvo Informatika"},"edm:object":{"@rdf:resource":"http://www.dlib.si/streamdb/URN:NBN:SI:DOC-V1PFS9XD/maxi/edm"},"edm:isShownAt":{"@rdf:resource":"http://www.dlib.si/details/URN:NBN:SI:DOC-V1PFS9XD"}}}}