INTELIGENT SOFTWARE SYSTEM FOR METABOLIC SYNDROMEDIAGNOSTICS
| Autor: | Ivanović, Darko |
|---|---|
| Přispěvatelé: | Kupusinac, Aleksandar, Doroslovački, Rade, Ivetić, Dragan, Malbaški, Dušan, Stokić, Edita, Ćulibrk, Dubravko |
| Jazyk: | srbština |
| Rok vydání: | 2018 |
| Předmět: |
Metabolic Syndrome
Mašinsko učenje Veštačkeneuronske mreže Decision Trees Mašinsko učenje Metabolički sindrom Dijagnostika Veštačkeneuronske mreže Stabla odlučivanja Linearna regresija Linear Regression Artificial NeuralNetworks Metabolički sindrom Machine Learning Linearna regresija Stabla odlučivanja Dijagnostika Diagnostics Machine Learning Metabolic Syndrome Diagnostics Artificial NeuralNetworks Decision Trees Linear Regression |
| Zdroj: | CRIS UNS Универзитет у Новом Саду |
| Popis: | Doktorska disertacija razmatra problem algoritamske dijagnostikemetaboličkog sindroma na osnovu lako merljivih parametara: pol,starosna dob, indeks telesne mase, odnos obima struka i visine,sistolni i dijastolni krvni pritisak. U istraživanju su primenjene ieksperimentalno ispitane tri različite metode mašinskog učenja:stabla odluke, linearna regresija i veštačke neuronske mreže.Pokazano je da veštačke neuronske mreže daju visok nivoprediktivnih vrednosti dovoljan za primenu u praksi. Korišćenjemdobijenog rezultata definisan je i implementiran inteligentnisoftverski sistem za dijagnostiku metaboličkog sindroma. The doctoral dissertation examines the problem of algorithmic diagnostics ofthe metabolic syndrome based on easily measurable parameters: sex, age,body mass index, waist and height ratio, systolic and diastolic bloodpressure. In the study, three different methods of machine learning wereapplied and experimentally examined: decision trees, linear regression andartificial neural networks. It has been shown that artificial neural networksgive a high level of predictive value sufficient to be applied in practice. Usingthe obtained result, an intelligent software system for the diagnosis ofmetabolic syndrome has been defined and implemented. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|