Napredna pretraga

Pregled bibliografske jedinice broj: 369922

Classification accuracy of algorithms for blood chemistry data of three aquaculture-influenced marine fish species


Čož-Rakovac, Rozelinda; Topić Popović, Natalija; Šmuc, Tomislav; Strunjak-Perović, Ivančica; Jadan, Margita
Classification accuracy of algorithms for blood chemistry data of three aquaculture-influenced marine fish species // Fish Physiology and Biochemistry, 35 (2009), 4; 641-647 doi:10.1007/s10695-008-9288-0 (međunarodna recenzija, članak, znanstveni)


Naslov
Classification accuracy of algorithms for blood chemistry data of three aquaculture-influenced marine fish species

Autori
Čož-Rakovac, Rozelinda ; Topić Popović, Natalija ; Šmuc, Tomislav ; Strunjak-Perović, Ivančica ; Jadan, Margita

Izvornik
Fish Physiology and Biochemistry (0920-1742) 35 (2009), 4; 641-647

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Machine learning techniques; sea bass; sea bream; mullet; plasma biochemistry

Sažetak
The aim of this study was determination and discrimination of biochemical data between three aquaculture-influenced marine fish species (sea bass, Dicentrarchus labrax ; sea bream, Sparus aurata L ; mullet, Mugil spp.) based on machine learning methods. The approach relying on machine learning methods gives more usable classification solutions and provides better insight into the collected data. So far, these new methods were applied to the problem of discrimination of blood chemistry data with respect to season and feed of one single species. This is the first time that these classification algorithms were used as a framework for rapid differentiation between three fish species. Among the machine learning methods used, decision trees provided the clearest model, which correctly classified 210 samples or 85.71 %, and incorrectly classified 35 samples or 14.29 % and clearly identified three investigated species regarding to their biochemical traits.

Izvorni jezik
Engleski

Znanstvena područja
Biologija, Veterinarska medicina, Poljoprivreda (agronomija)



POVEZANOST RADA


Projekt / tema
098-0000000-3168 - Strojno učenje prediktivnih modela u računalnoj biologiji (Tomislav Šmuc, )
098-1782739-2749 - Substanična biokemijska i filogenetska raznolikost tkiva riba, rakova i školjaka (Rozelinda Čož-Rakovac, )

Ustanove
Institut "Ruđer Bošković", Zagreb

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus
  • MEDLINE


Citati