Abstract
The objective of this study was determination and discrimination of biochemical data among three aquaculture-affected marine fish species (sea bass, Dicentrarchus labrax; sea bream, Sparus aurata L., and 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 have been applied to the problem of discrimination of blood chemistry data with respect to season and feed of a single species. This is the first time these classification algorithms have been used as a framework for rapid differentiation among 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 from their biochemical traits.
This is a preview of subscription content, access via your institution.
References
Adham KG, Ibrahim HM, Hamed SS, Saleh RA (2002) Blood chemistry of the Nile tilapia, Oreochromis niloticus (Linnaeus, 1757) under the impact of water pollution. Aquat Ecol 36:549–557. doi:10.1023/A:1021137122046
Breiman L (2001) Random forests. Mach Learn J 45:5–32. doi:10.1023/A:1010933404324
Burtis CA, Ashwood ER, Aldrich JE (1996) Tietz fundamentals of clinical chemistry. WB Saunders, Philadelphia, PA
Christofilogiannis P (1993) The veterinary approach to sea bass and sea bream. In: Brown L (ed) Aquaculture for veterinarians. Pergamon Press, Oxford, pp 379–395
Cowey CB, Walton MJ (1989) Intermediary metabolism. In: Halver JE (ed) Fish Nutrition, 2nd edn. Academic Press, New York, pp 259–329
Coz-Rakovac R, Strunjak-Perovic I, Topic Popovic N, Hacmanjek M, Simpraga M, Teskeredzic E (2002) Health status of wild and cultured sea bass in the northern Adriatic sea. Vet Med 47(8):222–226
Coz-Rakovac R, Strunjak-Perovic I, Hacmanjek M, Topic Popovic N, Lipej Z, Sostaric B (2005) Blood chemistry and histological properties of wild and cultured sea bass (Dicentrarchus labrax) in the north Adriatic sea. Vet Res Commun 29:677–687. doi:10.1007/s11259-005-3684-z
Coz-Rakovac R, Strunjak-Perovic I, Topic Popovic N, Hacmanjek M, Smuc T, Jadan M, Lipej Z, Homen Z (2008) Cage culture effects on mullets (Mugilidae) liver histology and blood chemistry profile. J Fish Biol 72:1–13. doi:10.1111/j.1095-8649.2008.01865.x
Goede RW, Barton BA (1990) Organismic indices and an autopsy-based assessment as indicators of health and condition in fish. In: Adams SM (ed) American fisheries symposium 8. American Fisheries Society, Bethesda, Maryland, pp 93–109
Hill S (1982) A literature review of the blood chemistry of rainbow trout Salmo gairdneri. J Fish Biol 20:535–569. doi:10.1111/j.1095-8649.1982.tb03954.x
Hrubec TC, Smith SA, Robertson JL (2001) Age related changes in haematology and plasma chemistry values of hybrid striped bass (Morone chysops, Morone saxatilis). Vet Clin Pathol 30:8–15. doi:10.1111/j.1939-165X.2001.tb00249.x
Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159–174. doi:10.2307/2529310
Mitchell T (1997) Machine learning. McGraw Hill, New York, USA
Nagakawa H, Tetsuya U, Hideyuki M (1999) Effect of feeding regime on biological and biochemical parameters in ayu. Fish Sci 65(2):259–263
Rehulka J (2003) Haematological analyses in rainbow trout Oncorhynchus mykiss affected by viral haemorrhagic septicaemica (VHS). Dis Aquat Organ 56:185–193. doi:10.3354/dao056185
Strunjak-Perovic I, Coz-Rakovac R, Topic Popovic N, Jadan M (2008) Seasonality of nuclear abnormalities in gilthead sea bream Sparus aurata (L.) erythrocytes. Fish Physiol Biochem (in press)
Topic G, Smuc T, Sojat Z, Skala K (2005) Reimplementation of the random forest algorithm. In: Vajtersic M, Trobec R, Zinterhof P, Uhl A (eds) Proceedings of parallel numerics. theory and applications. JSI Publisher, Salzburg, pp 119–128
Topic Popovic N, Strunjak-Perovic I, Coz-Rakovac R, Hacmanjek M, Jadan M (2006) Comparison of five tuna plasma analytes measured on two automated blood analyzers. Fish Physiol Biochem 32:99–103. doi:10.1007/s10695-006-0001-x
Witten IH, Frank E (1999) Data mining: practical machine learning tools and techniques with java implementations. Morgan Kaufmann, San Francisco, CA
Wood ME, Yasutake W, Halver JE, Woodall AN (1990) Chemical and histological studies of wild and hatchery salmon in fresh water. Trans Am Fish Soc 89:301–307. doi:10.1577/1548-8659(1960)89[301:CAHSOW]2.0.CO;2
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Coz-Rakovac, R., Topic Popovic, N., Smuc, T. et al. Classification accuracy of algorithms for blood chemistry data for three aquaculture-affected marine fish species. Fish Physiol Biochem 35, 641–647 (2009). https://doi.org/10.1007/s10695-008-9288-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10695-008-9288-0
Keywords
- Machine-learning techniques
- Sea bass
- Sea bream
- Mullet
- Plasma biochemistry