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

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.

The effect of artificial feed on blood biochemistry profile and liver histology of wild saddled bream, Oblada melanura (Sparidae)

“…On the contrary, Coz-Rakovac et al (2008) found no correlation between TP values and the fish feeding regime. The observed lower TP values in well fed O. melanura around cages are similar to those estimated for the aquaculture-affected sea bream (Coz-Rakovac et al, 2009), but any conclusions that are not supported by significant results would be very speculative. Moreover, although a difference in plasma CHOL between sampled populations was observed, its significance could not be determined due to the strong departure from normality of even log-transformed values.…”

“…However, we can just point out that observed GLU values of both saddled bream populations were lower than those estimated for the aquaculture-affected sea bream (Coz-Rakovac et al, 2009). The levels of TRIG are considered to be major indices of the health status of teleost, but they are not a reliable indicator of fish nutritional status (Wagner and Congleton, 2004).…”

“…Measurement of blood biochemistry parameters is commonly used diagnostic tool in biomonitoring and according to Coz-Rakovac et al (2008) it presents good indicator of the artificial feed effects. In order to document and better understand variability and dynamics of M A N U S C R I P T A C C E P T E D ACCEPTED MANUSCRIPT blood chemistry parameters in general, few studies were conducted on the sea bass, Dicentrarchus labrax (Coz-Rakovac et al, 2005), sea bream, Sparus aurata (Coz-Rakovac et al, 2009), bluefin tuna, Thunnus thynnus (Topic Popovic et al, 2006;2008), mullets (Coz-Rakovac et al, 2008) and salmonids (Coz-Rakovac et al, 2002) in the eastern Adriatic.…”

Overview of Smart Aquaculture System: Focusing on Applications of Machine Learning and Computer Vision

“…For instance, Coz-Rakovac et al [100] identified three aquaculture-affected species such as 120 seabass (Dicentrarchus labrax), 98 sea bream (Sparus aurata L.), and 66 mullets (Mugil spp.) thanks to biochemical data using machine learning methods.…”

“…There are 3 species which are identified based on their biochemical traits. The methodology of this study is shown in Figure 30 with decision tree and biochemistry analysis (AST, TP, TRIG, CHOL, and GLU collected from blood) [100].…”