Using machine learning algorithms to analyse the scute structure and sex identification of sterlet Acipenser ruthenus (Acipenseridae)

Abstract

Sturgeons are valued as specialty black caviar, which is very expensive. Only females are used in the technology of caviar aquaculture. Universal method of sex determination has not yet been developed. Most of known methods are not sufficiently accurate, or used at a relatively late age, or difficult to use. Perfect early determination of sex is considered to be impossible. Because of the dark colour of most sturgeons and important morphological differences, which fish of almost all ages have, were overlooked. We first found that the scute structure of sterlet sturgeon depends on the sex. The found dependencies with the help of machine learning algorithms open a possibility for creation of sex determination equipment using the artificial intelligence. Our results open a perspective for creation of sex determination methods for other 23 sturgeon species, which can increase the efficiency of caviar aquaculture and restoration of sturgeons in natural waters.

Artificial Intelligence-Based Aquaculture System for Optimizing the Quality of Water: A Systematic Analysis

“…Supervised learning is used for classification and regression as a learning method with a model that maintains the object's value. Citing the theory of machine learning and its advantages, several theories have been implemented in aquaculture, for example, the detection of fish biomass [51,52], calculation of fish size [53] and weight [54][55][56], individual counting [57], fish recognition [58], age detection [59], sex detection [60], fish species classification [61][62][63], feeding behavior [64], univariate prediction [65,66], and multivariate prediction [67], with high accuracy. Regarding artificial vision processes, the documents that make intelligent diagnoses of possible fish diseases will be addressed, ensuring their well-being and health and thus preventing the death of the species.…”

Artificial intelligence in aquaculture: basis, applications, and future perspectives

“…La identificación del sexo en los peces y su separación en espacios diferentes es una actividad importante que asegura la sostenibilidad de semilla para la acuicultura, mantener un plantel de reproductores machos y hembras es prioridad para proyectar la producción de semilla. Según Barulin (2019), la perfecta determinación temprana del sexo se considera imposible.…”

Using machine learning technique for disease outbreak prediction in rainbow trout ( Oncorhynchus mykiss ) farms

“…In addition, it has been reported that water quality parameters can be predicted with artificial intelligence applications (Yeon et al, 2008). Moreover, biomass detection (Yang et al, 2021), weight estimation (Fernandes et al, 2020), fish size estimation (Li et al, 2020) and sex identification (Barulin, 2019) can be successfully evaluated by using the ML methods.…”

“…Aquaculture applications with machine learning (ML) techniques have the potential to offer solutions to the problems that develop in the production process (Liakos et al, 2018; Samuel, 2000). In this regard, many studies on fish size (Li et al, 2020) and weight estimation (Fernandes et al, 2020), biomass detection (Yang et al, 2021) and sex discrimination (Barulin, 2019) were reported. Furthermore, the dissolved oxygen concentration of water (Cao et al, 2020; Huan et al, 2020; Ren et al, 2020) was successfully predicted.…”