Iranian Journal of Fisheries Sciences
مجله علوم شیلاتی ایران
IJFS
Agriculture
http://jifro.ir
1
admin
1562-2916
10.18869/acadpub.ijfs
en
jalali
1398
12
1
gregorian
2020
3
1
19
2
online
1
fulltext
en
Estimation of body weight of Sparus aurata with artificial neural network (MLP) and M5P (nonlinear regression)–LR algorithms
Stock assessment
Stock assessment
پژوهشي
Orginal research papers
In this study, morphometric features such as total length, standard length, and fork length obtained from a total of 321 <em>Sparus aurata</em> samples, including 164 females and 157 males, captured between 2012 and 2013 from İskenderun Bay were used as input value, while weight was used as an output value. The Artificial Neural Network (MLP-Multi<ins cite="mailto:levent" datetime="2018-09-03T08:41">-</ins><ins cite="mailto:levent" datetime="2018-09-03T08:42">L</ins><del cite="mailto:levent" datetime="2018-09-03T08:41"> L</del>ayer Perceptron) as well as the M5P algorithm and Linear Regression (LR) algorithm from version 3.7.11 of the WEKA Program were applied. When coefficients of correlation were assessed, the MLP algorithm for males, females and the total were calculated as 0.9686, 0.9605 and 0.9663, respectively; the M5P algorithm for males, females and the total were calculated as 0.9722, 0.9596 and 0.9735, respectively; and the LR Model for males, females and the total were calculated as 0.9777, 0.9498 and 0.9473, respectively. With respect to the Mean Absolute Error (MAE) calculations, the MLP algorithm MAE values for males, females and the total were calculated as 2.94, 2.57 and 2.7074, respectively; the M5P algorithm MAE values for males, females and the total were calculated as 2.400, 2.641 and 2.157, respectively; and the LR Model MAE values for males, females and the total were calculated as 3.217, 2.811 and 3.11, respectively. It can also be concluded from the study that, in order to predict ANN interactions Nonlinear Regression model is more effective and has better performance than the conventional models.
Weka 3.7.11, Artificial Neural Network-MLP, M5P, Sparus aurata, Morphometric feature, İskenderun Bay
541
550
http://jifro.ir/browse.php?a_code=A-10-2441-1&slc_lang=en&sid=1
L.
SANGÜN
leventsangun@gmail.com
`100319475328460033855`

100319475328460033855
Yes
Vocational School of Adana, University of Çukurova, , Çukurova-Adana, Türkiye.
O.İ.
Güney
inancguney@gmail.com
`100319475328460033856`

100319475328460033856
No
Vocational School of Adana, University of Çukurova, , Çukurova-Adana, Türkiye.
P.
Kokcu
pkokcu@cu.edu.tr
`100319475328460033857`

100319475328460033857
No
Vocational School of Adana, University of Çukurova, , Çukurova-Adana, Türkiye.
N.
Basusta
nbasusta@hotmail.com
`100319475328460033858`

100319475328460033858
No
Fisheries Faculty, Fırat University, TR-23119, Elazığ, Türkiye