Solving Capelin Time Series Ecosystem Problem using Hybrid Artificial Neural Networks- Genetic Algorithms Model
The Capelin stock in the Barents Sea is the largest in the world. It maintained a fishery with annual catches of up to 3 million tons. The Capelin stock problem has an impact in fish stock development. In this paper, the stock prediction problem of the Barents Sea capelin is attacked using Artificia...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.206.3983 http://www.ijcaonline.org/volume19/number2/pxc3873046.pdf |
Summary: | The Capelin stock in the Barents Sea is the largest in the world. It maintained a fishery with annual catches of up to 3 million tons. The Capelin stock problem has an impact in fish stock development. In this paper, the stock prediction problem of the Barents Sea capelin is attacked using Artificial Neural Network (ANNs) and Multiple Linear model Regression (MLR) model. The weights of ANNs are adapted using the Genetic Algorithm (GA).The models are compared against each other and empirical work has shown that the ANN-GA model can have better overall accuracy over (MLR). It performs 21 % over MLR model. |
---|