期刊
ENVIRONMENTAL MODELLING & SOFTWARE
卷 40, 期 -, 页码 245-254出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.envsoft.2012.10.001
关键词
Supervised classification; Multi-dimensional classification; Bayesian networks; Missing imputation; Discretization; Feature subset selection; Environmental modelling; Recruitment forecasting
类别
资金
- Fundacion Centros Tecnologicos Inaki Goenaga
- Etortek
- Basque Government [TIN2010-14931]
- Spanish Ministry of Education and Science
- COMBIOMED network in computational biomedicine (Carlos III Health Institute)
- project ECOANCHOA
- Department of Agriculture, Fisheries and Food of the Basque Country Government
- MEECE [212085]
- FACTS [244966]
A multi-species approach to fisheries management requires taking into account the interactions between species in order to improve recruitment forecasting of the fish species. Recent advances in Bayesian networks direct the learning of models with several interrelated variables to be forecasted simultaneously. These models are known as multi-dimensional Bayesian network classifiers (MDBNs). Preprocessing steps are critical for the posterior learning of the model in these kinds of domains. Therefore, in the present study, a set of 'state-of-the-art' uni-dimensional pre-processing methods, within the categories of missing data imputation, feature discretization and feature subset selection, are adapted to be used with MDBNs. A framework that includes the proposed multi-dimensional supervised preprocessing methods, coupled with a MDBN classifier, is tested with synthetic datasets and the real domain of fish recruitment forecasting. The correctly forecasting of three fish species (anchovy, sardine and hake) simultaneously is doubled (from 173% to 29.5%) using the multi-dimensional approach in comparison to mono-species models. The probability assessments also show high improvement reducing the average error (estimated by means of Brier score) from 0.35 to 0.27. Finally, these differences are superior to the forecasting of species by pairs. (C) 2012 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据