基于免疫进化算法的贝叶斯网络预测网箱转移周期

以象山港网箱养殖区2000～2006年的监测数据作为训练数据，结合专家知识采用基于免疫进化的贝叶斯网络结构增量式学习算法，构建了海底网箱转移的贝叶斯网络预测模型。该模型能有效的揭示出网箱养殖环境各个指标之间的因果关系，进而可以对指定的网箱养殖的网箱转移周期进行预测和决策。结果表明，评价的准确性是91．7％，证明该方法是有效可行的。

Predicting the shift cycle of the net-cage by the Bayesian network based on immune evolutionary algorithms

By taking the monitoring data of Xiangshan Bay from the year of 2000 to 2006 as the training data and referring to the prior knowledge,a Bayesian network was constructed through the incremental learning based on the immune heredity algorithm. The model can effectively express the causal relationship among the various indicators in the net-cage aquaculture environment, and the shift cycle of the net-cage aquaculture at Xiangshan can be predicted. The result showed that the appraisal accuracy reached 91.7%, which meant that this method is feasible.