摘要
文章提出了BP神经网络联合与DS证据推理相融合的模型,实现了多个领域不同层次的全部主/客观证据的特征级融合,还实现了多个模型的优势互补。解决了单一模型洪水预测问题存在的算法复杂度高,分类准确率低等问题。通过实验得出,主/客观证据融合方法不仅提高了12%的分类精度,还降低了算法的时间复杂度。
The paper presents a model by combining BP neural network and DS evidential reasoning,which not only achieves the feature level fusion of all subjective and objective evidences in various domains and layers,but also makes distinct models complement each other.The model solves these problems such as high complexity of algorithms and low accuracy rate of classifications lie in the flood prediction using single models.By the experiment,thls method improves classification precision by 12 percent and reduces the time complexity of algorithm.
出处
《计算机工程与应用》
CSCD
北大核心
2006年第12期197-199,216,共4页
Computer Engineering and Applications
基金
国家973重点基础研究发展规划资助项目(编号:G19990436)
浙江省水利厅科技项目(编号:RC0509)
关键词
洪水预测主/客观证据融合
BP神经网络
DS证据理论
flood prediction,subjective and objective evidences fusion ,BP Neural Network,DS evidential theory
