欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为解决多属性决策中的高维、非线性问题，提出一种基于粗糙集和遗传神经网络的智能多属性决策方法．利用粗糙集对多属性决策问题的条件属性进行约简，用遗传算法直接训练神经网络的权重形成遗传神经网络，约简后的属性数据进入遗传神经网络的智能决策系统．实证结果表明，该方法具有较好的泛化能力，与标准支持向量机方法相比，该方法具有一定的优势．
英文摘要：
An intelligent method based on rough sets （RS）, genetic algorithm （GA） and artificial neural network （ANN）, i. e, RSGAANN was developed to solve the problems of high dimension and nonlinearity in multiple attribute decision making （MADM）. RS was used for attribute selection to reduce the complexity of ANN and improve its speed, and GA was used to train the weights of ANN to constitute a GAANN model, and then the reduced data was introduced into GAANN to obtain the results of decision making. The empirical results reveal that RSGAANN method has better generalization ability. Compared with the standard SVM, RSGAANN has some superiority in respect of predicting accuracy.
同期刊论文项目
同项目期刊论文
期刊信息
位置：