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：
为了提高城市交通流预测神经网络方法的快速动态学习能力,提出了一种生长自组织神经网络群,将复杂的神经网络个体分解为多个训练简单的神经网络群组,并利用设计的动态生长自组织算法来避免神经网络在学习新知识的时候对已有知识造成破坏,同时保持整个群工作的高效稳定,规模不过度扩张.该神经网络群尝试解决神经网络的一次性学习问题,具有动态知识增殖学习能力和更强的错误自修复能力及系统适应灵活性.仿真结果表明,这一方法能够更精确地实现函数逼近和城市交通流自适应动态预测,适用于需要不断快速动态学习的复杂系统.
英文摘要：
To enhance the capacity of dynamic study and real-time forecasting on urban traffic flow,this paper proposes a type of growing self-organized neural network group（GSNNG）.A complex artificial neural network（ANN） is introduced into some easy-trained ANN-groups,and the dynamic-growing self-organized algorithm is adopted to avoid the ANN damages to the acquired knowledge when it learns some new ones.The algorithm is able to maintain the stability of the whole ANN-groups,as well as the efficiency and a reasonable scale-confined.The GSNNG solves the ANN＇s problem that new knowledge affects on the old ones,which had more dynamic knowledge-increasable,errors-self-repairing and adapting capacity.Simulation results show that the GSNNG produces higher forecasting precision and stronger dynamic performance in system-identification and traffic flow forecasting.The method is fit to the complex systems which need continual dynamic-study.
同期刊论文项目
同项目期刊论文
期刊信息
位置：