混合算法实现的RBF神经网络及在模式辨识中应用

把模糊聚类算法和RBF神经网络结合起来,得到一种基于混合算法的RBF神经网络.首先由改进的FCM算法确定神经网络结构;然后利用监督学习对网络参数进一步优化,并对输出权值调整.使网络不仅具有最优的拓扑结构,而且又具有较强的映射能力.对驾驶员的疲劳程度进行识别,得到了满意的结果.

Hybrid Algorithm-Based RBF Neural Network and Its Application on Mode Identification

A novel RBF neural network based on a hybrid algorithm was proposed. In the process of training, the structure of neural network is determined by using improved FCM algorithm, then a supervised learning scheme is used to tune the parameters of neural network fine. The proposed learning scheme estimates the minimal topology as well as increases the mapping ability of the neural network. The RBF neural network was trained and tested on the experimental data of the driver fatigue with satisfactory results.