Adaptive generalized regression neural network used for prediction of EMC

Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (6): 228-230.

• 工程与应用 • Previous Articles Next Articles

Adaptive generalized regression neural network used for prediction of EMC

ZHANG Yudong¹，WU Lenan¹，CHEN Shuwen^1，2

1.School of Information Science & Engineering，Southeast University，Nanjing 210096，China
2.Radiation Environmental Protection Consultation Center of Jiangsu Province，Nanjing 210096，China

Received:1900-01-01 Revised:1900-01-01 Online:2011-02-21 Published:2011-02-21

用于电磁兼容预测的自适应泛化回归神经网络

张煜东¹，吴乐南¹，陈书文^1，2

1.东南大学信息科学与工程学院，南京 210096
2.江苏省辐射环境保护咨询中心，南京 210096

Abstract

Abstract: To predict the Electromagnetic Compatibility（EMC） more effectively，an Adaptive Generalized Regression Neural Network（AGRNN） is proposed.It sets the smooth factor as half of the minimum data distance，and sets the bias as the reciprocal of the smooth factor.Test on simple one dimensional data shows the fitting curve of AGRNN is smoother and more adjacent to sample points no matter how data distribute.The specific example on electromagnetic coupling interference between two parallel wires demonstrates the median square error of the prediction by AGRNN is less than that of the improved BP，and the network needs no training.Thus，the proposed algorithm is valid and effective.

Key words: electromagnetic compatibility prediction, generalized regression, neural network

摘要： 为了更好地对电磁兼容进行预测，提出一种自适应泛化回归神经网络（AGRNN），与传统泛化回归神经网络（GRNN）区别在于：将光滑因子设为最小数据距离的1/2，将偏置设为光滑因子的倒数。对简单一维数据的测试表明，无论数据如何分布，AGRNN的拟合曲线均较GRNN更加接近样本点、且更平滑。以平行线间电磁耦合干扰为具体算例，证明AGRNN对训练数据与测试数据的预测优于改进BP算法，且网络不需要训练。

关键词: 电磁兼容预测, 泛化回归, 神经网络

ZHANG Yudong¹，WU Lenan¹，CHEN Shuwen^1，2. Adaptive generalized regression neural network used for prediction of EMC[J]. Computer Engineering and Applications, 2011, 47(6): 228-230.

张煜东¹，吴乐南¹，陈书文^1，2. 用于电磁兼容预测的自适应泛化回归神经网络[J]. 计算机工程与应用, 2011, 47(6): 228-230.

[1]	CHU Pengyu, LIU Lan. Short-term forecast of railway passenger traffic volume based on variable weight combination model [J]. Computer Engineering and Applications, 2017, 53(4): 228-232.
[2]	LU Xiaoyong1, YANG Hongwu2, GUO Weitong2, PEI Dong2. Prosody conversion of emotional speech based on PAD three dimensional emotion model [J]. Computer Engineering and Applications, 2013, 49(5): 230-235.
[3]	TAN Chang，XIAO Nanfeng. Static hand gesture recognition based on improved RCE neural network and RBF neural network [J]. Computer Engineering and Applications, 2011, 47(7): 172-176.
[4]	LI Kai，HAN Yanxia. Research on ensemble learning methods based on selective strategies [J]. Computer Engineering and Applications, 2011, 47(17): 26-30.
[5]	YANG Jinbao，WANG Lucai. Method for adaptive compensation of load cell’s nonlinear error [J]. Computer Engineering and Applications, 2011, 47(16): 242-245.
[6]	WEI Jing，LI Hengchao，FAN Pingzhi. Combined prediction with optimal weight for wireless communication traffic based on SOM [J]. Computer Engineering and Applications, 2011, 47(14): 73-75.

Adaptive generalized regression neural network used for prediction of EMC

用于电磁兼容预测的自适应泛化回归神经网络

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 6

Recommended Articles

Metrics