Nonlinear Regression for Analog Data based on BP Neural Network

被引：0

作者：

Jiang, Yin-Zhen ^{[1
]}

Wang, Yi-Huai ^{[1
]}

机构：

[1] Soochow Univ, Inst Comp Sci & Technol, Suzhou, Peoples R China

来源：

2010 INTERNATIONAL COLLOQUIUM ON COMPUTING, COMMUNICATION, CONTROL, AND MANAGEMENT (CCCM2010), VOL I | 2010年

关键词：

Embedded system; Analog data collection; BP neural networks; Nonlinear regression;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In order to solve the nonlinear regression problem in analog data collection system and achieve nonlinear analog correction by programming, a design method based on artificial neural network (ANN) is presented. After analyzing the lack of other regression methods, Error back-propagation (BP) algorithm is selected. The software on PC is designed to verify the feasibility and effectiveness of the BP algorithm, which is compared to least squares (LS) algorithm.

引用

页码：245 / 248

页数：4

共 8 条

[1] Backpropagation algorithms for a broad class of dynamic networks
De Jesus, Orlando
Hagan, Martin T.
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (01): : 14 - 27
[2] A modified backpropagation training algorithm for feedforward neural networks
Kathirvalavakumar, T
Thangavel, P
[J]. NEURAL PROCESSING LETTERS, 2006, 23 (02) : 111 - 119
[3] Khanna T., 1990, FDN NEURAL NETWORKS
[4] NONLINEAR MODELS OF TEMPERATURE SENSOR DYNAMICS
MINKINA, W
[J]. SENSORS AND ACTUATORS A-PHYSICAL, 1992, 30 (03) : 209 - 214
[5] Tzu C R, 2003, NEUROCOMPUTING, V50, P237
[6] WANG Yihuai, 2004, COMPUTER ENG APPL, V12, P79
[7] Yu X A, 2001, P IEEE INT S CIRC SY, P700
[8] Zhi H, 2006, IEEE T NEURAL NETWOR, V17, P1580

← 1 →