Comparison of Generalized Profile Function Models Based on Linear Regression and Neural Networks

被引：0

作者：

Radonja, Pero ^{[1
]}

机构：

[1] Inst Forestry, Div Forest Management & Police, Belgrade 11030, Serbia

来源：

ELEVENTH SYMPOSIUM ON NEURAL NETWORK APPLICATIONS IN ELECTRICAL ENGINEERING (NEUREL 2012) | 2012年

关键词：

Neural networks; Linear regression; Generalized models; Profile function; Generalized profile function models;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, the generalized profile function models, GPFMs, based on linear regression and neural networks, are compared. GPFM provides an approximation of individual models (models of individual stem profile) facility using only two basic measurements. GPFM based on neural network is obtained as the average of all available normalized individual models. It is shown that the application of neural networks provides a generalized model with good performance.

引用

页数：6

共 18 条

[1] [Anonymous], NEURAL NETWORK TOOLB
[2] [Anonymous], 1994, Neural networks: a comprehensive foundation
[3] BRINK C, 1986, EDV in Medizin und Biologie, V17, P20
[4] Hui GY, 1997, FORSTWISS CENTRALBL, V116, P315, DOI 10.1007/BF02766907
[5] KOROL M, 2003, FORSTW CBL, V122, P1
[6] Matovic B., 2007, ALLGEMEINE FORST JAG, p[7/8, 150]
[7] MAUNAGA Z, 1995, THESIS FACULTY FORES
[8] Pero Radonja, 2008, P 9 SEM NEUR NETW AP, P171
[9] Pero Radonja, 2006, P 8 SEM NEUR NETW AP, P189
[10] Radonja Pero, 2008, WSEAS Transactions on Systems, V7, P1186

← 1 2 →