The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS
Transactions ID Number: 28-387
Full Name: Pero Radonja
Position: Associate Professor
Age: ON
Sex: Male
Address: Kneza Viseslava 3, 11030 Belgrade
Country: YUGOSLAVIA
Tel: +381 11 3553 355
Tel prefix: +381 11
Fax: +381 11 2545 969
E-mail address: radonjap@eunet.yu
Other E-mails: stankovic@etf.bg.ac.yu
Title of the Paper: A Generalized Profile Function Model Based on Artificial Intelligence
Authors as they appear in the Paper: Pero Radonja, Srdjan Stankovic, and Dragana Drazic
Email addresses of all the authors: radonjap@eunet.yu , stankovic@etf.bg.ac.yu , drazicd@yubc.net
Number of paper pages: 10
Abstract: A generalized profile function model (GPFM) provides an approximation of individual profile functions of the objects (trees) in a region. It is shown in this paper that this generalized model can be successfully derived using artificial computational intelligence, that is, neural networks. The generalized model (GPFM) is obtained as a mean value of all the available normalized individual profile functions. Generation of GPFM is performed by using the basic dataset, and verification is done by using a validation data set. As an example of the application of the proposed GSPM in volume computing, 42 objects from the same region are considered. Statistical properties of the original, measured data and estimated data based on the generalized model are presented and compared. Testing of the obtained GPFM is performed also by regression analysis. The obtained correlation coefficients between the real data and the estimated data are very high, 0.9946 for the basic !
data set and 0.9933 for the validation dataset.
Keywords: Profile function, Generalized model, Neural networks, Histogram, Scatterplot
EXTENSION of the file: .pdf
Special (Invited) Session: Artificial Computational Intelligence in Generating Generalized Profile Function Model
Organizer of the Session: 598-321
How Did you learn about congress:
IP ADDRESS: 212.200.158.176
