|
NISCAIR ONLINE PERIODICALS REPOSITORY (NOPR) >
NISCAIR PUBLICATIONS >
Research Journals >
Indian Journal of Engineering and Materials Sciences (IJEMS) >
IJEMS Vol.12 [2005] >
IJEMS Vol.12(2) [April 2005] >
| Title: | A study of applying nested hyper-rectangle learning model to concrete strength estimation |
| Authors: | Chen, Li |
| Issue Date: | Apr-2005 |
| Publisher: | CSIR |
| IPC Code: | C04B14/00 |
| Abstract: | The aim of this
paper is to demonstrate an exemplar-based nested hyper-rectangle learning model
(NHLM) and apply it to estimate the strength of high performance concrete
(HPC). The proposed model is based on the concept of seeding training data in the
Euclidean i-space (where i denotes the number of features) as
hyper-rectangles. The well-designed structures and one-shot learning procedures
of NHLM could adjust learning abilities efficiently when new examples are
added. HPC is a highly complex material, which makes modelling its behaviour a
very difficult task. Compared with a standard back-propagation neural network
(BPN), the experimental results indicate that NHLM provides a powerful tool for
estimating the strength of HPC. |
| Page(s): | 117-121 |
| ISSN: | 0975-1017 (Online); 0971-4588 (Print) |
| Source: | IJEMS Vol.12(2) [April 2005]
|
|
