Data Driven Knowledge Extraction of Materials Properties


Kandola, J.S., Gunn, S.R., Sinclair, I. and Reed, P.A.S. (1999) Data Driven Knowledge Extraction of Materials Properties. At Intelligent Processing and Manufacturing of Materials, Hawaii, U.S.A., , 361-366.

Download

[img] Microsoft Word
Download (171Kb)

Description/Abstract

In this paper the problem of modelling a large commercial materials dataset using advanced adaptive numeric methods is described. The various approaches are briefly outlined, with an emphasis on their characteristics with respect to generalisation, performance and transparency. A highly novel Support Vector Machine (SVM) approach incorporating a high degree of transparency via a full ANalysis Of VAriance (ANOVA) expansion is also used. Using the example of predicting 0.2% proof stress from a set of materials features, we show how the different modelling techniques compare when benchmarked against independent test data.

Item Type: Conference or Workshop Item (Speech)
Additional Information: Accepted for Publication at IPMM 99 CD-ROM. Organisation: IEEE
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Electronic & Software Systems
ePrint ID: 252054
Date Deposited: 29 Nov 2003
Last Modified: 27 Mar 2014 19:53
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/252054

Actions (login required)

View Item View Item