Data driven knowledge extraction of materials properties
Data driven knowledge extraction of materials properties
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.
361-366
Kandola, J.S.
c976459a-d502-4688-b741-334c06796ca8
Gunn, S.R.
306af9b3-a7fa-4381-baf9-5d6a6ec89868
Sinclair, I.
b7a58838-8f58-4010-a06b-91c6512bcfaa
Reed, P.A.S.
8b79d87f-3288-4167-bcfc-c1de4b93ce17
July 1999
Kandola, J.S.
c976459a-d502-4688-b741-334c06796ca8
Gunn, S.R.
306af9b3-a7fa-4381-baf9-5d6a6ec89868
Sinclair, I.
b7a58838-8f58-4010-a06b-91c6512bcfaa
Reed, P.A.S.
8b79d87f-3288-4167-bcfc-c1de4b93ce17
Kandola, J.S., Gunn, S.R., Sinclair, I. and Reed, P.A.S.
(1999)
Data driven knowledge extraction of materials properties.
Intelligent Processing and Manufacturing of Materials, , Hawaii, United States.
.
(doi:10.1109/IPMM.1999.792507).
Record type:
Conference or Workshop Item
(Other)
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.
Text
IPMM_99
- Accepted Manuscript
More information
Published date: July 1999
Additional Information:
Accepted for Publication at IPMM 99 CD-ROM. Organisation: IEEE
Venue - Dates:
Intelligent Processing and Manufacturing of Materials, , Hawaii, United States, 1999-07-01
Organisations:
Electronic & Software Systems
Identifiers
Local EPrints ID: 252054
URI: http://eprints.soton.ac.uk/id/eprint/252054
PURE UUID: 90d90a25-d044-4e2c-b731-03da09dc10c7
Catalogue record
Date deposited: 29 Nov 2003
Last modified: 15 Mar 2024 02:45
Export record
Altmetrics
Contributors
Author:
J.S. Kandola
Author:
S.R. Gunn
Author:
I. Sinclair
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
