Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/116118
DC Field | Value | |
---|---|---|
dc.title | Signaling the shift and identifying its source in bivariate spc | |
dc.contributor.author | Hwarng, H.B. | |
dc.date.accessioned | 2014-12-12T07:36:34Z | |
dc.date.available | 2014-12-12T07:36:34Z | |
dc.date.issued | 2005 | |
dc.identifier.citation | Hwarng, H.B. (2005). Signaling the shift and identifying its source in bivariate spc. Proceedings of the 35th International Conference on Computers and Industrial Engineering, ICC and IE 2005 : 953-958. ScholarBank@NUS Repository. | |
dc.identifier.isbn | 9755612653 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/116118 | |
dc.description.abstract | In multivariate statistical process control, the convenience of summarizing the behavior of multiple variables of interest in one single statistic, e.g., T2, does not relieve the need for pinpointing the source of the out-of-control signal. In this paper we demonstrate the possibility of simultaneously identifying the shift and the source of the shift in a bivariate process using neural networks. In addition to the ability to indicate the source variable(s) of shifts, average run length produced by the neural-network based identifier shows that the performance of the network identifier is superior to that of Hotelling T2chart for small to medium shifts. | |
dc.source | Scopus | |
dc.subject | Bivariate | |
dc.subject | Control charts | |
dc.subject | Hotelling t 2 chart | |
dc.subject | Multivariate SPC | |
dc.subject | Neural networks | |
dc.type | Conference Paper | |
dc.contributor.department | DECISION SCIENCES | |
dc.description.sourcetitle | Proceedings of the 35th International Conference on Computers and Industrial Engineering, ICC and IE 2005 | |
dc.description.page | 953-958 | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.