Staff View: Recipe generation from small samples by weighted kernel regression

Recipe generation from small samples by weighted kernel regression

The cost of experimental setup during an assembly process development of a chipset, particularly the under-fill process, can often result in insufficient data samples. In INTEL Malaysia, for example, the historical chipset data from an under fill process consists of only a few samples. As a result,...

Full description

Saved in:

Bibliographic Details
Main Authors:	Shapiai, Mohd. Ibrahim, Ibrahim, Zuwairie, Khalid, Marzuki
Format:	Book Section
Published:	IEEE 2011
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://eprints.utm.my/id/eprint/29575/ http://dx.doi.org/10.1109/ICMSAO.2011.5775473
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utm.29575
record_format	eprints
spelling	my.utm.295752017-02-05T00:01:47Z http://eprints.utm.my/id/eprint/29575/ Recipe generation from small samples by weighted kernel regression Shapiai, Mohd. Ibrahim Ibrahim, Zuwairie Khalid, Marzuki TK Electrical engineering. Electronics Nuclear engineering The cost of experimental setup during an assembly process development of a chipset, particularly the under-fill process, can often result in insufficient data samples. In INTEL Malaysia, for example, the historical chipset data from an under fill process consists of only a few samples. As a result, existing machine learning algorithms for predictive modeling cannot be applied to this setting. Despite this challenge, the use of data driven decisions remains critical for further optimization of this engineering process. In this study, a weighted kernel regression (WKR) is introduced to improve the predictive modeling in the setting with limited data samples. In the proposed framework, the original Nadaraya-Watson kernel regression (NWKR) algorithm is modified. Even though only four samples are used during the training stage of our experiment, the proposed approach is able to provide an accurate prediction within the engineer’s requirements as compared with other existing predictive modelings including NWKR and artificial neural networks with back-propagation algorithm (ANNBP). Thus, the proposed approach is beneficial for recipe generation in an assembly process development. IEEE 2011 Book Section PeerReviewed Shapiai, Mohd. Ibrahim and Ibrahim, Zuwairie and Khalid, Marzuki (2011) Recipe generation from small samples by weighted kernel regression. In: 2011 4th International Conference on Modeling, Simulation and Applied Optimization, ICMSAO 2011. IEEE, Kuala Lumpur. ISBN 978-1-4577-0005-7 http://dx.doi.org/10.1109/ICMSAO.2011.5775473 10.1109/ICMSAO.2011.5775473
institution	Universiti Teknologi Malaysia
building	UTM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Malaysia
content_source	UTM Institutional Repository
url_provider	http://eprints.utm.my/
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Shapiai, Mohd. Ibrahim Ibrahim, Zuwairie Khalid, Marzuki Recipe generation from small samples by weighted kernel regression
description	The cost of experimental setup during an assembly process development of a chipset, particularly the under-fill process, can often result in insufficient data samples. In INTEL Malaysia, for example, the historical chipset data from an under fill process consists of only a few samples. As a result, existing machine learning algorithms for predictive modeling cannot be applied to this setting. Despite this challenge, the use of data driven decisions remains critical for further optimization of this engineering process. In this study, a weighted kernel regression (WKR) is introduced to improve the predictive modeling in the setting with limited data samples. In the proposed framework, the original Nadaraya-Watson kernel regression (NWKR) algorithm is modified. Even though only four samples are used during the training stage of our experiment, the proposed approach is able to provide an accurate prediction within the engineer’s requirements as compared with other existing predictive modelings including NWKR and artificial neural networks with back-propagation algorithm (ANNBP). Thus, the proposed approach is beneficial for recipe generation in an assembly process development.
format	Book Section
author	Shapiai, Mohd. Ibrahim Ibrahim, Zuwairie Khalid, Marzuki
author_facet	Shapiai, Mohd. Ibrahim Ibrahim, Zuwairie Khalid, Marzuki
author_sort	Shapiai, Mohd. Ibrahim
title	Recipe generation from small samples by weighted kernel regression
title_short	Recipe generation from small samples by weighted kernel regression
title_full	Recipe generation from small samples by weighted kernel regression
title_fullStr	Recipe generation from small samples by weighted kernel regression
title_full_unstemmed	Recipe generation from small samples by weighted kernel regression
title_sort	recipe generation from small samples by weighted kernel regression
publisher	IEEE
publishDate	2011
url	http://eprints.utm.my/id/eprint/29575/ http://dx.doi.org/10.1109/ICMSAO.2011.5775473
_version_	1643648330088054784
score	13.211869

Recipe generation from small samples by weighted kernel regression

Similar Items