Feature Reduction and Selection for Use in Machine Learning for Manufacturing

Duaa Alrufaihi; Omogbai Oleghe; Mohammed Almanei; Sandeep Jagtap; Konstantinos Salonitis

doi:10.3233/ATDE220605

Feature Reduction and Selection for Use in Machine Learning for Manufacturing

Duaa Alrufaihi, Omogbai Oleghe, Mohammed Almanei, Sandeep Jagtap, Konstantinos Salonitis

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

In a complex manufacturing system such as the multistage manufacturing system, maintaining the quality of the products becomes a challenging task. It is due to the interconnectivity and dependency of factors that can affect the final product. With the increasing availability of data, Machine Learning (ML) approaches are applied to assess and predict quality-related issues. In this paper, several ML algorithms, including feature reduction/selection methods, were applied to a publicly available multistage manufacturing dataset to predict the characteristic of the output measurements in (mm). A total of 24 prediction models were produced. The accuracy of the prediction models and the execution time were the evaluation metrics. The results show that uncontrolled variables are the most common features that have been selected by the selection/reduction methods suggesting their strong relationship to the quality of the product. The performance of the prediction models was heavily dependent on the ML algorithm.

Original language	English
Title of host publication	Advances in Manufacturing Technology XXXV
Subtitle of host publication	Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research
Editors	Mahmoud Shafik, Keith Case
Publisher	IOS Press
Pages	289-296
Number of pages	8
ISBN (Electronic)	9781614994398
ISBN (Print)	9781643683300
DOIs	https://doi.org/10.3233/ATDE220605
Publication status	Published - 2022 Nov 8
Externally published	Yes
Event	19th International Conference on Manufacturing Research, ICMR 2022 - Derby, United Kingdom Duration: 2022 Sept 6 → 2022 Sept 8

Publication series

Name	Advances in Transdisciplinary Engineering
Volume	25

Conference

Conference	19th International Conference on Manufacturing Research, ICMR 2022
Country/Territory	United Kingdom
City	Derby
Period	2022/09/06 → 2022/09/08

Bibliographical note

Publisher Copyright:
© 2022 The authors and IOS Press.

Subject classification (UKÄ)

Production Engineering, Human Work Science and Ergonomics

Free keywords

algorithms
Complex manufacturing systems
Machine Learning

Access to Document

10.3233/ATDE220605Licence: CC BY-NC

Cite this

Alrufaihi, D., Oleghe, O., Almanei, M., Jagtap, S., & Salonitis, K. (2022). Feature Reduction and Selection for Use in Machine Learning for Manufacturing. In M. Shafik, & K. Case (Eds.), Advances in Manufacturing Technology XXXV : Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research (pp. 289-296). (Advances in Transdisciplinary Engineering; Vol. 25). IOS Press. https://doi.org/10.3233/ATDE220605

Alrufaihi, Duaa ; Oleghe, Omogbai ; Almanei, Mohammed et al. / Feature Reduction and Selection for Use in Machine Learning for Manufacturing. Advances in Manufacturing Technology XXXV : Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research. editor / Mahmoud Shafik ; Keith Case. IOS Press, 2022. pp. 289-296 (Advances in Transdisciplinary Engineering).

@inproceedings{7025018a6b114f1286426b64de3dbf29,

title = "Feature Reduction and Selection for Use in Machine Learning for Manufacturing",

abstract = "In a complex manufacturing system such as the multistage manufacturing system, maintaining the quality of the products becomes a challenging task. It is due to the interconnectivity and dependency of factors that can affect the final product. With the increasing availability of data, Machine Learning (ML) approaches are applied to assess and predict quality-related issues. In this paper, several ML algorithms, including feature reduction/selection methods, were applied to a publicly available multistage manufacturing dataset to predict the characteristic of the output measurements in (mm). A total of 24 prediction models were produced. The accuracy of the prediction models and the execution time were the evaluation metrics. The results show that uncontrolled variables are the most common features that have been selected by the selection/reduction methods suggesting their strong relationship to the quality of the product. The performance of the prediction models was heavily dependent on the ML algorithm.",

keywords = "algorithms, Complex manufacturing systems, Machine Learning",

author = "Duaa Alrufaihi and Omogbai Oleghe and Mohammed Almanei and Sandeep Jagtap and Konstantinos Salonitis",

note = "Publisher Copyright: {\textcopyright} 2022 The authors and IOS Press.; 19th International Conference on Manufacturing Research, ICMR 2022 ; Conference date: 06-09-2022 Through 08-09-2022",

year = "2022",

month = nov,

day = "8",

doi = "10.3233/ATDE220605",

language = "English",

isbn = " 9781643683300",

series = "Advances in Transdisciplinary Engineering",

publisher = "IOS Press",

pages = "289--296",

editor = "Mahmoud Shafik and Keith Case",

booktitle = "Advances in Manufacturing Technology XXXV",

address = "Netherlands",

}

Alrufaihi, D, Oleghe, O, Almanei, M, Jagtap, S & Salonitis, K 2022, Feature Reduction and Selection for Use in Machine Learning for Manufacturing. in M Shafik & K Case (eds), Advances in Manufacturing Technology XXXV : Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research. Advances in Transdisciplinary Engineering, vol. 25, IOS Press, pp. 289-296, 19th International Conference on Manufacturing Research, ICMR 2022, Derby, United Kingdom, 2022/09/06. https://doi.org/10.3233/ATDE220605

Feature Reduction and Selection for Use in Machine Learning for Manufacturing. / Alrufaihi, Duaa; Oleghe, Omogbai; Almanei, Mohammed et al.
Advances in Manufacturing Technology XXXV : Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research. ed. / Mahmoud Shafik; Keith Case. IOS Press, 2022. p. 289-296 (Advances in Transdisciplinary Engineering; Vol. 25).

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Feature Reduction and Selection for Use in Machine Learning for Manufacturing

AU - Alrufaihi, Duaa

AU - Oleghe, Omogbai

AU - Almanei, Mohammed

AU - Jagtap, Sandeep

AU - Salonitis, Konstantinos

PY - 2022/11/8

Y1 - 2022/11/8

N2 - In a complex manufacturing system such as the multistage manufacturing system, maintaining the quality of the products becomes a challenging task. It is due to the interconnectivity and dependency of factors that can affect the final product. With the increasing availability of data, Machine Learning (ML) approaches are applied to assess and predict quality-related issues. In this paper, several ML algorithms, including feature reduction/selection methods, were applied to a publicly available multistage manufacturing dataset to predict the characteristic of the output measurements in (mm). A total of 24 prediction models were produced. The accuracy of the prediction models and the execution time were the evaluation metrics. The results show that uncontrolled variables are the most common features that have been selected by the selection/reduction methods suggesting their strong relationship to the quality of the product. The performance of the prediction models was heavily dependent on the ML algorithm.

AB - In a complex manufacturing system such as the multistage manufacturing system, maintaining the quality of the products becomes a challenging task. It is due to the interconnectivity and dependency of factors that can affect the final product. With the increasing availability of data, Machine Learning (ML) approaches are applied to assess and predict quality-related issues. In this paper, several ML algorithms, including feature reduction/selection methods, were applied to a publicly available multistage manufacturing dataset to predict the characteristic of the output measurements in (mm). A total of 24 prediction models were produced. The accuracy of the prediction models and the execution time were the evaluation metrics. The results show that uncontrolled variables are the most common features that have been selected by the selection/reduction methods suggesting their strong relationship to the quality of the product. The performance of the prediction models was heavily dependent on the ML algorithm.

KW - algorithms

KW - Complex manufacturing systems

KW - Machine Learning

U2 - 10.3233/ATDE220605

DO - 10.3233/ATDE220605

M3 - Paper in conference proceeding

AN - SCOPUS:85145561617

SN - 9781643683300

T3 - Advances in Transdisciplinary Engineering

SP - 289

EP - 296

BT - Advances in Manufacturing Technology XXXV

A2 - Shafik, Mahmoud

A2 - Case, Keith

PB - IOS Press

T2 - 19th International Conference on Manufacturing Research, ICMR 2022

Y2 - 6 September 2022 through 8 September 2022

ER -

Alrufaihi D, Oleghe O, Almanei M, Jagtap S, Salonitis K. Feature Reduction and Selection for Use in Machine Learning for Manufacturing. In Shafik M, Case K, editors, Advances in Manufacturing Technology XXXV : Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research. IOS Press. 2022. p. 289-296. (Advances in Transdisciplinary Engineering). doi: 10.3233/ATDE220605

Feature Reduction and Selection for Use in Machine Learning for Manufacturing

Abstract

Publication series

Conference

Bibliographical note

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Cite this