Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer

Qusay Shihab Hamad; Sami Abdulla Mohsen Saleh; Shahrel Azmin Suandi; Hussein Samma; Yasameen Shihab Hamad; Ibrahim Al Amoudi

doi:10.1007/978-981-99-9005-4_61

Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer

Qusay Shihab Hamad
, Sami Abdulla Mohsen Saleh
, Shahrel Azmin Suandi^*
, Hussein Samma
, Yasameen Shihab Hamad
, Ibrahim Al Amoudi

^*Corresponding author for this work

SDAIA-KFUPM Joint Research Center for Artificial Intelligence

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

Abstract

Feature selection is critical in fields like data mining and pattern classification, as it eliminates irrelevant data and enhances the quality of highly dimensional datasets. This study explores the effectiveness of the Q-learning embedded sine cosine algorithm (QLESCA) for feature selection in industrial casting defect detection using the VGG19 model. QLESCA’s performance is compared to other optimization algorithms, with experimental results showing that QLESCA outperforms the other algorithms in terms of classification metrics. The best accuracy achieved by QLESCA is 97.0359%, with an average fitness value of − 0.99124. The proposed method provides a promising approach to improve the accuracy and reliability of industrial casting defect detection systems, which is essential for product quality and safety. Our findings suggest that using powerful optimization algorithms like QLESCA is crucial for obtaining the best subsets of information in feature selection and achieving optimal performance in classification tasks.

Original language	English
Title of host publication	Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications
Editors	Nur Syazreen Ahmad, Junita Mohamad-Saleh, Jiashen Teh
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	485-491
Number of pages	7
ISBN (Print)	9789819990047
DOIs	https://doi.org/10.1007/978-981-99-9005-4_61
State	Published - 2024
Event	12th International Conference on Robotics, Vision, Signal Processing, and Power Applications, ROVISP 2023 - Penang, Malaysia Duration: 28 Aug 2023 → 29 Aug 2023

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1123 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	12th International Conference on Robotics, Vision, Signal Processing, and Power Applications, ROVISP 2023
Country/Territory	Malaysia
City	Penang
Period	28/08/23 → 29/08/23

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Keywords

Convolutional neural networks
Feature engineering
Machine learning
Support vector machine (SVM) classifier
Swarm intelligence

ASJC Scopus subject areas

Industrial and Manufacturing Engineering

Access to Document

10.1007/978-981-99-9005-4_61

Cite this

Hamad, Q. S., Saleh, S. A. M., Suandi, S. A., Samma, H., Hamad, Y. S., & Al Amoudi, I. (2024). Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer. In N. S. Ahmad, J. Mohamad-Saleh, & J. Teh (Eds.), Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications (pp. 485-491). (Lecture Notes in Electrical Engineering; Vol. 1123 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-9005-4_61

Hamad, Qusay Shihab ; Saleh, Sami Abdulla Mohsen ; Suandi, Shahrel Azmin et al. / Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer. Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications. editor / Nur Syazreen Ahmad ; Junita Mohamad-Saleh ; Jiashen Teh. Springer Science and Business Media Deutschland GmbH, 2024. pp. 485-491 (Lecture Notes in Electrical Engineering).

@inproceedings{f701f7077f934a1c97591133c7c8169a,

title = "Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer",

abstract = "Feature selection is critical in fields like data mining and pattern classification, as it eliminates irrelevant data and enhances the quality of highly dimensional datasets. This study explores the effectiveness of the Q-learning embedded sine cosine algorithm (QLESCA) for feature selection in industrial casting defect detection using the VGG19 model. QLESCA{\textquoteright}s performance is compared to other optimization algorithms, with experimental results showing that QLESCA outperforms the other algorithms in terms of classification metrics. The best accuracy achieved by QLESCA is 97.0359\%, with an average fitness value of − 0.99124. The proposed method provides a promising approach to improve the accuracy and reliability of industrial casting defect detection systems, which is essential for product quality and safety. Our findings suggest that using powerful optimization algorithms like QLESCA is crucial for obtaining the best subsets of information in feature selection and achieving optimal performance in classification tasks.",

keywords = "Convolutional neural networks, Feature engineering, Machine learning, Support vector machine (SVM) classifier, Swarm intelligence",

author = "Hamad, \{Qusay Shihab\} and Saleh, \{Sami Abdulla Mohsen\} and Suandi, \{Shahrel Azmin\} and Hussein Samma and Hamad, \{Yasameen Shihab\} and \{Al Amoudi\}, Ibrahim",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 12th International Conference on Robotics, Vision, Signal Processing, and Power Applications, ROVISP 2023 ; Conference date: 28-08-2023 Through 29-08-2023",

year = "2024",

doi = "10.1007/978-981-99-9005-4\_61",

language = "English",

isbn = "9789819990047",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "485--491",

editor = "Ahmad, \{Nur Syazreen\} and Junita Mohamad-Saleh and Jiashen Teh",

booktitle = "Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications",

address = "Germany",

}

Hamad, QS, Saleh, SAM, Suandi, SA, Samma, H, Hamad, YS & Al Amoudi, I 2024, Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer. in NS Ahmad, J Mohamad-Saleh & J Teh (eds), Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications. Lecture Notes in Electrical Engineering, vol. 1123 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 485-491, 12th International Conference on Robotics, Vision, Signal Processing, and Power Applications, ROVISP 2023, Penang, Malaysia, 28/08/23. https://doi.org/10.1007/978-981-99-9005-4_61

Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer. / Hamad, Qusay Shihab; Saleh, Sami Abdulla Mohsen; Suandi, Shahrel Azmin et al.
Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications. ed. / Nur Syazreen Ahmad; Junita Mohamad-Saleh; Jiashen Teh. Springer Science and Business Media Deutschland GmbH, 2024. p. 485-491 (Lecture Notes in Electrical Engineering; Vol. 1123 LNEE).

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

TY - GEN

T1 - Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer

AU - Hamad, Qusay Shihab

AU - Saleh, Sami Abdulla Mohsen

AU - Suandi, Shahrel Azmin

AU - Samma, Hussein

AU - Hamad, Yasameen Shihab

AU - Al Amoudi, Ibrahim

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - Feature selection is critical in fields like data mining and pattern classification, as it eliminates irrelevant data and enhances the quality of highly dimensional datasets. This study explores the effectiveness of the Q-learning embedded sine cosine algorithm (QLESCA) for feature selection in industrial casting defect detection using the VGG19 model. QLESCA’s performance is compared to other optimization algorithms, with experimental results showing that QLESCA outperforms the other algorithms in terms of classification metrics. The best accuracy achieved by QLESCA is 97.0359%, with an average fitness value of − 0.99124. The proposed method provides a promising approach to improve the accuracy and reliability of industrial casting defect detection systems, which is essential for product quality and safety. Our findings suggest that using powerful optimization algorithms like QLESCA is crucial for obtaining the best subsets of information in feature selection and achieving optimal performance in classification tasks.

AB - Feature selection is critical in fields like data mining and pattern classification, as it eliminates irrelevant data and enhances the quality of highly dimensional datasets. This study explores the effectiveness of the Q-learning embedded sine cosine algorithm (QLESCA) for feature selection in industrial casting defect detection using the VGG19 model. QLESCA’s performance is compared to other optimization algorithms, with experimental results showing that QLESCA outperforms the other algorithms in terms of classification metrics. The best accuracy achieved by QLESCA is 97.0359%, with an average fitness value of − 0.99124. The proposed method provides a promising approach to improve the accuracy and reliability of industrial casting defect detection systems, which is essential for product quality and safety. Our findings suggest that using powerful optimization algorithms like QLESCA is crucial for obtaining the best subsets of information in feature selection and achieving optimal performance in classification tasks.

KW - Convolutional neural networks

KW - Feature engineering

KW - Machine learning

KW - Support vector machine (SVM) classifier

KW - Swarm intelligence

UR - https://www.scopus.com/pages/publications/85190361754

U2 - 10.1007/978-981-99-9005-4_61

DO - 10.1007/978-981-99-9005-4_61

M3 - Conference contribution

AN - SCOPUS:85190361754

SN - 9789819990047

T3 - Lecture Notes in Electrical Engineering

SP - 485

EP - 491

BT - Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications

A2 - Ahmad, Nur Syazreen

A2 - Mohamad-Saleh, Junita

A2 - Teh, Jiashen

PB - Springer Science and Business Media Deutschland GmbH

T2 - 12th International Conference on Robotics, Vision, Signal Processing, and Power Applications, ROVISP 2023

Y2 - 28 August 2023 through 29 August 2023

ER -

Hamad QS, Saleh SAM, Suandi SA, Samma H, Hamad YS, Al Amoudi I. Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer. In Ahmad NS, Mohamad-Saleh J, Teh J, editors, Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications. Springer Science and Business Media Deutschland GmbH. 2024. p. 485-491. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-99-9005-4_61

Optimizing Feature Selection for Industrial Casting Defect Detection Using QLESCA Optimizer

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this