Citation

Othman, Marinah and Ashik, Muhammad Hasif Saiful and Fadhir, Muhammad Firdaus Mohd and Mansor, Sarina and Robi, Siti Nur Aisyah and Jamaludin, Juliza and Ariffin, Khairul Nabilah Zainul (2026) Machine Learning-Assisted Optimization of Photonic Crystal Fiber-Surface Plasmon Resonance (PCF-SPR) Sensors for Microplastic Detection. In: 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026, 22 April 2026 - 23 April 2026, Sakhir.

Preview

Text 11.pdf Download (1MB) | Preview

Abstract

Microplastic pollution poses a significant threat to aquatic ecosystems; however, the development of highsensitivity Photonic Crystal Fiber Surface Plasmon Resonance (PCF-SPR) sensors remains limited by computationally intensive trial-and-error simulations. This study investigates the effectiveness of machine learning (ML) algorithms in optimizing dual sliced PCF-SPR sensor parameters to accelerate the design process. A comprehensive dataset of geometric parameters and optical performance metrics is generated using COMSOL Multiphysics and used to train Artificial Neural Network (ANN) and Extreme Gradient Boosting (XGBoost) regression models. Results show that XGBoost achieves better predictive accuracy and identifies an optimal sensor configuration with a sensitivity of 5000 nm/RIU. The proposed ML-assisted framework significantly reduces computational cost while providing deeper insight into parameter–performance relationships, offering a scalable approach for real-time microplastic monitoring system development.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	, Image sensors , Surface plasmon resonance
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 Sep 2026 04:32
Last Modified:	04 Sep 2026 04:32
URII:	http://shdl.mmu.edu.my/id/eprint/16716

Downloads

Edit (login required)