Advanced Optimization of 2D Material-Based Biosensor Through Machine Learning
Sensing and Imaging · 16.06.2025 · 26 (1)
DOI: 10.1007/s11220-025-00617-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensing and Imaging, online erschienen am 16.06.2025. Verfasst von Aymen Hlali und 1 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 30 Literaturangaben.
Abstract (Originalsprache)
This work introduces a highly sensitive and tunable THz biosensor designed for detecting breast cancer cells. The proposed sensor is based on a ring resonator with a centrally positioned sample carrier, utilizing a hybrid structure of black phosphorus (BP) and graphene. To optimize the interaction between Electronic Chemical Potential of Graphene and BP’s electron doping, a machine learning approach employing the K-Nearest Neighbors (KNN) model was implemented. Electromagnetic simulations demonstrate exceptional sensitivity, reaching 24.165 THz/RIU for healthy cells and 30.534 THz/RIU for cancerous cells. This design, characterized by its high sensitivity, structural simplicity, and tunability, highlights significant potential for applications in THz biomedical diagnostics, particularly in early breast cancer detection.
Zitieren
APA
Hlali, A., & Zairi, H. (2025). Advanced Optimization of 2D Material-Based Biosensor Through Machine Learning. Sensing and Imaging, 26(1). https://doi.org/10.1007/s11220-025-00617-2
Vancouver
Hlali A, Zairi H. Advanced Optimization of 2D Material-Based Biosensor Through Machine Learning. Sensing and Imaging. 2025;26(1). doi:10.1007/s11220-025-00617-2
BibTeX
@article{Hlali2025,
author = {Hlali, Aymen and Zairi, Hassen},
title = {Advanced Optimization of 2D Material-Based Biosensor Through Machine Learning},
journal = {Sensing and Imaging},
year = {2025},
volume = {26},
number = {1},
doi = {10.1007/s11220-025-00617-2}
}
EUVIMED