Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film

Patrick D. McAtee; Akhlesh Lakhtakia

doi:10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062

Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film

Patrick D. McAtee
, Akhlesh Lakhtakia

Engineering Science and Mechanics

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

Abstract

Two machine-learning paradigms have been applied to the analysis of an optical sensor comprising a sculptured thin-film (STF) grown atop a thin metal layer. The porosity of the STF allows for changes in its dielectric properties due to infiltrating liquids. More specifically, a solution containing analytes can bind to the metal layer, changing the refractive index near the metal/STF interface. This induces a change in the condition to excite a surface-plasmon-polariton (SPP) wave guided by that interface, thereby altering the reflectance as a function of incidence angle when the sensor is used in the wellknown prism-coupled configuration. Artificial neural networks (ANNs) and support vector machines (SVMs) were used to analyze reflectance data to determine concentrations of analytes in solution infilitrating chiral STFs. Training with this data allowed for identification of Immunoglobin-G concentrations. Also, machine learning is promising for simultaneous multianalyte sensing.

Original language	English (US)
Title of host publication	2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	73-76
Number of pages	4
ISBN (Electronic)	9798331523671
DOIs	https://doi.org/10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062
State	Published - 2025
Event	2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Ottawa, Canada Duration: Jul 13 2025 → Jul 18 2025

Publication series

Name	IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)
ISSN (Print)	1522-3965
ISSN (Electronic)	1947-1491

Conference

Conference	2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025
Country/Territory	Canada
City	Ottawa
Period	7/13/25 → 7/18/25

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062

Cite this

McAtee, P. D., & Lakhtakia, A. (2025). Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film. In 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings (pp. 73-76). (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062

McAtee, Patrick D. ; Lakhtakia, Akhlesh. / Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film. 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 73-76 (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)).

@inproceedings{6ed6fa6c3c38458c8c7a7857fef40861,

title = "Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film",

abstract = "Two machine-learning paradigms have been applied to the analysis of an optical sensor comprising a sculptured thin-film (STF) grown atop a thin metal layer. The porosity of the STF allows for changes in its dielectric properties due to infiltrating liquids. More specifically, a solution containing analytes can bind to the metal layer, changing the refractive index near the metal/STF interface. This induces a change in the condition to excite a surface-plasmon-polariton (SPP) wave guided by that interface, thereby altering the reflectance as a function of incidence angle when the sensor is used in the wellknown prism-coupled configuration. Artificial neural networks (ANNs) and support vector machines (SVMs) were used to analyze reflectance data to determine concentrations of analytes in solution infilitrating chiral STFs. Training with this data allowed for identification of Immunoglobin-G concentrations. Also, machine learning is promising for simultaneous multianalyte sensing.",

author = "McAtee, \{Patrick D.\} and Akhlesh Lakhtakia",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 ; Conference date: 13-07-2025 Through 18-07-2025",

year = "2025",

doi = "10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062",

language = "English (US)",

series = "IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "73--76",

booktitle = "2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings",

address = "United States",

}

McAtee, PD & Lakhtakia, A 2025, Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film. in 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings. IEEE Antennas and Propagation Society, AP-S International Symposium (Digest), Institute of Electrical and Electronics Engineers Inc., pp. 73-76, 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025, Ottawa, Canada, 7/13/25. https://doi.org/10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062

Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film. / McAtee, Patrick D.; Lakhtakia, Akhlesh.
2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. p. 73-76 (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)).

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

TY - GEN

T1 - Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film

AU - McAtee, Patrick D.

AU - Lakhtakia, Akhlesh

PY - 2025

Y1 - 2025

N2 - Two machine-learning paradigms have been applied to the analysis of an optical sensor comprising a sculptured thin-film (STF) grown atop a thin metal layer. The porosity of the STF allows for changes in its dielectric properties due to infiltrating liquids. More specifically, a solution containing analytes can bind to the metal layer, changing the refractive index near the metal/STF interface. This induces a change in the condition to excite a surface-plasmon-polariton (SPP) wave guided by that interface, thereby altering the reflectance as a function of incidence angle when the sensor is used in the wellknown prism-coupled configuration. Artificial neural networks (ANNs) and support vector machines (SVMs) were used to analyze reflectance data to determine concentrations of analytes in solution infilitrating chiral STFs. Training with this data allowed for identification of Immunoglobin-G concentrations. Also, machine learning is promising for simultaneous multianalyte sensing.

AB - Two machine-learning paradigms have been applied to the analysis of an optical sensor comprising a sculptured thin-film (STF) grown atop a thin metal layer. The porosity of the STF allows for changes in its dielectric properties due to infiltrating liquids. More specifically, a solution containing analytes can bind to the metal layer, changing the refractive index near the metal/STF interface. This induces a change in the condition to excite a surface-plasmon-polariton (SPP) wave guided by that interface, thereby altering the reflectance as a function of incidence angle when the sensor is used in the wellknown prism-coupled configuration. Artificial neural networks (ANNs) and support vector machines (SVMs) were used to analyze reflectance data to determine concentrations of analytes in solution infilitrating chiral STFs. Training with this data allowed for identification of Immunoglobin-G concentrations. Also, machine learning is promising for simultaneous multianalyte sensing.

UR - https://www.scopus.com/pages/publications/105030884630

UR - https://www.scopus.com/pages/publications/105030884630#tab=citedBy

U2 - 10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062

DO - 10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062

M3 - Conference contribution

AN - SCOPUS:105030884630

T3 - IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)

SP - 73

EP - 76

BT - 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025

Y2 - 13 July 2025 through 18 July 2025

ER -

McAtee PD, Lakhtakia A. Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film. In 2025 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, AP-S/CNC-USNC-URSI 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2025. p. 73-76. (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)). doi: 10.1109/AP-S/CNC-USNC-URSI55537.2025.11266062

Machine-Learning-Based Optical Sensing of Analytes Infiltrating a Chiral Sculptured Thin Film

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this