Artificial neural network to estimate the refractive index of a liquid infiltrating a chiral sculptured thin film

Abstract

We theoretically expanded the capabilities of optical sensing based on surface plasmon resonance in a prism-coupled configuration by incorporating artificial neural networks (ANNs). We used calculations modeling the situation in which an index-matched substrate with a metal thin film and a porous chiral sculptured thin film (CSTF) deposited successively on it is affixed to the base of a triangular prism. When a fluid is brought in contact with the exposed face of the CSTF, the latter is infiltrated. As a result of infiltration, the traversal of light entering one slanted face of the prism and exiting the other slanted face of the prism is affected. We trained two ANNs with differing structures using reflectance data generated from simulations to predict the refractive index of the infiltrant fluid. The best predictions were a result of training the ANN with simpler structure. With realistic simulated-noise, the performance of this ANN is robust.

Experimental detection of Immunoglobulin G by prism-coupled angular interrogation and a support vector machine

“…(ii) A sensor of the second type (S2) requires a CSTF 10,24,25 be deposited on top of the Au thin film. As θ inc changes, different SPP waves guided by the planar interface of the Au thin film and the infiltrated CSTF can be excited at discrete values of θ inc .…”

“…In general, for the three types of sensors used here, this light contains both pand s-polarized components. 24,25 The two arms of the machine were rotated in synchrony, being controlled by a stepper motor (NEMA23-597, Applied Motion Products, Watsonville, California) coupled with a stepper driver (3540i, Applied Motion Products), both operated using commercial software (SiNet Hub Programmer, Applied Motion Products). The CCD camera captured the intensity of the reflected light using the uc480 Camera Manager (ThorLabs).…”

“…15 With the continual increase in the availability of computational power, machinelearning paradigms are being applied to a multitude of tasks in engineering and medicine with great success. [16][17][18][19][20][21][22][23][24][25] In this paper, we present the use of a specific machine-learning paradigm, called a support vector machine (SVM), 26,27 to classify three different solutions containing differing concentrations of Immunoglobulin G (IgG), which is the most common type of antibody found in blood and extracellular fluid. 28 Protein A, 29,30 a surface protein found in the bacteria Staphylococcus aureus, was chosen as the bioreceptor.…”

Theory of artificial-neural-network-based simultaneous optical sensing of two analytes using sculptured thin films

“…In a predecessor paper, 61 we had investigated the efficacy of S4 with the additional constraint that no bioreceptor is present. Thus, the void regions of the CSTF atop the metal layer of thickness L 1…”

A Divide-and-Cooperate Machine Learning Model-Based RBF With Its VC Dimension Analysis

“…Machine learning is one of the most important techniques to implement AI. Many models on machine learning such as artificial neural network (ANN) [7][8][9][10][11], support vector machine (SVM) [12][13][14][15] have been developed. Recently, due to the success in Chinese chess matches between human and machines, deep learning [16][17][18] becomes a highlight in AI research.…”