Retrieval of size and refractive index of spherical particles by multiangle light scattering: neural network method application

Berdnik, Vladimir V.; Loiko, Valery A.

doi:10.1364/ao.48.006178

Cited by 23 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [ 15 ] describes an ANN for detecting amino acids and several solid organic compounds. The work in [ 16 ] explains how a trained ANN was successfully used in assessing the size and the refractive index. The paper cited as [ 17 ] describes how an ANN was used in measuring the radius of spherical particles.…”

Section: Introductionmentioning

confidence: 99%

An Artificial Neural Network Assisted Dynamic Light Scattering Procedure for Assessing Living Cells Size in Suspension

Chicea

2020

Sensors

View full text Add to dashboard Cite

Dynamic light scattering (DLS) is an essential technique used for assessing the size of the particles in suspension, covering the range from nanometers to microns. Although it has been very well established for quite some time, improvement can still be brought in simplifying the experimental setup and in employing an easier to use data processing procedure for the acquired time-series. A DLS time series processing procedure based on an artificial neural network is presented with details regarding the design, training procedure and error analysis, working over an extended particle size range. The procedure proved to be much faster regarding time-series processing and easier to use than fitting a function to the experimental data using a minimization algorithm. Results of monitoring the long-time variation of the size of the Saccharomyces cerevisiae during fermentation are presented, including the 10 h between dissolving from the solid form and the start of multiplication, as an application of the proposed procedure. The results indicate that the procedure can be used to identify the presence of bigger particles and to assess their size, in aqueous suspensions used in the food industry.

show abstract

Section: Introductionmentioning

confidence: 99%

An Artificial Neural Network Assisted Dynamic Light Scattering Procedure for Assessing Living Cells Size in Suspension

Chicea

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…With the availability of open-source and easy to use libraries [1,2] and graphics processing units at affordable prices, researchers from various disciplines of science and engineering are using artificial neural networks to learn from and make predictions on data in various forms. Optical material characterization based on reflectometry (or ellipsometry) data is one of these applications, where deep learning has been implemented to identify two-dimensional (2D) nanostructures [3][4][5][6] and to obtain optical constants of particles [7], thin films [8,9], solutions [10], tissues [11], and soils [12]. This work focuses on determining optical constants of atomically thin layered materials as follows.…”

Section: Introduction: Deep Learning and Optical Materials Characterizmentioning

confidence: 99%

“…Hence, the method used for optical property extraction should be not only accurate but also efficient. As previously mentioned [3][4][5][6][7][8][9][10][11], deep learning is a promising field for this very purpose, which can be used in two different ways: regression [8] or classification [12,19]. Since previous regression based Original content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence.…”

Section: Introduction: Deep Learning and Optical Materials Characterizmentioning

confidence: 99%

Determining optical constants of 2D materials with neural networks from multi-angle reflectometry data

Şimşek¹

2020

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Synthetically generated multi-angle reflectometry data is used to train a neural network based learning system to estimate the refractive index of atomically thin layered materials in the visible part of the electromagnetic spectrum. Unlike previously developed regression based optical characterization methods, the prediction is achieved via classification by using the probabilities of each input element belonging to a label as weighting coefficients in a simple analytical formula. Various types of activation functions and gradient descent optimizers are tested to determine the optimum combination yielding the best performance. For the verification of the proposed method's accuracy, four different materials are studied. In all cases, the maximum error is calculated to be less than 0.3%. Considering the highly dispersive nature of the studied materials, this result is a substantial improvement in terms of accuracy and efficiency compared to traditional approaches.

show abstract

“…Another paper, [22] presents a Neural Network implementation for pattern recognition used in a flow cytometer for identifying the presence of dangerous fibers, like asbestos, in air. Papers [23] and [24] present results on evaluating the size and refractive index for particles in suspension using measurement of angle-dependent light scattered and analyzing the radial basis function with a Neural Network. Another paper [25] presents results for a Neural Network which was fed with data from the polarized light signature in the shape of Mueller matrix for detecting amino acids and other organic compounds of solid type.…”

Section: Introductionmentioning

confidence: 99%

Using Dynamic Light Scattering Experimental Setup and Neural Networks For Particle Sizing

Rei

Chicea

2017

ACTA Universitatis Cibiniensis

View full text Add to dashboard Cite

Using a Lorentzian function fit as reference, a basic experiment was designed for processing IntroductionThe study of nanoparticles is a topic of major interest in the last decades due to the wide array of applications, especially in the area of biology and medicine. As a consequence of their small size, one order of magnitude smaller than the living cells, they can be used to deliver various substances to living cells, producing, in general, only minor perturbations. The applications of these nanomaterials were presented in several papers, such as [1]. During development of these applications, there were concerns about the toxicity of these methods. As a result, techniques for monitoring the nanoparticles concentration were also developed [2].The properties of the systems of nanoparticles are in direct relation to the size distribution of the particles in the fluid. For this reason, the size characterization of these systems is one relevant aspect for further development of the nanotechnology applications. There are various techniques used for this. One modern technique is the Transmission Electron Microscopy (TEM) which evaluates particles in the range from nanometers to micrometers. This method has a good resolution but is in general expensive, time consuming and does not work in-situ. Another method is the X-Ray powder diffraction which can offer the size distribution of the particles [3]. For metal oxides, for which the assumption used is that the crystallite size is the same as the particle size, the Scherrer equation [4] can offer the mean particle size. For colloidal particles, the Guinier formula [5] can be used in a similar way. However, also these two methods are slow and do not work in-situ. The particle size for nano-systems can also be assessed by the method called "Atomic Force Microscopy" (AFM) [6], [7]. Paper [7] shows a comparison of AFM with TEM. Results show that AFM sizing requires very thin samples over several layers. The samples are scanned line by line and this takes a lot of time. Comparisons and reviews of other techniques used for nanoparticle size characterization are presented in many papers, such as [8]. As in [9], the properties of the nanofluid change very fast during nanoparticle aggregation, and as a consequence, a fast procedure for monitoring the size is needed. A valid option for this are the optical procedures, which use coherent light scattering.The optical methods make use of an incident coherent beam of light which illuminates an active sample volume containing the nanoparticles. Each particle represents a scattering center and becomes a secondary light source. The intensity of the scattered light is anisotropic and depends on the size and shape of the scattering centers. This is described by the phase function, for which there are several models used to represent it [10], [11], [12].If the incident beam is coherent, so are the secondary waves emitted by each scattering center. If a screen or a detector is present, all the wavelets emitted by all the scattering...

show abstract

Retrieval of size and refractive index of spherical particles by multiangle light scattering: neural network method application

Cited by 23 publications

References 20 publications

An Artificial Neural Network Assisted Dynamic Light Scattering Procedure for Assessing Living Cells Size in Suspension

An Artificial Neural Network Assisted Dynamic Light Scattering Procedure for Assessing Living Cells Size in Suspension

Determining optical constants of 2D materials with neural networks from multi-angle reflectometry data

Using Dynamic Light Scattering Experimental Setup and Neural Networks For Particle Sizing

Contact Info

Product

Resources

About