Identification of Model Particle Mixtures Using Machine-Learning-Assisted Laser Diffraction

  title={Identification of Model Particle Mixtures Using Machine-Learning-Assisted Laser Diffraction},
  author={Arturo Villegas and Mario Alan Quiroz-Ju{\'a}rez and Alfred B. U’Ren and Juan P. Torres and Roberto de J. Le{\'o}n-Montiel},
We put forward and demonstrate with model particles a smart laser-diffraction analysis technique aimed at particle mixture identification. We retrieve information about the size, shape, and ratio concentration of two-component heterogeneous model particle mixtures with an accuracy above 92%. We verify the method by detecting arrays of randomly located model particles with different shapes generated with a Digital Micromirror Device (DMD). In contrast to commonly-used laser diffraction schemes… 

Figures and Tables from this paper



An ultra-compact particle size analyser using a CMOS image sensor and machine learning

A team of researchers has made a low-cost, miniaturised PSA capable of determining the volume median diameter of particles suspended in liquids and incorporates a collimated beam configuration using a commonly available image sensor to capture scattering images and machine learning to predict the particle size distribution.

Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles.

It is demonstrated that two popular machine-learning algorithms, cascade classifiers and deep convolutional neural networks (CNN) can solve the feature-localization problem orders of magnitude faster than current state-of-the-art techniques.

Machine-learning-based computationally efficient particle size distribution retrieval from bulk optical properties.

An efficient numerical approach to solving the inverse scattering problem by accelerating the calculation of bulk optical properties based on machine learning and the particle swarm optimization algorithm is employed to optimize the particle size distribution parameters.

CATCH: Characterizing and Tracking Colloids Holographically Using Deep Neural Networks.

Characterizing and Tracking Colloids Holographically (CATCH) with deep convolutional neural networks is fast enough for real-time applications and otherwise outperforms conventional analytical algorithms, particularly for heterogeneous and crowded samples.

Convolutional neural network applied for nanoparticle classification using coherent scatterometry data.

This work trained a convolutional neural network, including its architecture optimization, and achieved 95% accurate results, compared to an existing method based on line-by-line search and thresholding, demonstrating up to a twofold enhanced performance in particle classification.