TY - JOUR
T1 - Autoencoder-aided measurement of concentration from a single line of speckle
AU - Karamehmedović, Mirza
AU - Sehic, Kenan
AU - Dammann, Bernd
AU - Suljagić, Mirza
AU - Karamehmedović, Emir
PY - 2019
Y1 - 2019
N2 - We demonstrate that a single 6mm line sample of simulated near-field speckleintensity suffices for accurate estimation of the concentration of dielectric micro-particles over a range from 104 to 6 · 106 particles per ml. For this estimation, we analyze the speckle using both standard methods (linear principal component analysis, support vector machine (SVM)) and a neural network, in the form of a sparse stacked autoencoder (SSAE) with a softmax classifier or with an SVM. Using an SSAE with SVM, we classify line speckle samples according to particle concentration with an average accuracy of over 78%, with other methods close behind.
AB - We demonstrate that a single 6mm line sample of simulated near-field speckleintensity suffices for accurate estimation of the concentration of dielectric micro-particles over a range from 104 to 6 · 106 particles per ml. For this estimation, we analyze the speckle using both standard methods (linear principal component analysis, support vector machine (SVM)) and a neural network, in the form of a sparse stacked autoencoder (SSAE) with a softmax classifier or with an SVM. Using an SSAE with SVM, we classify line speckle samples according to particle concentration with an average accuracy of over 78%, with other methods close behind.
U2 - 10.1364/OE.27.029098
DO - 10.1364/OE.27.029098
M3 - Journal article
C2 - 31684650
SN - 1094-4087
VL - 27
SP - 29098
EP - 29123
JO - Optics Express
JF - Optics Express
IS - 20
ER -