Si plate radius influence on the photoacoustic signal processed by neural networks

Abstract

The effect of the sample radius on the total photoacoustic signal processed by neural networks trained with undistorted and distorted signals is carefully analyzed for modulation frequencies from 20 Hz to 20 kHz. This is done for signals generated for a 400- μm-thick Si n-type plate, whose radius varies from 2 to 7 mm. It is found that the networks trained with both undistorted or distorted signals yield the best predictions for sample radii between 2 and 3 mm, which is close to the used microphone aperture radius of 1.5 mm. The network trained only with undistorted signals gives the best results for sample radii comparable to the microphone dimensions. The obtained results of neural networks in the prediction of Si-plate radius indicate the experimental necessity to use samples with radii slightly over to a microphone aperture.

A method for efficient classification of microphones based on expert knowledge and computational intelligence

“…Machine learning algorithms and especially neural networks are living extreme growth in number of applications, and their utilization in photoacoustic (PA) has been current trend, bringing significant improvements in: determination of physical parameters [1] [2] [3], PA instruments composition [4], noise influence decrease [5], PA tomography image reconstruction [6], etc. Literature overview brings a fact that deep learning is more and more represented in PA, what is understandable concerning the reality of deep learning, as most sophisticated artificial intelligence (AI) architecture [7].…”