Abstract
This article undertakes the subject matter of applying artificial neural networks to analyze optical reflectance spectra of objects exhibiting a change of optical properties in the domain of time. A compact Digital Light Projection NIRscan Nano Evaluation Module spectrometer was used to record spectra. Due to the miniature spectrometer’s size and its simplicity of measurement, it can be used to conduct tests outside of a laboratory. A series of plant-derived objects were used as test subjects with rapidly changing optical properties in the presented research cycle. The application of artificial neural networks made it possible to determine the aging time of plants with a relatively low mean squared error, reaching 0.56 h for the Levenberg–Marquardt backpropagation training method. The results of the other ten training methods for artificial neural networks have been included in the paper.
Highlights
Near Infrared Spectroscopy (NIR) can be an effective and fast tool for measuring objects with time-variable optical characteristics, e.g., plant-derived objects [1,2]
Device (DMD), which replaces the system of detectors or scanning mechanism and acts as a programmable wavelength filter [3]
The short time of a single-spectrum measurement makes it possible to quickly obtain measurement results of reflectance spectra of various objects, including those rapidly changing over time outside of a laboratory
Summary
Near Infrared Spectroscopy (NIR) can be an effective and fast tool for measuring objects with time-variable optical characteristics, e.g., plant-derived objects [1,2]. I.e., a backward propagation neural network was applied to efficiently optimize the pulse electrodeposition process of Ni–W-graded coating. Another example of using ANNs in materials science was described in the paper [6]. The main goal of this paper is to expand methods of analyzing the reflectance spectra of objects with properties changing over time using the DLP measuring technique. Based on conceptions of applications’ expert systems developed to establish input-output relationships of various manufacturing processes and data analysis [4,9,10,11], a method to analyze time-variable optical reflectance spectra in DLP spectroscopy using ANN has been applied. A discussion on obtained research results and a summary with main conclusions and a plan of future research are included
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
