scholarly journals Application of Artificial Neural Networks in Analysis of Time-Variable Optical Reflectance Spectra in Digital Light Projection Spectroscopy

Coatings ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 37
Author(s):  
Marek Gąsiorowski ◽  
Piotr Szymak ◽  
Leszek Bychto ◽  
Aleksy Patryn
Keyword(s):  
Neural Networks ◽  
Optical Properties ◽  
Artificial Neural Networks ◽  
Mean Squared Error ◽  
Reflectance Spectra ◽  
Training Methods ◽  
Optical Reflectance ◽  
Research Cycle ◽  
Evaluation Module ◽  
Artificial Neural

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.

Artificial Neural Networks Estimation for Thicknesses of Multilayer Nano-Scale Films

2019 ◽  
Vol 962 ◽  
pp. 41-48
Author(s):  
Tzong Daw Wu ◽  
Jiun Shen Chen ◽  
Ching Pei Tseng ◽  
Cheng Chang Hsieh
Keyword(s):  
Thin Films ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Real Time ◽  
Film Growth ◽  
Mean Squared Error ◽  
Squared Error ◽  
Thin Film Optics ◽  
The Mean ◽  
Artificial Neural

This study presents a real-time method for determining the thickness of each layer in multilayer thin films. Artificial neural networks (ANNs) were introduced to estimate thicknesses from a transmittance spectrum. After training via theoretical spectra which were generated by thin-film optics and modified by noise, ANNs were applied to estimate the thicknesses of four-layer nanoscale films which were TiO2, Ag, Ti, and TiO2 thin films assembled sequentially on polyethylene terephthalate (PET) substrates. The results reveal that the mean squared error of the estimation is 2.6 nm2, and is accurate enough to monitor film growth in real time.

Learning in Artificial Neural Networks: A Statistical Perspective

1989 ◽  
Vol 1 (4) ◽  
pp. 425-464 ◽  
Author(s):  
Halbert White
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Optimization Theory ◽  
Comprehensive Treatment ◽  
Training Methods ◽  
Network Learning ◽  
Advantages And Disadvantages ◽  
Systems Identification ◽  
Artificial Neural ◽  
Insight Into

The premise of this article is that learning procedures used to train artificial neural networks are inherently statistical techniques. It follows that statistical theory can provide considerable insight into the properties, advantages, and disadvantages of different network learning methods. We review concepts and analytical results from the literatures of mathematical statistics, econometrics, systems identification, and optimization theory relevant to the analysis of learning in artificial neural networks. Because of the considerable variety of available learning procedures and necessary limitations of space, we cannot provide a comprehensive treatment. Our focus is primarily on learning procedures for feedforward networks. However, many of the concepts and issues arising in this framework are also quite broadly relevant to other network learning paradigms. In addition to providing useful insights, the material reviewed here suggests some potentially useful new training methods for artificial neural networks.

Applying of Neural Networks for Testing of Tracers with using of Empirical Data

2019 ◽  
Vol 218 (3) ◽  
pp. 5-23
Author(s):  
Dariusz Ampuła
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Test Results ◽  
Test Methodology ◽  
Laboratory Test Results ◽  
Depth Analysis ◽  
Evaluation Module ◽  
Artificial Neural ◽  
Marine Climate ◽  
Over 40 Years

Abstract An attempt of designing artificial neural networks for empirical laboratory test results tracers No. 5, No. 7 and No. 8 was introduced in the article. These tracers are applied in cartridges with calibres from 37 mm to 122 mm which are still used and stored both in the marine climate and land. The results of laboratory tests of tracers in the field of over 40 years of tests have been analysed. They have been properly prepared in accordance with the requirements that are necessary to design of neural networks. Only the evaluation module of these tracers was evaluated, because this element of tests, fulfilled the necessary assumptions needed to build artificial neural networks. Several hundred artificial neural networks have been built for each type of analysed tracers. After an in-depth analysis of received results, it was chosen one the best neural network, the main parameters of which were described and discussed in the article. Received results of working built of neural networks were compared with previously functioning manual evaluation module of these tracers. On the basis conducted analyses, proposed the modification of functioning test methodology by replacing the previous manual evaluation modules through elaborated automatic models of artificial neural networks. Artificial neural networks have a very important feature, namely they are used in the prediction of specific output data. This feature successfully used in diagnostic tests of other elements of ammunition.

Use of Artificial Neural Networks and Arima to Forecasting Consumption Sawnwood of Pinus sp. in Brazil

2019 ◽  
Vol 21 (1) ◽  
pp. 51-61 ◽  
Author(s):  
D.A. Buratto ◽  
R. Timofeiczyk Junior ◽  
J.C.G.L. Silva ◽  
J.R. Frega ◽  
M.S.S.A. Wiecheteck ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Mean Squared Error ◽  
Arima Model ◽  
Secondary Data ◽  
Information Criterion ◽  
Absolute Error ◽  
Percentage Error ◽  
Explanatory Variables ◽  
Artificial Neural

The objective of this study was to analyze the application of an artificial neural networks model and an ARIMA model to predict the consumption of sawnwood of pine. For this, we use real and secondary data collected and obtained from a historical data source, corresponding to the period from 1997 to 2016, which were later tested to generate the forecast models. Based on economic and statistical criteria, six explanatory variables were used to fit the best model. The choice of the model was made based on Mean Squared Error, Mean Absolute Error, Theil U metric, Percentage Error of Forecast and Akaike value information criterion. The results indicated that the models generated through the ARIMA model presented better performance when compared to the artificial neural network. The best adjusted model estimated a reduction of 1.33% in consumption of sawnwood of pine in Brazil for the period between 2017 and 2020.

Sign in / Sign up

Export Citation Format

Share Document