Universal technique for optimization of neural network training parameters: gasoline near infrared data example

Abstract

The universal technique of finding optimum training parameters for multi-layer perceptron-such as percentage of samples in a cross-validation set and quantities of training iterations with various initial values-is offered. This technique is aimed at the searching of optimum values of two complex factors depending on accuracy and convergence of a network, and also on the time of its training. Their conventional names are ''cross-validation coefficient'' and ''training iteration coefficient''. Near infrared spectroscopy data for gasoline samples are used to evaluate the efficiency of the method.

Near-Infrared (NIR) Spectroscopy for Biodiesel Analysis: Fractional Composition, Iodine Value, and Cold Filter Plugging Point from One Vibrational Spectrum

“…Vegetable oils are other complex samples, which are interesting for NIR analysis. The results presented herein can help in the rapid and accurate analysis of other biofuels (e.g., bioalcohols/alcohol fuel, ethanol–gasoline fuel, cellulosic ethanol, bioethers, algae fuel), products of petroleum refining (liquid petroleum gas, gasoline, naphtha, kerosene/jet aircraft fuels, diesel fuel, (marine) fuel oils, lubricating and industrial oils, paraffin wax, asphalt and tar, and petroleum coke) and petrochemicals (olefins and their precursors, aromatic hydrocarbons (e.g., benzene or mixed xylenes)). − The use of NIR spectroscopy in other fields of analytical chemistry, such as pharmaceutical (drug) quality control, food quality control (green and black tea, apples, grapes, etc. ), and active pharmaceutical ingredient (API)/pharmacon (pharmakon) analysis of tablets, , can be enhanced by application of modern methods of multivariate data analysis, including ANNs as well as other machine learning methods (data mining, pattern recognition, adaptive control) within the framework of Bayesian statistics. , Other analytical methods, such as gas chromatography (GC), nuclear magnetic resonance spectroscopy (NMR), ultraviolet–visible light spectroscopy (UV–vis), infrared (IR) and Raman vibrational spectroscopies, can greatly gain from combination with ANNs.…”

“…This Introduction will discuss three issues that are important for the current study, namely, (i) near-infrared (NIR) spectroscopy and its role in modern analytical chemistry, − (ii) biofuels as an alternative to the traditional diesel fuel, − and (iii) modern methods of data analysis. − References for detailed discussions will be provided.…”

Prediction of the Hypertension Risk of the Elderly in Built Environments Based on the LSTM Deep Learning and Bayesian Fitting Method

“…A deep learning algorithm is used to predict parameters through training data, provided that the most accurate ratio between training time and its reproducibility is the best value of the number of iterations [54]. Training samples are used to adjust the parameters in the training factors.…”

The Use of UV-Visible Reflectance Spectroscopy as an Objective Tool to Evaluate Pearl Quality

“…In such cases a more empirical approach such as the use of an ANN is more useful. Thus, the main reason selecting a more complex model, such as an ANN, over PCR or latent variables based models, such as partial least squares discriminant analysis (PLS-DA), is the presence of strong non-linearity in the data [ 17 , 18 ]. The ANN modeling technique has attracted increasing interest in recent years as a most promising candidate for classification and multivariate calibration problems.…”