The application of artificial neural networks for the selection of key thermoanalytical parameters in medicinal plants analysis

In the present study three thermoanalytical methods: differential thermal analysis (DTA), thermogravimetric analysis (TGA), and derivative thermogravimetric analysis (DTG) were used to investigate the thermal behavior of medicinal plant raw materials. In order to describe DTA curve, designation of the onset T(i), and peak T(p), temperatures was required. In TGA the mass losses Delta(m), and in DTG the temperature range of peak DeltaT, peak temperature T(p), and peak height h, were recorded. All parameters were read for three stages of the thermal decomposition of plant samples which resulted in obtaining eighteen thermal variables for each sample. Some similarities in the course of thermal decomposition of the same plant organs were recognized, but complexity of the obtained data made it very difficult to determine if they could differentiate between medicinal plant materials and which of them encode the most valuable information about the studied herbals. In order to confirm the existence of any relations between the chemical composition of medicinal plants and their thermal decomposition and to find out which thermoanalytical variables or decomposition stages can be considered as the most significant in terms of their evaluation, it was decided to apply fully connected feed-forward artificial neural networks (ANN). Two different training algorithms were used to address the problem: back-propagation of error and conjugate gradient descent. To verify the results two-dimensional (2-D) Kohonen self-organizing feature maps (SOFMs) were employed. Two alternative datasets of thirteen key variables discriminating plant samples have been proposed.     

Artificial neural networks based on principal component analysis input selection for clinical pattern recognition analysis

Two clinical data sets were applied for pattern recognition in order to discover the correlation between urinary nucleoside profiles and tumours. One data set contains 168 clinical urinary samples, of which 84 specimens are from female thyroid cancer patients (malignant tumour group), and the other samples were collected from healthy women (normal group). However, 168 clinical urinary samples comprised the second data set, too. In all the specimens, each number of the samples for both uterine cervical cancer patients (malignant tumour group) and healthy females (normal group) is 60, and the other 48 samples were collected from uterine myoma patients (benign tumour group). For the two data sets, the separation and quantitative determination of the clinical urinary nucleosides were performed by capillary electrophoresis (CE). The pattern recognition was achieved applying multiple layer perceptron artificial neural networks (MLP ANN) based on conjugate gradient descent training algorithm. Moreover, applying the proposed principal component analysis (PCA) input selection scheme to MLP ANN, the accuracy rate of the pattern recognition was improved to some extent (or without any deterioration) even by much simpler structure of MLP ANN. The study showed that MLP ANN based on PCA input selection was a promising tool for pattern recognition.     

Growing neural networks for a multivariate calibration and variable selection of time-resolved measurements

In this study, an algorithm for growing neural networks is proposed. Starting with an empty network the algorithm reduces the error of prediction by subsequently inserting connections and neurons. The type of network element and the location where to insert the element is determined by the maximum reduction of the error of prediction. The algorithm builds non-uniform neural networks without any constraints of size and complexity. The algorithm is additionally implemented into two frameworks, which use a data set limited in size very efficiently, resulting in a more reproducible variable selection and network topology.

The algorithm is applied to a data set of binary mixtures of the refrigerants R22 and R134a, which were measured by a surface plasmon resonance (SPR) device in a time-resolved mode. Compared with common static neural networks all implementations of the growing neural networks show better generalization abilities resulting in low relative errors of prediction of 0.75% for R22 and 1.18% for R134a using unknown data.     

Complementary use of partial least-squares and artificial neural networks for the non-linear spectrophotometric analysis of pharmaceutical samples

The complementary use of partial least-squares (PLS) multivariate calibration and artificial neural networks (ANNs) for the simultaneous spectrophotometric determination of three active components in a pharmaceutical formulation has been explored. The presence of non-linearities caused by chemical interactions was confirmed by a recently discussed methodology based on Mallows augmented partial residual plots. Ternary mixtures of chlorpheniramine, naphazoline and dexamethasone in a matrix of excipients have been resolved by using PLS for the two major analytes (chlorpheniramine and naphazoline) and ANNs for the minor one (dexamethasone). Notwithstanding the large number of constituents, their high degree of spectral overlap and the occurrence of non-linearities, rapid and simultaneous analysis has been achieved, with reasonably good accuracy and precision. No extraction procedures using non-aqueous solvents are required.     

The use of artificial neural networks for the selection of the most appropriate thermal parameters and for the classification of a set of phenylcarbamic acid derivates

The objective of this work was to apply artificial neural networks (ANNs) to the classification group of 43 derivatives of phenylcarbamic acid. To find the appropriate clusters Kohonen topological maps were employed. As input data, thermal parameters obtained during DSC and TG analysis were used. Input feature selection (IFS) algorithms were used in order to give an estimate of the relative importance of various input variables. Additionally, sensitivity analysis was carried out to eliminate less important thermal variables. As a result, one classification model was obtained, which can assign our compounds to an appropriate class. Because the classes contain groups of molecules structurally related, it is possible to predict the structure of the compounds (for example the position of the substitution alkoxy group in the phenyl ring) on the basis of obtained parameters.     

Use of neural networks in on-line analysis

The evaluation principles of neural networks are presented and compared with common known techniques. The concepts in data processing, introduced by neural nets are explained and processing types implemented by neural networks are presented. The evaluation of gas sensitive sensors will be an example for the special features of neural nets, with a focus to the self-organizing map.@peanuts.informatik.uni-tuebingen.de     

Parameter selection for peak alignment in chromatographic sample profiling: objective quality indicators and use of control samples

In chromatographic profiling applications, peak alignment is often essential as most chromatographic systems exhibit small peak shifts over time. When using currently available alignment algorithms, there are several parameters that determine the outcome of the alignment process. Selecting the optimum set of parameters, however, is not straightforward, and the quality of an alignment result is at least partly determined by subjective decisions. Here, we demonstrate a new strategy to objectively determine the quality of an alignment result. This strategy makes use of a set of control samples that are analysed both spiked and non-spiked. With this set, not only the system and the method can be checked but also the quality of the peak alignment can be evaluated. The developed strategy was tested on a representative metabolomics data set using three software packages, namely Markerlynx™, MZmine and MetAlign. The results indicate that the method was able to assess and define the quality of an alignment process without any subjective interference of the analyst, making the method a valuable contribution to the data handling process of chromatography-based metabolomics data.     

Artificial neural networks based on genetic input selection for quantification in overlapped capillary electrophoresis peaks

The application of multilayer perceptron artificial neural networks (MLP ANN) based on genetic input selection for quantification of the unresolved peaks in micellar electrokinetic capillary chromatography (MECC) is reported. An optimization strategy for genetic input selection was also proposed. When the corresponding CE peaks cannot be resolved completely only by separation techniques, MLP ANN based on genetic input selection can be a suitable tool to resolve the problem. Both the spectra and the electrophoretograms of the unseparated analytes were used as the multivariate input data. The two kinds of the data were suitable for quantification of overlapped CE peaks by MLP ANN based on genetic input selection. The study also shows that the applying of genetic input selection in MLP ANN can improve the precision of quantification in both completely and partially overlapped CE peaks to some extent.     

On the use of computational neural networks for the prediction of polymer properties

A general purpose computational paradigm using neural networks is shown to be capable of efficiently predicting properties of polymeric compounds based on the structure and composition of the monomeric repeat unit. Results are discussed for the prediction of the heat capacity, glass transition temperature, melting temperature, change in the heat capacity at the glass transition temperature, degradation temperature, tensile strength and modulus, ultimate elongation, and compressive strength for 11 different families of polymers. The accuracies of the predictions range from 1–13% average absolute error. The worst results were obtained for the mechanical properties (tensile strength and modulus: 13%, 7% elongation: 12%, and compressive strength: 8%) and the best results for the thermal properties (heat capacity, glass transition temperature, and melting point: <4%). A simple modification to the overall method is devised to better take into account the fact that the mechanical properties are experimentally determined with a fairly large range (due to variability in measurement procedures and especially the sample). This modification treats the bounds on the range for the mechanical properties as complex numbers (complex, modular neural networks) and leads to more rapid optimization with a smaller average error (reduced by 3%).Dedicated to Professor Bernhard Wunderlich on the occasion of his 65th birthdayThis research was sponsored by the Division of Materials Sciences, Office of Basic Energy Sciences, U.S. Department of Energy, under Contract No. DE-AC05-84R21400 with Lockheed Martin Energy Systems, Inc. We would like to express our gratitude for the continued collaboration, support, and interest of Prof. Wunderlich in our research. We would also like to thank participants of the 1st DOE Workshop on Applications of Neural Networks in Materials Sciences for useful discussion on materials properties and neural networks.     

The analysis of seasonal air pollution pattern with application of neural networks

Air pollution monitoring includes measuring the concentrations of air contaminants such as nitrogen dioxide, sulfur dioxide, some polycyclic aromatic hydrocarbons(PAHs), suspended particulate matter (PM) and tar substances. The purpose of this study was to determine the possibility of using artificial neural networks for identification of any patterns occurring during heating and nonheating seasons. The samples included in the study were collected over a period of 5 years (1997–2001) in the area of the city of Gdansk and the levels of pollutants measured in the samples collected were used as inputs to two different types of neural networks: multilayer perceptron (MLP) and self-organizing map (SOM). The MLP was used as a tool to predict in what heating season a certain sample was collected, and the SOM was applied for mapping all samples to recognize any similarities between them. This study also presents the comparison between two projection methods—linear (principal component analysis, PCA) and nonlinear (SOM)—in extracting valuable information from multidimensional environmental data. In the research the MLP model with 13-12-1 topology was developed and successfully trained for classification of air samples from different seasons. The sensitivity analysis on the inputs to the MLP indicated benz[α]anthracene, benzo[α]pyrene, PM₁, SO₂, tar substances and PM₁₀ as the most distinctive variables, while PCA pointed to PAHs and PM₁.     

Artificial neural networks in analysis of indinavir and its degradation products retention

Artificial neural networks (ANN) are biologically inspired computer programs designed to simulate the way in which the human brain processes the information. In the past few years, coupling of experimental design (ED) and ANN became useful tool in the method optimization. This paper presents the application of ED-ANN in analysis of chromatographic behavior of indinavir and its degradation products. According to preliminary study, full factorial design 2⁴ was chosen to set input variables for network training. Experimental data (inputs) and results for retention factors from experiments (outputs) were used to train the ANN with aim to define correlation among variables. For networks training multi-layer perceptron (MLP) with back propagation (BP) algorithm was used. Network with the lowest root mean square (RMS) had 4-8-3 topology. Predicted data were in good agreement with experimental data (correlation was higher than 0.9713 for training set). Regression statistics confirmed good ability of trained network to predict compounds retention.     

The use of microwave ovens for rapid organic synthesis

Four different types of organic reactions have been studied and seven different organic compounds have been prepared, under pressure in a microwave oven. Considerable rate increases have been observed.     

STXMPy: a new software package for automated region of interest selection and statistical analysis of XANES data

Background  

Soft X-ray spectromicroscopy based absorption near-edge structure analysis, is a spectroscopic technique useful for investigating sample composition at a nanoscale of resolution. While the technique holds great promise for analysis of biological samples, current methodologies are challenged by a lack of automatic analysis software e. g. for selection of regions of interest and statistical comparisons of sample variability.     

The use of polymer heteronuclei for crystalline polymorph selection

A method for the production of crystalline polymorphs from solution is described which utilizes a diverse set of polymer heteronuclei. Application to crystalline polymorph selection for the important pharmaceuticals acetaminophen and carbamazepine is demonstrated. This method provides a new paradigm for polymorph selection, where solvent and temperature conditions can be chosen on the basis of process considerations and the polymer heteronucleus can be varied for specific polymorph production.     

Classification of rapeseed and soybean oils by use of unsupervised pattern-recognition methods and neural networks

Unsupervised pattern-recognition methods and Kohonen neural networks have been applied to the classification of rapeseed and soybean oil samples according to their type and quality by use of chemical and physical properties (density, refractive index, saponification value, and iodine and acid numbers) and thermal properties (thermal decomposition temperatures) as variables. A multilayer feed-forward (MLF) neural network (NN) has been used to select the most important variables for accurate classification of edible oils. To accomplish this task different neural networks architectures trained by back propagation of error method, using chemical, physical, and thermal properties as inputs, were employed. The network with the best performance and the smallest root mean squared (RMS) error was chosen. The results of MLF network sensitivity analysis enabled the identification of key properties, which were again used as variables in principal components analysis (PCA), cluster analysis (CA), and in Kohonen self-organizing feature maps (SOFM) to prove their reliability.     

Spectroscopic identification and quantitative analysis of binary mixtures using artificial neural networks

This work deals with the application of artificial neural networks to two common problems in spectroscopy: the identification of distorted UV-visible spectra of a specific class of organic compounds, and the quantitative determination of single components in binary mixtures of these compounds. The examined species were six organic indicators, whose spectra are very similar to each other; the trained networks have proven to be very powerful in both applications.