Modeling with artificial neural networks

Moreno, L., Cartas, R., Merkogi, A., Alegret, S., Gutierrez, J.M., Leija, L., Hernandez, P.R., Munoz, R. Data Compression for a Voltammetric Electronic Tongue Modelled with Artificial Neural Networks. Anal. Lett. 38, 2189-2206 (2005)... 

The application of hybrid modelling to chemical and biochemical reactors has been exemplified in several works. The most widely adopted hybrid structure is based on the mass balance equations, like in the traditional first principles approach, but the reaction kinetics are modelled with artificial neural networks (ANNs) (Psichogios and Ungar (1992), Schubert et al. (1994), Montague and Morris (1994), Feyo de Azevedo et al. 

L. Hadjiiski, P. Geladi and Ph. Hopke, A comparison of modelling nonlinear systems with artificial neural networks and partial least squares, Chemom. Intell. Lab. Syst., 49, 1999, 91-103. 

Thus, multilinear models were introduced, and then a wide series of tools, such as nonlinear models, including artificial neural networks, fuzzy logic, Bayesian models, and expert systems. A number of reviews deal with the different techniques [4-6]. Mathematical techniques have also been used to keep into account the high number (up to several thousands) of chemical descriptors and fragments that can be used for modeling purposes, with the problem of increase in noise and lack of statistical robustness. Also in this case, linear and nonlinear methods have been used, such as principal component analysis (PCA) and genetic algorithms (GA) [6]. 

Givehchi, A. and Schneider, G. (2004) Impact of descriptor vector scaling on the classification of drugs and nondrugs with artificial neural networks./. Mol. Model., 10, 204—211. 

Modelling Cells Reaction Kinetics with Artificial Neural Networks A Comparison of Three Network Architectures... 

A structure descriptor is a mathematical representation of a molecule resulting from a procedure transforming the structural information encoded within a symbolic representation of a molecule. This mathematical representation has to be invariant to the molecule s size and number of atoms, to allow model building with statistical methods and artificial neural networks. 

Since biological systems can reasonably cope with some of these problems, the intuition behind neural nets is that computing systems based on the architecture of the brain can better emulate human cognitive behavior than systems based on symbol manipulation. Unfortunately, the processing characteristics of the brain are as yet incompletely understood. Consequendy, computational systems based on brain architecture are highly simplified models of thek biological analogues. To make this distinction clear, neural nets are often referred to as artificial neural networks. 

Recently, a new approach called artificial neural networks (ANNs) is assisting engineers and scientists in their assessment of fuzzy information, Polymer scientists often face a situation where the rules governing the particular system are unknown or difficult to use. It also frequently becomes an arduous task to develop functional forms/empirical equations to describe a phenomena. Most of these complexities can be overcome with an ANN approach because of its ability to build an internal model based solely on the exposure in a training environment. Fault tolerance of ANNs has been found to be very advantageous in physical property predictions of polymers. This chapter presents a few such cases where the authors have successfully implemented an ANN-based approach for purpose of empirical modeling. These are not exhaustive by any means. 

Even so, artificial neural networks exhibit many brainlike characteristics. For example, during training, neural networks may construct an internal mapping/ model of an external system. Thus, they are assumed to make sense of the problems that they are presented. As with any construction of a robust internal model, the external system presented to the network must contain meaningful information. In general the following anthropomorphic perspectives can be maintained while preparing the data ... 

An artificial neural network based approach for modeling physical properties of nine different siloxanes as a function of temperature and molecular configuration will be presented. Specifically, the specific volumes and the viscosities of nine siloxanes were investigated. The predictions of the proposed model agreed well with the experimental data [41]. 

Ibric S, Jovanovic M, Djuric A, Parojcic J, Petrovic SD, Solomun L, Stupor B. Artificial neural networks in the modelling and optimization of aspirin extended release tablets with Eudragit LlOO as matrix substance. Pharm Sci Tech 2003 4 62-70. 

Aqueous solubility is selected to demonstrate the E-state application in QSPR studies. Huuskonen et al. modeled the aqueous solubihty of 734 diverse organic compounds with multiple linear regression (MLR) and artificial neural network (ANN) approaches [27]. The set of structural descriptors comprised 31 E-state atomic indices, and three indicator variables for pyridine, ahphatic hydrocarbons and aromatic hydrocarbons, respectively. The dataset of734 chemicals was divided into a training set ( =675), a vahdation set (n=38) and a test set (n=21). A comparison of the MLR results (training, r =0.94, s=0.58 vahdation r =0.84, s=0.67 test, r =0.80, s=0.87) and the ANN results (training, r =0.96, s=0.51 vahdation r =0.85, s=0.62 tesL r =0.84, s=0.75) indicates a smah improvement for the neural network model with five hidden neurons. These QSPR models may be used for a fast and rehable computahon of the aqueous solubihty for diverse orgarhc compounds. 

In recent years there has been much activity to devise methods for multivariate calibration that take non-linearities into account. Artificial neural networks (Chapter 44) are well suited for modelling non-linear behaviour and they have been applied with success in the field of multivariate calibration [47,48]. A drawback of neural net models is that interpretation and visualization of the model is difficult. Several non-linear variants of PCR and PLS regression have been proposed. Conceptually, the simplest approach towards introducing non-linearity in the regression model is to augment the set of predictor variables (jt, X2, ) with their respective squared terms (xf,. ..) and, optionally, their possible cross-product... 

In the last decades not only thousands of chemical descriptors but also many advanced, powerful modeling algorithms have been made available, The older QSAR models were linear equations with one or a few parameters. Then, other tools have been introduced, such as artificial neural network, fuzzy logic, and data mining algorithms, making possible non linear models and automatic generation of mathematical solutions. 

Artificial neural networks are now widely used in science. Not only are they able to learn by inspection of data rather than having to be told what to do, but they can construct a suitable relationship between input data and the target responses without any need for a theoretical model with which to work. For example, they are able to assess absorption spectra without knowing about the underlying line shape of a spectral feature, unlike many conventional methods. 

Over the last several years, the number of studies on application of artificial neural network for solving modeling problems in analytical chemistry and especially in optical fibre chemical sensor technology, has increase substantially69. The constructed sensors (e.g. the optical fibre pH sensor based on bromophenol blue immobilized in silica sol-gel film) are evaluated with respect to prediction of error of the artificial neural network, reproducibility, repeatability, photostability, response time and effect of ionic strength of the buffer solution on the sensor response. 

Use of multivariate approaches based on classification modelling based on cluster analysis, factor analysis and the SIMCA technique [98,99], and the Kohonen artificial neural network [100]. All these methods, though rarely implemented, lead to very good results not achievable with classical strategies (comparisons, amino acid ratios, flow charts) and, moreover it is possible to know the confidence level of the classification carried out. 

---