Artificial neural networks instrumentation

Several additional instrumental techniques have also been developed for bacterial characterization. Capillary electrophoresis of bacteria, which requires little sample preparation,42 is possible because most bacteria act as colloidal particles in suspension and can be separated by their electrical charge. Capillary electrophoresis provides information that may be useful for identification. Flow cytometry also can be used to identify and separate individual cells in a mixture.11,42 Infrared spectroscopy has been used to characterize bacteria caught on transparent filters.113 Fourier-transform infrared (FTIR) spectroscopy, with linear discriminant analysis and artificial neural networks, has been adapted for identifying foodbome bacteria25,113 and pathogenic bacteria in the blood.5... 

A screening design detected significant instrumental and chemical variables to volatilise and measure Sb. They were optimised using response surfaces derived from central composite designs. Findings were confirmed using artificial neural networks... 

One commercially available sensor array analysis system, offered by Mosaic Industries [51], is Rhino , a microprocessor-based instrument with an array composed of discrete, resistive gas sensors. An artificial neural network processes sensor inputs and relates them to patterns established by training the instrument with gas components and mixtures of interest for a specific application. In principle, each system is customized for an application by the choice of sensors and the gas detection needs. Potential applications for this system are limited by the availability of suitable sensors and the complexity needed for discrimination. 

Many instruments aheady have some chemometrics routines built into their software in such a way that their use is totally transparent to the final user (and sometimes the word chemometrics is not even mentioned, to avoid possible aversion). Of course, they are closed routines, and therefore the user cannot modify them. It is quite obvious that it would be much better if chemometric knowledge were much more widespread, in order that the user could better understand what kind of treatment the data have undergone and eventually modify the routines in order to make them more suitable to the user s requirements. As computers become faster and faster, it is nowadays possible to routinely apply some approaches requiring very high computing power. Two of them are Genetic Algorithms (GA) and Artificial Neural Networks (ANN). 

Eden Prairie, MN), DICKEY-john OmegAnalyzerG (DICKEY-john Corp, Auburn, IL), Perten DA 7200 (Perten Instruments Inc., Springfield, IL), Bruker Optics/ Cog-nis QTA (Brucker Optics Inc., Billerica, MA), and an ASD LabSpec Pro (Analytical Spectral Devices Inc., Boulder, CO) for 18 amino acids. Partial least squares (PLS) and support vector machines (SVM) regression models performed significantly better than artificial neural networks (ANN). They used a calibration data set of 526 samples... 

During the early stages of our bee biomonitoring project, we chemically profiled each component that was used in the construction of our instrumented hive condos (Table 2.4). Unpainted pine boards were rich in terpene peaks. In fact, using artificial neural networks, we were often able to identify from which hive a sample came, based heavily on their individual terpene fingerprints [112, 113]. Vinyl screens gave rise to several ethers. Polyethylene parts released various aromatic and aliphatic derivatives. The application of white paint to the exterior surfaces of hive boxes added some organic acids, alcohols, and additional hydrocarbons to the hive environment. 

Neural networks have been used, most effectively, as a way of establishing robust NIR calibrations. It is the calibration method of choice for a whole cereal grain, transmission instrument, which is being used worldwide for many of the analyses required for estimating grain quality. An artificial neural network program performs many iterations in order to establish the optimum solution required from large, complex datasets. 

Complex chemical systems are composed of one or more components in a mixture with a significant degree of spectral interference, or of several components with a large amount of mutual physical and/or chemical interaction. In these cases, quantitative analysis is best performed by statistical methods such as principal component regression (PCR) or partial least squares (PLS) [36] these are offered in the software packages of instrument manufacturers and software suppliers. Artificial neural networks (ANNs) should be primarily used when a data set is nonlinear [37]. 

Since the 1970s, NIR spectroscopy has provided the means to test wheat at delivery to handlers, merchants, or direct to the mill. For ground wheat, protein may be determined with three or four fixed filters 2180, 2100 (1940 required for corrected moisture basis), and either 1680 or 2230 nm. In countries with wheat grading systems, such as Australia, Canada, and the US, segregation is carried out on the basis of load-by-load NIR testing of growers deliveries at country silos. Nowadays, this is almost exclusively by whole grain instruments, the most popular of which is the FOSS Infratec. This type of instrument is calibrated with tens of thousands of samples and development of a model based on artificial neural networks (8, 9). 

---