Networks calibration

One of the tasks that can be accomplished relatively easily in flow analysis is the creation of conditions that allow a series of measurement results to be obtained using only a single standard solution (and not several standard solutions). A classic example is the network calibration method, performed using a flow system made up of a network of tubes of different lengths connected to each other prior to the detector (Fig. 3.10a) [6]. In this system, the injected segment of standard solution is... 

Fig. 3.10 Network calibration method (a) St standard solution, S sample solution, Det detection system (b) P1-P5 characteristic points serving for construction of the calibration graphs (see Fig. 3.11) t time after injection...

Fig. 3.11 Interpretation of the measurement data obtained in the network calibration method Pj-Ps signals obtained for the set of standard solutions, R j-/fx5 signals obtained for the sample, analyte concentration in the standard solution, calculated analyte concentration in the sample...

Cu, Ni Electroplating solutions UV—Vis 0.5-6.0mgL 1 Cu 1.0—15.0 mg L-1 Ni 120 Artificial neural networks calibration/catalytic method/zone stopping [141]... 

Cu, Zn, Ni, Mn Natural waters UV-Vis 0.1—2.0 mg L"1 ca 100 Sequential injection system/artificial neural networks calibration [142]... 

Vitamins Bi, B2, B6 Tablet dissolution tests Fluorimetry Not relevant 135 Chemometrics involving an artificial neural networks calibration/zone stopping at the detector [156]... 

N. Chu, C. Ding, S.-H. Fan, Stopped-flow sequential injection spectrophotometry for simultaneous determination of Cu, Zn, Ni, and Mn in environmental water with artificial neural networks calibration, Anal. Lett. 43 (2010) 335. 

Cacas, M. C., Ledoux, E., de Marsily, G., Tillie, B., Barbreau, B., Durand, A., Feuga B. and Peaudecerf, P. 1990. Modeling fracture flow with a stochastic discrete fracture network Calibration and validation, 1, The flow model. Water Resour. Res., 26(3), pp. 479-489. 

In addition to fulfilling the in-house requirements for quality control, state and local air monitoring networks which are collecting data for compliance purposes are required to have an external performance audit on an annual basis. Under this program, an independent organization supplies externally calibrated sources of air pollutant gases to be measured by the instrumentation undergoing audit. An audit report summarizes the performance of the instruments. If necessary, further action must be taken to eliminate any major discrepancies between the internal and external calibration results. 

The sensor usually consists of a coil of wire made from the material that is wound on a former and the whole sealed to prevent oxidization, although a film of the metal deposited on a ceramic substrate can also be used. The resistor is connected in a Wheatstone bridge network (Figure 17.17), using fixed resistors in the other three arms. The instrument connected across the bridge is calibrated directly in terms of temperature. The range is limited by the linearity of the device and the upper temperature, which can be measured, must be well below the melting point of the material. 

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... 

M. Click and G.M. Hieftje, Classification of alloys with an artificial neural network and multivariate calibration of Glow-Discharge emission spectra. Appl. Spectrosc., 45 (1991) 1706-1716. 

A. Bos, M. Bos and W.E. Van der Linden, Artificial neural networks as a multivariate calibration tool modeling the ion-chromium nickel system in x-ray fluorescence spectra. Anal. Chim. Acta, 277 (1993) 289-295. 

M.N. Tib and R. Narayanaswamy, Multichannel calibration technique for optical-fibre chemical sensor using artificial neural network. Sensors Actuators, B39 (1997) 365-370. 

The variable delay can be as simple as an RC network. Often the variable delay line is calibrated directly in terms of lifetime units (nanoseconds). When the reference and comparison signals are in phase the fluorescence lifetimes can simply be read off the calibrated variable delay. 

Goodacre, R. Trew, S. Wrigley-Jones, C. Neal, M. J. Maddock, J. Ottley, T. W. Porter, N. Kell, D. B. Rapid screening for metabolite overproduction in fermentor broths using pyrolysis mass spectrometry with multivariate calibration and artificial neural networks. Biotechnol. Bioengin. 1994, 44,1205-1216. 

For PyMS to be used for (1) routine identification of microorganisms and (2) in combination with ANNs for quantitative microbiological applications, new spectra must be comparable with those previously collected and held in a data base.127 Recent work within our laboratory has demonstrated that this problem may be overcome by the use of ANNs to correct for instrumental drift. By calibrating with standards common to both data sets, ANN models created using previously collected data gave accurate estimates of determi-nand concentrations, or bacterial identities, from newly acquired spectra.127 In this approach calibration samples were included in each of the two runs, and ANNs were set up in which the inputs were the 150 new calibration masses while the outputs were the 150 old calibration masses. These associative nets could then by used to transform data acquired on that one day to data acquired at an earlier data. For the first time PyMS was used to acquire spectra that were comparable with those previously collected and held in a database. In a further study this neural network transformation procedure was extended to allow comparison between spectra, previously collected on one machine, with spectra later collected on a different machine 129 thus calibration transfer by ANNs was affected. Wilkes and colleagues130 have also used this strategy to compensate for differences in culture conditions to construct robust microbial mass spectral databases. 

M. L. Magee, J. T. On mass spectrometer instrument standardization and interlaboratory calibration transfer using neural networks. Anal. Chim. Acta 1997,384, 511-532. 

In analytical chemistry, Artificial Neural Networks (ANN) are mostly used for calibration, see Sect. 6.5, and classification problems. On the other hand, feedback networks are usefully to apply for optimization problems, especially nets ofHoPFiELD type (Hopfield [1982] Lee and Sheu [1990]). 

Intensified metabolic control, especially in case of diabetes, demands minimal-invasive or non-invasive methods of analytical measurement. For this goal, a method has been developed to measure the blood glucose content in vivo, in direct contact with the skin, by means of diffuse reflection near infrared (NIR) spectroscopy on the basis of multivariate calibration and neural networks (Muller et al. [1997] Fischbacher et al. [1997] Danzer et al. [1998]). Because no patients with any standard blood glucose value are available in principle, a method of indirect calibration has... 

Neural networks are applied in analytical chemistry in many and diverse ways. Used in calibration, ANNs have especially advantages in case of nonlinear relationships, multicomponent systems and single component analysis in case of various disturbances. 

Another form of artificial intelligence is realized in artificial neural networks (ANN). The principle of ANNs has been presented in Sect. 6.5. Apart from calibration, data analysis and interpretation is one of the most important fields of application of ANNs in analytical chemistry (Tusar et al. [1991] Zupan and Gasteiger [1993]) where two branches claim particular interest ... 

Both cases can be dealt with both by supervised and unsupervised variants of networks. The architecture and the training of supervised networks for spectra interpretation is similar to that used for calibration. The input vector consists in a set of spectral features yt(Zj) (e.g., intensities at selected wavelengths zi). The output vector contains information on the presence and absence of certain structure elements and groups fixed by learning rules (Fig. 8.24). Various types of ANN models may be used for spectra interpretation, viz mainly such as Adaptive Bidirectional Associative Memory (BAM) and Backpropagation Networks (BPN). The correlation... 

---