Full-range optical pH sensor based on imaging techniques

A new colour-based disposable sensor array for a full pH range (0-14) is described. The pH sensing elements are a set of different pH indicators immobilized in plasticized polymeric membranes working by ion-exchange or co-extraction. The colour changes of the 11 elements of the optical array are obtained from a commercial scanner using the hue or H component of the hue, saturation, value (HSV) colour space, which provides a robust and precise parameter, as the analytical parameter. Three different approaches for pH prediction from the hue H of the array of sensing elements previously equilibrated with an unknown solution were studied: Linear model, Sigmoid competition model and Sigmoid surface model providing mean square errors (MSE) of 0.1115, 0.0751 and 0.2663, respectively, in the full-range studied (0-14). The performance of the optical disposable sensor was tested for pH measurement, validating the results against a potentiometric reference procedure. The proposed method is quick, inexpensive, selective and sensitive and produces results similar to other more complex optical approaches for broad pH sensing.     

Application of an artificial neural network (ANN) and piezoelectric chemical sensor array for identification of volatile organic compounds

A piezoelectric chemical sensor array was developed using four quartz crystals. Gas chromatographic stationary phases were used as sensing materials and the array was connected to an artificial neural network (ANN). The application of the ANN method proved to be particularly advantageous if the measured property (mass, concentration, etc.) should not be connected exactly to the signal of the transducers of the piezoelectric sensor. The optimum structure of neural network was determined by a trial and error method. Different structures were tried with several neurons in the hidden layer and the total error was calculated. The optimum values of primary weight factors, learning rate (η=0.15), momentum term (μ=0.9), and the sigmoid parameter (β=1) were determined. Finally, three hidden neurons and 900 training cycles were applied. After the teaching process the network was used for identification of taught analytes (acetone, benzene, chloroform, pentane). Mixtures of organic compounds were also analysed and the ANN method proved to be a reliable way of differentiating the sensing materials and identifying the volatile compounds.     

Application of an artificial neural network (ANN) and piezoelectric chemical sensor array for identification of volatile organic compounds

A piezoelectric chemical sensor array was developed using four quartz crystals. Gas chromatographic stationary phases were used as sensing materials and the array was connected to an artificial neural network (ANN). The application of the ANN method proved to be particularly advantageous if the measured property (mass, concentration, etc.) should not be connected exactly to the signal of the transducers of the piezoelectric sensor. The optimum structure of neural network was determined by a trial and error method. Different structures were tried with several neurons in the hidden layer and the total error was calculated. The optimum values of primary weight factors, learning rate (η=0.15), momentum term (μ=0.9), and the sigmoid parameter (β=1) were determined. Finally, three hidden neurons and 900 training cycles were applied. After the teaching process the network was used for identification of taught analytes (acetone, benzene, chloroform, pentane). Mixtures of organic compounds were also analysed and the ANN method proved to be a reliable way of differentiating the sensing materials and identifying the volatile compounds.     

Neural network modelling of adsorption isotherms

This paper examines the possibility to use a single neural network to model and predict a wide array of standard adsorption isotherm behaviour. Series of isotherm data were generated from the four most common isotherm equations (Langmuir, Freundlich, Sips and Toth) and the data were fitted with a unique neural network structure. Results showed that a single neural network with a hidden layer having three neurons, including the bias neuron, was able to represent very accurately the adsorption isotherm data in all cases. Similarly, a neural network with four hidden neurons, including the bias, was able to predict very accurately the temperature dependency of adsorption data.     

An electronic tongue using potentiometric all-solid-state PVC-membrane sensors for the simultaneous quantification of ammonium and potassium ions in water

The simultaneous determination of NH₄⁺ and K⁺ in solution has been attempted using a potentiometric sensor array and multivariate calibration. The sensors used are rather non-specific and of all-solid-state type, employing polymeric (PVC) membranes. The subsequent data processing is based on the use of a multilayer artificial neural network (ANN). This approach is given the name "electronic tongue" because it mimics the sense of taste in animals. The sensors incorporate, as recognition elements, neutral carriers belonging to the family of the ionophoric antibiotics. In this work the ANN type is optimized by studying its topology, the training algorithm, and the transfer functions. Also, different pretreatments of the starting data are evaluated. The chosen ANN is formed by 8 input neurons, 20 neurons in the hidden layer and 2 neurons in the output layer. The transfer function selected for the hidden layer was sigmoidal and linear for the output layer. It is also recommended to scale the starting data before training. A correct fit for the test data set is obtained when it is trained with the Bayesian regularization algorithm. The viability for the determination of ammonium and potassium ions in synthetic samples was evaluated; cumulative prediction errors of approximately 1% (relative values) were obtained. These results were comparable with those obtained with a generalized regression ANN as a reference algorithm. In a final application, results close to the expected values were obtained for the two considered ions, with concentrations between 0 and 40 mmol L^–1.     

Usage of Artificial Neural Network (Back Propagation) in Optimising Salicylic Acid Determination with Ferric(III) Nitrate

Abstract

The use of artificial neural networks (ANN) in optimizing salicylic acid (SA) determination is presented in this paper. A simple and rapid spectrophotometric method for salicylic acid (SA) determination was carried out based on the complexation of salicylic acid–ferric(III) nitrate, SAFe(III). The SA forms a stable purple complex with ferric(III) nitrate at pH 2.45. The useful dynamic linear range is 0.01–0.35 g/L. It has a maximum absorption at 524 nm and the stability is more than 50 hours. The results were used for artificial neural networks (ANNs) training to optimize data. For training and validation purposes, a back‐propagation (BP) artificial neural network (ANN) was used. The results showed that ANN technique was very effective and useful in broadening the limited dynamic linear response range mentioned to an extensive calibration response (0.01–0.70 g/L). It was found that a network with 22 hidden neurons was highly accurate in predicting the determination of SA. This network scores a summation of squared error (SSE) skill and low average predicted error of 0.0078 and 0.00427 g/L, respectively.     

Simultaneous determination of penicillin and ampicillin by spectral fibre-optical enzyme optodes and multivariate data analysis based on transient signals obtained by flow injection analysis

A multicomponent detection system using optical biosensors and flow injection analysis is described. The analysis of mixtures containing penicillin and ampicillin was realised by evaluating dynamic measurements of Phenol Red spectra in penicillinase optodes in combination with a diode array spectrometer. A variety of optodes has been produced by changing the composition of the receptor gel and the working pH. A set of characteristic quantities (describing dynamic and static features) could be obtained for each optode. These were used to compare the predictivity of classical multivariate calibration methods as well as of an artificial neural network. In addition, different algorithms were applied for the evaluation of the spectral data in order to select the most appropriate method for feature extraction. In consequence, the information obtained from the multivariate calibration models was used to set up an optimal sensor array consisting of four optodes with different types of penicillinase at different working pH.     

Ultrasonic treatment of water contaminated with various pollutants onto copper nanowires loaded on activated carbon using response surface methodology and artificial intelligent

In this study, the potential application of copper nanowires loaded on activated carbon for simultaneous removal of Disulfine blue (DB), Crystal violet (CV) and Sunset yellow (SY) has been described. The relation between adsorption properties with variables such as solution pH, adsorbent value, contact time and initial dyes concentration was investigated and optimized. A three‐layer artificial neural network (ANN) model was utilized to predict dyes removal (%) by adsorbent following conduction of experiments. The training of network at above mention experimental data confirms its ability to forecast the removal performance with a linear transfer function (purelin) at output layer. The Levenberg–Marquardt algorithm and tangent sigmoid transfer function (tansig) with 16 neurons at the hidden layer was applied. Parameters were optimized by central composite design (CCD) combined with response surface methodology (RSM) and desirability function. The accuracy of ANN was judged according to both MSE and AAD% at optimal conditions and results indicate its superiority to RSM model in term of higher R² and lower AAD% values. This observation was also corroborated by the parity plots between the predicted and experimental values. The ANN model was better in both data fitting and prediction capability in comparison to RSM model.     

Broad-Range Optical pH Sensor Based on Binary Mixed-Indicator Doped Sol-Gel Film and Application of Artificial Neural Network

Abstract

In this article, we constructed a pH optical sensor based on m-cresol purple/bromocresol green mixed indicators. The sensor possessed different behaviors at various pH values from ?1.04 to 8.70. The observed behaviors were modeled by means of a PC-feed-forward artificial neural network (ANN) with back-propagation training algorithm. The resulting ANN model was used to predict pH values of new measured spectra from unknown solutions. The results showed very good agreement between true and predicted pH values. The sensor revealed no leaching and excellent reversibility. Other advantages of the sensor include rapid response time, long-term stability, reversibility, high sensitivity, and little hysteresis effect.     

Simultaneous spectrophotometric determination of Fe and Ni with xylenol orange using principal component analysis and artificial neural networks in some industrial samples

Artificial neural networks (ANNs) are among the most popular techniques for nonlinear multivariate calibration in complicated mixtures using spectrophotometric data. In this study, Fe and Ni were simultaneously determined in aqueous medium with xylenol orange (XO) at pH 4.0. In this way, after reducing the number of spectral data using principal component analysis (PCA), an artificial neural network consisting of three layers of nodes was trained by applying a back-propagation learning rule. Sigmoid transfer functions were used in the hidden and output layers to facilitate nonlinear calibration. Adjustable experimental and network parameters were optimized, 30 calibration and 20 prediction samples were prepared over the concentration ranges of 0-400 mug l(-1) Fe and 0-300 mug l(-1) Ni. The resulting R.S.E. of prediction (S.E.P.) of 3.8 and 4.7% for Fe and Ni were obtained, respectively. The method has been applied to the spectrophotometric determination of Fe and Ni in synthetic samples, some Ni alloys, and some industrial waste waters.     

Photocatalytic Degradation of Oxytetracycline in Aqueous Solutions with TiO2 in Suspension and Prediction by Artificial Neural Networks

In this study, the photocatalytic degradation of oxytetracycline (OTC) in aqueous solutions has been studied under different conditions such as initial pollutant concentrations, amount of catalyst, and pH of the solution. Experimental results showed that photocatalysis was clearly the predominant process in the pollutant degradation, since OTC adsorption on the catalyst and photolysis are negligible. The optimal TiO₂ concentration for OTC degradation was found to be 1.0 g/L. The apparent rate constant decreased, and the initial degradation rate increased with increasing initial OTC concentration with the other parameters kept unchanged. Subsequently, data obtained from photocatalytic degradation were used for training the artificial neural networks (ANN). The Levenberg–Marquardt algorithm, log sigmoid function in the hidden layer, and the linear activation function in the output layer were used. The optimized ANN structure was four neurons at the input layer, eighteen neurons at the hidden layer, and one neuron at the output layer. The application of 18 hidden neurons allowed to obtain the best values for R² and the mean squared error, 0.99751 and 7.504e–04, respectively, showing the relevance of the training, and hence the network can be used for final prediction of photocatalytic degradation of OTC with suspended TiO₂.     

Classical and modern algorithms for the evaluation of data from sensor-arrays

Sensors have found wide application in process control, environmental analysis, and other analytical problems in recent years. Optical sensor arrays can be used to monitor organic solvent vapour mixtures by use of reflectometric interference spectroscopy. Lack in selectivity of the sensitive polymer films requires multivariate algorithms for evaluation. Two major aspects are of interest: the random error of calibration and the interpretation of the influence of a single sensor in an array with redundant information. Due to the partial selectivity of the different sensitive layers, non-linearities, cross-sensitivities, and differences in sensitivity, the selection of the most suitable sensitive polymer layers is not trivial. Model based algorithms allow the interpretation of variables whereas the model free algorithms provide better results concerning the random error of calibration. We choose the pruning algorithm to optimize a neural network topology in order to obtain the qualitative information on the sensor elements from the remaining links between the input layer and the hidden layer. We compare these results to the ones obtained for linear and non-linear PLS1 by partial least squares (PLS1) and calculate the errors for the calibration. Received: 3 December 1996 / Revised: 27 February 1997 / Accepted: 4 March 1997     

Classical and modern algorithms for the evaluation of data from sensor-arrays

Sensors have found wide application in process control, environmental analysis, and other analytical problems in recent years. Optical sensor arrays can be used to monitor organic solvent vapour mixtures by use of reflectometric interference spectroscopy. Lack in selectivity of the sensitive polymer films requires multivariate algorithms for evaluation. Two major aspects are of interest: the random error of calibration and the interpretation of the influence of a single sensor in an array with redundant information. Due to the partial selectivity of the different sensitive layers, non-linearities, cross-sensitivities, and differences in sensitivity, the selection of the most suitable sensitive polymer layers is not trivial. Model based algorithms allow the interpretation of variables whereas the model free algorithms provide better results concerning the random error of calibration. We choose the pruning algorithm to optimize a neural network topology in order to obtain the qualitative information on the sensor elements from the remaining links between the input layer and the hidden layer. We compare these results to the ones obtained for linear and non-linear PLS1 by partial least squares (PLS1) and calculate the errors for the calibration.     

CCD camera full range pH sensor array

Changes in colors of an array of optical sensors that responds in full pH range were recorded using a CCD camera. The data of the camera were transferred to the computer through a capture card. Simple software was written to read the specific color of each sensor. In order to associate sensor array responses with pH values, a number of different mathematics and chemometrics methods were investigated and compared. The results show that the use of “Microsoft Excel's Solver” provides results which are in very good agreement with those obtained with chemometric methods such as artificial neural network (ANN) and partial least square (PLS) methods.     

人工神经网络预测煤炭成浆浓度的研究

考虑煤炭的多种理化特性建立了成浆浓度的神经网络预测模型,对其数据预处理方法、学习率和中间层节点数等进行了深入讨论。水分、挥发分、分析基碳、灰分和氧等五个因子对于煤炭成浆性的预测起到主导作用。五因子、七因子和八因子神经网络模型对煤炭成浆浓度的预测误差分别为：0.53%、0.50%和0.74%,而现有回归分析方程的误差为1.15%,故神经网络模型比回归分析方程有更好的预测能力,尤以七因子模型最佳。     

EIS multianalyte sensing with an automated SIA system—An electronic tongue employing the impedimetric signal

In this work, the simultaneous quantification of three alkaline ions (potassium, sodium and ammonium) from a single impedance spectrum is presented. For this purpose, a generic ionophore - dibenzo-18-crown-6 - was used as a recognition element, entrapped into a polymeric matrix of polypyrrole generated by electropolymerization. Electrochemical impedance spectroscopy (EIS) and artificial neural networks (ANNs) were employed to obtain and process the data, respectively. In fact, EIS detected the ions exchanged between the medium and the sensing layer whereas ANNs, after an appropriated training process, could turn the impedance spectrum into concentrations values. A sequential injection analysis (SIA) system was employed for operation and to automatically generate the information required for the training of the ANN. Best results were obtained by using a backpropagation neural network made up by two hidden layers: the first one contained three neurons with the radbas transfer function and the second one ten neurons with the tansig transfer function. Three commercial fertilizers were tested employing the proposed methodology on account of the high complexity of their matrix. The experimental results were compared with reference methods.     

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.     

Identification of combustible material with piezoelectric crystal sensor array using pattern-recognition techniques

A promising way of increasing the selectivity and sensitivity of gas sensors is to treat the signals from a number of different gas sensors with pattern recognition (PR) method. A gas sensor array with seven piezoelectric crystals each coated with a different partially selective coating material was constructed to identify four kinds of combustible materials which generate smoke containing different components. The signals from the sensors were analyzed with both conventional multivariate analysis, stepwise discriminant analysis (SDA), and artificial neural networks (ANN) models. The results show that the predictions were even better with ANN models. In our experiment, we have reported a new method for training data selection, 'training set stepwise expending method' to solve the problem that the network can not converge at the beginning of the training. We also discussed how the parameters of neural networks, learning rate eta, momentum term alpha and few bad training data affect the performance of neural networks.     

Application of artificial neural networks for formulation and modeling of dye adsorption onto multiwalled carbon nanotubes

In this study, an artificial neural network (ANN) has been developed to predict the adsorption amount of dye (methylene blue) onto multiwalled carbon nanotubes. Batch experiments have been carried out to obtain experimental data. Important parameters in the adsorption system such as initial dye concentration, adsorbent dosage, temperature, pH and contact time have been used as the inputs of the network, while the output is the final concentration of dye in aqueous solution after adsorption. The neural network structure has been optimized by testing various training algorithms and different number of neurons in a hidden layer. An empirical equation for determination of final dye concentration in aqueous solutions after adsorption has been developed by using the weights of the optimized network. The results of the optimized ANN have been compared with conventional models in equilibrium and kinetic fields. According to error analysis and determination coefficient, the ANN was found to be the most appropriate model to describe this adsorption process. Sensitivity analysis showed that initial dye concentration, pH and contact time are the most effective parameters in this process. The influence percentages of these parameters on the output were 28, 24 and 24 %, respectively.     

Direct and inverse neural network modeling in free radical polymerization

The first part of this paper reviews of the most important aspects regarding the use of neural networks in the polymerization reaction engineering. Then, direct and inverse neural network modeling of the batch, bulk free radical polymerization of methyl methacrylate is performed. To obtain monomer conversion, number and weight average molecular weights, and mass reaction viscosity, separate neural networks and, a network with multiple outputs were built (direct neural network modeling). The inverse neural network modeling gives the reaction conditions (temperature and initial initiator concentration) that assure certain values of conversion and polymerization degree at the end of the reaction. Each network is a multi-layer perceptron with one or two hidden layers and a different number of hidden neurons. The best topology correlates with the smallest error at the end of the training phase. The possibility of obtaining accurate results is demonstrated with a relatively simple architecture of the networks. Two types of neural network modeling, direct and inverse, represent possible alternatives to classical procedures of modeling and optimization, each producing accurate results and having simple methodologies.