Prediction of molar absorptivities of color reagents and their color reactions with yttrium by artificial neural networks

The new topological indices A(x1)-A(x3) suggested in our laboratories were applied to the study of structure-property relationships between color reagents and their color reactions with yttrium. The topological indices of twenty asymmetrical phosphone bisazo derivatives of chromotropic acid were calculated. The work shows that QSPR can be used as a novel aid to predict the molar absorptivities of color reactions and in the long term to be helpful tool in-color reagent design. Multiple regression analysis and neural network were employed simultaneously in this study. The results demonstrated the feasibility and the effectiveness of the method.

Classification of valence changes of trivalent rare earth ions in alkaline earth borates using artificial neural networks

The investigations of classification on the valence changes from RE3+ to RE2+ (RE = Eu, Sm, Yb, Tm) in host compounds of alkaline earth berate were performed using artificial neural networks (ANNs). For comparison, the common methods of pattern recognition, such as SIMCA, KNN, Fisher discriminant analysis and stepwise discriminant analysis were adopted. A learning set consisting of 24 host compounds and a test set consisting of 12 host compounds were characterized by eight crystal structure parameters. These parameters were reduced from 8 to 4 by leaps and bounds algorithm. The recognition rates from 87.5 to 95.8% and prediction capabilities from 75.0 to 91.7% were obtained. The results provided by ANN method were better than that achieved by the other four methods. (C) 1999 Elsevier Science B.V. All rights reserved.

Artificial neural network applied to diagnosis of lung cancer

Artificial neural network(ANN) approach was applied to classification of normal persons and lung cancer patients based on the metal content of hair and serum samples obtained by inductively coupled plasma atomic emission spectrometry (ICP-AES) for the two groups. This method was verified with independent prediction samples and can be used as an aiding means of the diagnosis of lung cancer. The case of predictive classification with one element missing in the prediction samples was studied in details, The significance of elements in hair and serum samples for classification prediction was also investigated.

Development and application of a sol-gel immunosorbent-based method for the determination of isoproturon in surface water

An immunosorbent was fabricated by encapsulation Of monoclonal anti-isoproturon antibodies in sol-gel matrix. The immunosorbent-based loading, rinsing and eluting processes were optimized. Based on these optimizations, the sol-gel immunosorbent (SG-IS) selectively extracted isoproturon from an artificial mixture of 68 pesticides. In addition to this high selectivity, the SG-IS proved to be reusable. The SG-IS was combined with liquid chromatography-tandem mass spectrometry (LC-MS-MS) to determine isoproturon in surface water, and the linear range was up to 2.2 mu g/l with correlation coefficient higher than 0.99 and relative standard deviation (RSD) lower than 5% (n = 8). The limit of quantitation (LOQ) for 25-ml surface water sample was 5 ng/l. (c) 2006 Elsevier B.V. All rights reserved.