Application of principal component-wavelet neural network in spectrophotometric determination of acidity constants of 4-(2-thiazolylazo)-resorcinol

Performance comparison of wavelet neural network and adaptive neuro-fuzzy inference system with small data sets

In this work, performance of wavelet neural network (WNN) and adaptive neuro-fuzzy inference system (ANFIS) models were compared with small data sets by different criteria such as second order corrected Akaike information criterion (AICc), Bayesian information criterion (BIC), root mean squared error (RMSE), mean absolute relative error (MARE), coefficient of determination (R²), external Q² function ( [Formula: see text] ) and concordance correlation coefficient (CCC). Another criterion was the over-fitting. Ten data sets were selected from literature and their data were divided into training, test, and validation sets. Network parameters were optimized for WNN and ANFIS models and the best architectures with the lowest errors were selected for each data set. A precise survey of the number of permitted adjustable parameters (NPAP) and the total number of adjustable parameters (TNAP) in WNN and ANFIS models was shown that 60% of the ANFIS models and 30% of the WNN models had over-fitting. As a rule of thumb, to avoid over-fitting it is suggested that the ratio of the number of observations in training set to the number of input neurons must be greater than 10 and 20 for WNN and ANFIS, respectively. The smaller ratio required in WNN indicates its flexibility vs. ANFIS that relates to differences in structure and connections in the both networks.

Development and validation of the simple and sensitive spectrophotometric method of sulphanilamides determination with 4-(2-thiazolylazo)-resorcinol in veterinary preparations

New simple, rapid, and accurate spectrophotometric techniques for sulphanilamides assay in combination drugs have been elaborated. The method is based on the formation of coloured products of sulphanilamides diazonium salt azoсoupling with heterocyclic azo reagent 4-(2-thiazolylazo)-resorcinol (TAR) in alkaline medium (pH 9.5) with the following measurement of their absorbance at λmax = 615 nm. Formed products are stable for 1 hour at room temperature. Effective molar absorptivities at absorbance maximum 615 nm for disazo dyes were ~ 104 M-1 cm-1. Linear ranges for sulphanilamides determination were 0.5−30.0 μg mL-1. The developed method was used for the suphanilamides determination in tablets, powder, solutions, suspensions and ointments.

Spectrophotometric determination of acidity constants of 2-(2-Thiazolylazo)-Cresol in various water-organic solvent media mixtures using chemometrics methods

The combination of soft- and hard-modeling was used to the spectrophotometric studies of the acidity constants of 2-(2-Thiazolylazo)-Cresol (TAC) at 25°C and at ionic strength 0.1 mol L(-1) in pure water as well as in aqueous media containing variable percentages (10-50%) of organic solvents. The organic solvents used were methanol, ethanol, dimethyl formamide (DMF) and 1,4-dioxane. The acidity constants of all related equilibria are estimated using the whole spectral fitting of the collected data to an established factor analysis model. DATAN program was applied for determining acidity constants and pure spectra of different form of TAC. Results show that the acidity constants of TAC are influenced as the percentages of solvents added to the solution. The corresponding pKa values in solvent-water mixtures were determined. There are linear relationships between acidity constants and the mole fraction of organic solvents in the solvent mixtures. The effects of various solvents on absorption properties and acidity constants of each component are also discussed.