The accurate estimation of physicochemical properties of ternary mixtures containing ionic liquids via artificial neural networks.

The estimation of the density and refractive index of ternary mixtures comprising the ionic liquid (IL) 1-butyl-3-methylimidazolium tetrafluoroborate, 2-propanol, and water at a fixed temperature of 298.15 K has been attempted through artificial neural networks. The obtained results indicate that the selection of this mathematical approach was a well-suited option. The mean prediction errors obtained, after simulating with a dataset never involved in the training process of the model, were 0.050% and 0.227% for refractive index and density estimation, respectively. These accurate results, which have been attained only using the composition of the dissolutions (mass fractions), imply that, most likely, ternary mixtures similar to the one analyzed, can be easily evaluated utilizing this algorithmic tool. In addition, different chemical processes involving ILs can be monitored precisely, and furthermore, the purity of the compounds in the studied mixtures can be indirectly assessed thanks to the high accuracy of the model.

Linking chemical parameters to sensory panel results through neural networks to distinguish olive oil quality.

A wide variety of olive oil samples from different origins and olive types has been chemically analyzed as well as evaluated by trained sensory panelists. Six chemical parameters have been obtained for each sample (free fatty acids, peroxide value, two UV absorption parameters (K232 and K268), 1,2-diacylglycerol content, and pyropheophytins) and linked to their quality using an artificial neural network-based model. Herein, the nonlinear algorithms were used to distinguish olive oil quality. Two different methods were defined to assess the statistical performance of the model (a K-fold cross-validation (K = 6) and three different blind tests), and both of them showed around a 95-96% correct classification rate. These results support that a relationship between the chemical and the sensory analyses exists and that the mathematical tool can potentially be implemented into a device that could be employed for various useful applications.

An automated sample preparation for detection of 72 doping-related substances.

Automation of sample preparation procedures in a doping control laboratory is of great interest due to the large number of samples that have to be analyzed, especially in large events where a high throughput protocol is required to process samples over 24 h. The automation of such protocols requires specific equipment capable of carrying out the diverse mechanical tasks required for accomplishing these analytical methodologies, which include pipetting, shaking, heating, or crimping. An automated sample preparation procedure for the determination of doping-related substances by gas chromatography-mass spectrometry (GC-MS) and gas chromatography-tandem mass spectrometry (GC-MS/MS) analysis, including enzymatic hydrolysis, liquid-phase extraction and derivatization steps, was developed by using an automated liquid handling system. This paper presents a description of the equipment, together with the validation data for 72 doping-related compounds including extraction efficiency, evaluation of carry-over, interferences, and robustness. Validation was approached as a comparison between the results obtained using the manual protocol and the transferred automated one. The described methodology can be applied for sample preparation in routine anti-doping analysis with high sample throughput and suitable performance.

Estimation of the refractive indices of imidazolium-based ionic liquids using their polarisability values.

Statistical models have been used to estimate the refractive index of 72 imidazolium-based ionic liquids using the electronic polarisability of their ions as the data for two different mathematical approaches: artificial neural networks, in the form of multi-layer perceptrons, and multiple linear regression models. Although the artificial neural networks and linear models have been able to accomplish this task, the multi-layer perceptron model has been shown to be a more accurate method, thanks to its ability of determining non-linear relationships between different dependent variables. Additionally, it is clear that the multiple linear regression presents a systematic deviation in the estimated refractive index values, which confirms that it is an inappropriate model for this system.

Neural networks to estimate the water content of imidazolium-based ionic liquids using their refractive indices.

A non-linear model has been developed to estimate the water content of 1-butyl-3-methylimidazolium tetrafluoroborate, 1-butyl-3-methylimidazolium methylsulfate, and 1,3-dimethylimidazolium methylsulfate ionic liquids using their respective refractive index values. The experimental values measured to design the neural network (NN) model were registered at 298.15K. These were determined at different relative humidity values which ranged from 11.1% to 84.3%. The estimated results were compared with experimental measurements of water content obtained by the Karl Fischer technique, and the differences between the real and estimated values were less than 0.06% in the internal validation process. In addition, an external validation test was developed using bibliographical references. In this case, the mean prediction error was less than 5.4%. In light of these results, the NN model shows an acceptable goodness of fit, sufficient robustness, and a more than adequate predictive capacity to estimate the water content of the ILs through the analysis of their refractive index.

Estimation with neural networks of the water content in imidazolium-based ionic liquids using their experimental density and viscosity values.

A multilayer perceptron neural network (NN) model has been created for the estimation of the water content present in the following ionic liquids (ILs): 1-butyl-3-methylimidazolium tetrafluoroborate, 1-butyl-3-methylimidazolium methylsulfate, 1,3-dimethylimidazolium methylsulfate and 1-ethyl-3-methylimidazolium ethylsulfate. To achieve this goal, their density and viscosity values were used. The experimental values of these physicochemical properties, employed to design the NN model, were measured and registered at 298.15K. They were determined at different relative humidity values ranging from 11.1 to 84.3%. The estimated results were then compared with the experimental measurements of the water content, which were carried out by the Karl Fischer technique, and the difference between the real and estimated values was less than 0.05 and 3.1% in the verification and validation processes, respectively. In addition, an external validation process was developed using four bibliographical references. In this case, the mean prediction error was less than 6.3%. In light of these results, the NN model shows an acceptable goodness of fit, sufficient robustness, and an adequate estimative capacity to determine the water content inside the studied range of the ILs analyzed.