Data Compression for a Voltammetric Electronic Tongue Modelled with Artificial Neural Networks

Moreno‐Barón, Laura; Cartas, R.; Merkoçi, Arben; Alegret, Salvador; Gutiérrez, Juan Manuel; Leija, L.; Hernández, P.R.; Muñoz, Robert; Valle, Manel del

doi:10.1080/00032710500259342

Cited by 50 publications

(26 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the high dimensionality conditions, data was compressed by using DWT or FFT transforms, and subsequently unfolded in a single vector to form the input to the ANN model. The training algorithm (Bayesian regularization) and the DWT (Daubechies) and FFT parameters (decomposition levels and number of coefficients) are stated on Figure ; these were chosen based on previous experience with similar conditions . As can be seen in Figure S4 (supporting info) the loss of information in the compression step is limited, and the general shape of the original signal is preserved.…”

Section: Methodsmentioning

confidence: 99%

Analysis of Amino Acid Mixtures by Voltammetric Electronic Tongues and Artificial Neural Networks

2016

View full text Add to dashboard Cite

1IntroductionThea nalysis of amino acids (AAs) is usually performed using techniques such as gas [1,2] and liquid [3,4] chromatography or capillary electrophoresis [5][6][7].T hough, the great demand of AA determinations in many important fields,s uch as clinicala nalysiso rf ood and pharmaceuticali ndustry [ 8,9],l eads to then eed of simpler and faster procedures,s uch as sensor-based methods.T hese electroanalyticala pproaches are reported as good methods for the analysis of specific AAs thankst ot he electroactivityp resented by aromaticand thiolg roups [8].Materials traditionally usedi nt he constructiono fs ensors for this kind of applications are carbon,p latinum and gold. But these materials are usually modified in order to increase the sensitivity and introducen ew features due to electrocatalytic activity, which leads to an increase in the range of detectable AAs [10].Theu se of metal oxide-modified sensors (MOS) has increasedd uring the last years duet oi ts great potential in the analysis of manye lectroactive substances [11,12] or even the detection of the presence of some bacteria in complex systems [13].M oreover, the recent availability of these materials in the form of nanopowder has facilitated enormously the possibility of using them as electrode modifiers.P otential of usingM OS materials has widened its scope especially by the use of semiconducting MOS arrays as gas sensors forming electronic noses (ENs). ENs have gained recognition in many fields like food, aromao rm edical diagnosis [ 14].T he large amount of data provided by ENs increases the sensitivity and selectivity of the method just by multivariate data processing, which avoids tedious derivatizationo ro ptimisation of the sensors for eacha nalyte [15,16].H owever,t he use of MOS is only ap ossible option to develop electronic noses and/or electronic tongues (ETs) [17].ETs have been used for more than ad ecade,a nd its use has grown considerably as they present al arge scope of applications,i ncluding environmental analysis, food industry and agriculture [18][19][20].D ue to the good performance of voltammetric techniques to analyze certain AAs, voltammetric ETs have already been presenteda s ag ood approach for their analysis,i nt his case for the ones with oxidizable properties,s uch as cysteine( CYS), tyrosine (TYR) and tryptophan (TRP) [21][22][23].An important weakness of voltammetric ETs residesi n the complexity of the response obtained, as there is an eed to process each voltammogram from eachs ensor. However, huge amounts of data derived from voltammetric analysis have usually been modelleds uccessfully by usingp rior compression which interprets and extracts meaningful data, offsets any matrix effecta nd may allow the resolution of interfering agents and drifts.T he most widely used multivariate data analysis techniques for voltammetric ETs are principal componenta nalysis,p artial least squares regression (PLS) and artificial neural networks (ANNs) [24][25][26].PLS represents the data in new coordinate axes, but in this ca...

show abstract

Section: Methodsmentioning

confidence: 99%

Analysis of Amino Acid Mixtures by Voltammetric Electronic Tongues and Artificial Neural Networks

2016

View full text Add to dashboard Cite

show abstract

“…Based on previous experience [40], the compression details were optimized. Finally it was used as compression approach the discrete wavelet transform (DWT) employing the mother function Daubechies 3 and a second decomposition level . The DWT pretreatment allowed compressing the initial data set information (206 currents per sample) into 55 coefficients with a space saving of 73.3 % (calculation details: 1‐55/206).…”

Section: Resultsmentioning

confidence: 99%

Artificial Neural Networks for the Resolution of Dopamine and Serotonin Complex Mixtures Using a Graphene‐Modified Carbon Electrode

2019

View full text Add to dashboard Cite

This work explores an electrode modified with electrochemically reduced graphene oxide (ERGO) for the voltammetric resolution of mixtures of neurotransmitters and its most common interferents. This enhanced sensitivity device coupled with advanced chemometric tools, such as artificial neural networks (ANNs), is able to resolve and quantify complex mixtures with overlapped signals. In this case, it has been applied to dopamine (DA), serotonin (5‐hydroxytryptamine, 5‐HT) and its main physiologic interferents, ascorbic acid (AA) and uric acid (UA), which play a relevant role in human body. The results obtained for individual analysis make evident a higher sensitivity of the developed sensor than the unmodified electrode. Furthermore, it has been attained an ANN response model with good correlation ability allowing the separation and quantification of each compound with comparison slope of predicted vs. expected concentrations with correlation better than 0.974. In short, the developed ERGO‐modified sensor not only improved the signal but it also permitted resolving and quantifying each compound in complex mixtures when the proper chemometric treatment was used.

show abstract

“…This aspect of voltammetric electronic tongues has also received attention from our laboratory. In a first work, PCA and Wavelet transform were used and compared as a compression tool stage, in order to extract significant information from the voltammograms and use the reduced information for the modeling [69]. The case studied was the resolution of mixtures of the three oxidizable amino acids tryptophan, cysteine, and tyrosine, and the best response model was obtained with Wavelet transform followed by ANN modeling.…”

Section: Data Compression In Voltammetric Electronic Tonguesmentioning

confidence: 99%

Electronic Tongues Employing Electrochemical Sensors

2010

View full text Add to dashboard Cite

This review presents recent advances concerning work with electronic tongues employing electroanalytical sensors. This new concept in the electroanalysis sensor field entails the use of chemical sensor arrays coupled with chemometric processing tools, as a mean to improve sensors performance. The revision is organized according to the electroanalytical technique used for transduction, namely: potentiometry, voltammetry/amperometry or electrochemical impedance. The significant use of biosensors, mainly enzyme-based is also presented. Salient applications in real problem solving using electrochemical electronic tongues are commented.

show abstract

Data Compression for a Voltammetric Electronic Tongue Modelled with Artificial Neural Networks

Cited by 50 publications

References 32 publications

Analysis of Amino Acid Mixtures by Voltammetric Electronic Tongues and Artificial Neural Networks

Analysis of Amino Acid Mixtures by Voltammetric Electronic Tongues and Artificial Neural Networks

Artificial Neural Networks for the Resolution of Dopamine and Serotonin Complex Mixtures Using a Graphene‐Modified Carbon Electrode

Electronic Tongues Employing Electrochemical Sensors

Contact Info

Product

Resources

About