Optimization of Sensors to be Used in a Voltammetric Electronic Tongue Based on Clustering Metrics

Abstract

Herein we investigate the usage of principal component analysis (PCA) and canonical variate analysis (CVA), in combination with the F factor clustering metric, for the a priori tailored selection of the optimal sensor array for a given electronic tongue (ET) application. The former allows us to visually compare the performance of the different sensors, while the latter allows us to numerically assess the impact that the inclusion/removal of the different sensors has on the discrimination ability of the ET. The proposed methodology is based on the measurement of a pure stock solution of each of the compounds under study, and the posterior analysis by PCA/CVA with stepwise iterative removal of the sensors that demote the clustering when retained as part of the array. To illustrate and assess the potential of such an approach, the quantification of paracetamol, ascorbic acid, and uric acid mixtures were chosen as the study case. Initially, an array of eight different electrodes was considered, from which an optimal array of four sensors was derived to build the quantitative ANN model. Finally, the performance of the optimized ET was benchmarked against the results previously reported for the analysis of the same mixtures, showing improved performance.

Experiences in the detection of drugs of abuse in smuggling seizures and forensic samples using electronic tongue principles

“…To illustrate the potential of the proposed approach, four different scenarios of increasing complexity were considered; namely, identification of different opioids without and with mixing them with different cutting agents, and the quantification of opioids mixtures, without or with the presence of different cutting agents. For each of them, a different set of samples was prepared and measured with the proposed sensor arrays (after optimization of the sensors chosen [10]), submitting afterwards the obtained responses to the appropriate chemometric model depending whether a qualitative or quantitative response was sought. For all the supervised models, the sets of samples were split into two subsets: train subset (used to fit the model) and test subset (used to assess its performance).…”

“…The first step was the analytical characterization of the voltammetric responses of the different electrodes towards the different dugs considered, to ensure that there is some response, and that differentiated responses are also obtained between the different electrodes. Next, voltammograms were submitted to PCA, and the clustering observed was used to select the optimal sensor array for each scenario [10].…”

Sensor Selection for an Electronic Tongue for the Rapid Detection of Paralytic Shellfish Toxins: A Case Study

“…To address this question, several attempts to formalize sensor selection for the electronic tongue have been proposed recently. Several works propose the use of Principal Component Analysis (PCA) for the simultaneous assessment of sensitivity and the reproducibility of sensors, permitting the selection of the most suitable ones for particular analytical tasks [10][11][12]. Measurements with several sensors are carried out in the individual solutions of analytes with varying or equal concentrations, and the PCA model is calculated using sensor responses.…”

“…Measurements with several sensors are carried out in the individual solutions of analytes with varying or equal concentrations, and the PCA model is calculated using sensor responses. In 2020, Sarma et al [10] proposed a visual examination of the PCA scores and loading plots for selecting sensors discriminating between samples. In other studies [11][12][13], PCA was employed in combination with different clustering indices calculated using PCA scores, such as F factor, Dunn, Davies-Bouldin, Silhouette, and Calinski-Harabasz.…”

Feature importance methods unveiling the cross-sensitive response of an integrated sensor array to quantify major cations in drinking water

“…In particular, potentiometric Electronic Tongues (ETs) comprising an array of low-selective chemical sensors [5] have proven to be useful for remote sensing applications and monitoring changes in liquid composition over time [6]. A popular approach to optimize the design of ETs has been to evaluate the sensitivity of individual sensors in samples containing only one target analyte [7] or training machine learning models on all possible combinations of available sensors [8]. This contribution proposes an alternative, generalized data-driven method for designing such systems, as follows:…”