2026-10-14T07:36:16Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34024680 2026-09-29T14:50:43Z category_146 category_873 category_734 category_811 category_106 portal_63 item_type_6 month_year_09_2026

Beyond Optimal Conditions in Optical Sensor Arrays: Big Analytical Data Meets Multiway Deep Learning Nazanin Esmaeili (25137576) Zahra Shojaeifard (2824097) Bahram Hemmateenejad (1288830) Space Science Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Science Policy underlying analytical information single sensing element single optimized condition sample species rather parallel factor analysis optical sensor arrays numerous interacting variables linear discriminant analysis investigate chemical relationships intrinsic chemical complexity hardness – softness different valence states defined sample sets deep learning strategies convolutional neural network complex chemical samples chemical features influencing 23 sensor elements 21 %, respectively optimized conditions may beyond optimal conditions big data mode feature selection using 42 metal ions experimental design approaches comprehensive data set dimensional matrix ), way tensor mode three structural modes three ph levels achieve unprecedented accuracy metal ions dimensional data dimensional ), conditions satisfied prediction set concatenated data investigated using validated accuracies tucker decomposition study highlights selectively recognized resulting high redox flexibility often overlooked multivariate behavior fully extract cnn ). Complex systems comprising variate samples are influenced by numerous interacting variables that are often overlooked under conventionally optimized experimental conditions, where parameters are typically tuned using one factor at a time or experimental design approaches. Although such optimized conditions may be adequate for small or well-defined sample sets, larger and chemically diverse data sets require comprehensive exploration of the full multidimensional data space to fully extract the underlying analytical information. In this work, we considered the chemical features influencing the system by constructing a comprehensive data set that captures the intrinsic chemical complexity of the sample species rather than relying on a single optimized condition. To this end, the discrimination of 42 metal ions with different valence states was investigated using a paper-based colorimetric sensor array composed of 23 sensor elements, evaluated under six conditions comprising two paper substrates and three pH levels (3.0, 7.0, and 11). The optimization process did not achieve a cross-validated accuracy exceeding 57.94%. The resulting high-dimensional data were analyzed in three structural modes to compare two-way, three-way, and deep learning strategies: (i) the two-way tensor mode (two-dimensional matrix), in which the concatenated data of all conditions satisfied during optimization were evaluated using principal component analysis (PCA) and PCA coupled with linear discriminant analysis (PCA–LDA); (ii) the three-way tensor mode (three-dimensional), where parallel factor analysis (PARAFAC) and Tucker decomposition were applied; and (iii) the big data mode, which was analyzed using a convolutional neural network (CNN). Among these approaches, the two-way and three-way chemometric models achieved cross-validated accuracies of 72.22% and 49.21%, respectively, while the CNN model provided complete discrimination of all 42 metal ions, reaching an accuracy of 99.7% on a prediction set. Furthermore, to investigate chemical relationships and multivariate behavior, metal ions were grouped into seven chemically meaningful categories reflecting their hardness–softness, redox flexibility, bioactivity, and toxicity. Feature selection using the Davies–Bouldin index (DBI) identified 14 metal ions that could be selectively recognized by a single sensing element, demonstrating strong discriminative potential. Overall, this study highlights how moving beyond “optimal conditions” and embracing full multidimensional data sets enables deep models such as CNNs to achieve unprecedented accuracy in complex chemical samples. 2026-09-29T00:00:00Z Text Journal contribution 10.1021/acs.analchem.6c02653.s001 https://figshare.com/articles/journal_contribution/Beyond_Optimal_Conditions_in_Optical_Sensor_Arrays_Big_Analytical_Data_Meets_Multiway_Deep_Learning/34024680 CC BY-NC 4.0