A Gustatory-Emotion Coupling Model of Nerve Conduction Mechanisms for Taste Identification

Taste identification research is a pivotal issue in agriculture and guides agricultural production to guarantee food quality. The bio-inspired electronic tongue (e-tongue) has emerged as a powerful tool for taste classification, demonstrating superiority over human sensory evaluation and physiochemical analysis technologies. However, current taste analysis with e-tongue system focuses on data processing while neglecting the nerve conduction mechanisms (NCMs) underlying human taste perception, which constrains the performance in taste classification. Motivated by this, a gustatory-emotion coupling model (GECM) based on NCMs for human taste and emotion systems (HTESs) is proposed to improve the performance of taste identification. First, the topological structure of nerve transmission pathways for taste and emotion information is built, and the dynamic characteristics of the HTESs are characterized via the GECM. Second, the response characteristics of the brain (including 1/<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</i> and chaotic characteristics) are reproduced in the GECM output under stimulation, and the bionic characteristics of the GECM are validated. Finally, a convolutional neural network (CNN) is designed to process the GECM output for taste identification. Compared with multiple classifiers, the best identification performance, which includes the accuracies of 98.88% and 98.45%, the recall scores of 98.91% and 98.23%, the precision scores of 99.17% and 98.90%, the kappa coefficients of 98.61% and 98.07%, and the F<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub>-scores of 99.04% and 98.57%, is acquired using the GECM-CNN. In conclusion, the performance of taste recognition for e-tongue system is improved via the GECM. It provides a foundation for guiding agricultural production and evaluating food quality from NCMs.