Qualitative Recognition of Primary Taste Sensation Based on Surface Electromyography

Abstract

Based on surface electromyography (sEMG), a novel recognition method to distinguish six types of human primary taste sensations was developed, and the recognition accuracy was 74.46%. The sEMG signals were acquired under the stimuli of no taste substance, distilled vinegar, white granulated sugar, instant coffee powder, refined salt, and Ajinomoto. Then, signals were preprocessed with the following steps: sample augments, removal of trend items, high-pass filter, and adaptive power frequency notch. Signals were classified with random forest and the classifier gave a five-fold cross-validation accuracy of 74.46%, which manifested the feasibility of the recognition task. To further improve the model performance, we explored the impact of feature dimension, electrode distribution, and subject diversity. Accordingly, we provided an optimized feature combination that reduced the number of feature types from 21 to 4, a preferable selection of electrode positions that reduced the number of channels from 6 to 4, and an analysis of the relation between subject diversity and model performance. This study provides guidance for further research on taste sensation recognition with sEMG.

TastePeptides-EEG: An Ensemble Model for Umami Taste Evaluation Based on Electroencephalogram and Machine Learning

“…This model achieved an accuracy rate of 49.95% and an AUC31 of 0.71 for the five basic tastes . In addition to EEG data, You Wang used differential electrodes to detect facial and chewing muscles to obtain surface electromyography (sEMG) and further achieved an accuracy rate of 74.46% by random forest algorithm . Romeo-Arroyo employed a decision tree to process data from multiple sub-brain regions to achieve a 79% discriminating accuracy for distinct stimuli (“sweet” vs “nonsweet” odors; “sweet-taste”, “sweet-flavor”, and “nonsweet flavor”; and “sweet stimuli” vs “nonsweet stimuli”) …”

“…You Wang proposed a novel recognition method to distinguish six types of human primary taste sensations based on surface electromyography (sEMG) and achieved a recognition accuracy of 74.46%. 18 Placidi utilized EEG to capture disgust caused by recalling unpleasant scents and developed a BLC model with a 90% accuracy rate. 19 In this study, 125 brain wave signals from 5 brain regions were used as input data to characterize brain activity, and an umami perception model TastePeptides-EEG was established through an integrated model.…”

“…Benefiting from advances in computer performance and iterations of algorithms, researchers now have more tools for pattern recognition and data analysis. You Wang proposed a novel recognition method to distinguish six types of human primary taste sensations based on surface electromyography (sEMG) and achieved a recognition accuracy of 74.46% . Placidi utilized EEG to capture disgust caused by recalling unpleasant scents and developed a BLC model with a 90% accuracy rate .…”