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

Article Chemistry, Applied

A TastePeptides-Meta system including an umami/bitter classification model Umami_YYDS, a TastePeptidesDB database and an open-source package Auto_Taste_ML

Zhiyong Cui et al.

Summary: This study established a taste peptide database and a prediction model to provide a convenient method for rapid screening of umami peptides, which was validated by sensory experiments.

FOOD CHEMISTRY (2023)

Add to Collection

Article Agriculture, Multidisciplinary

Conserved Sites and Recognition Mechanisms of T1R1 and T2R14 Receptors Revealed by Ensemble Docking and Molecular Descriptors and Fingerprints Combined with Machine Learning

Zhiyong Cui et al.

Summary: In this study, 489 taste peptides with umami/bitter taste were analyzed and used to train a classification model based on docking analysis, molecular descriptors, and molecular fingerprints. The model, called taste peptide docking machine (TPDM), showed that certain molecular descriptors and fingerprints had the greatest impact on the umami/bitter prediction of peptides. Key recognition modes of umami/bitter receptors were also identified based on the docking results.

JOURNAL OF AGRICULTURAL AND FOOD CHEMISTRY (2023)

Add to Collection

Article Biophysics

Bimetallic bionic taste sensor for perception of the synergistic effect of umami substances

Yanyang Yu et al.

Summary: A bimetallic bionic taste sensor was developed to evaluate the synergistic effect of umami substances, showing good linearity and wide detection range. It could recognize the synergistic effect of umami substances in real samples and the effect was more obvious at lower concentrations and balanced ratios. This study provides a promising platform for further research on the mechanism of synergistic effect and multifunctional industrial applications.

BIOSENSORS & BIOELECTRONICS (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Basic Taste Sensation Recognition From EEG Based on Multiscale Convolutional Neural Network With Residual Learning

Han Gao et al.

Summary: This article proposes EEG-MSRNet, a novel fully convolutional neural network for EEG-based classification of basic taste sensations. The network utilizes multiscale temporal and spatial convolution operations, as well as convolutional and global average pooling layers, to achieve stable and generalizable recognition performance. Experimental results demonstrate the effectiveness of EEG-MSRNet for taste sensation recognition, with potential applications in taste disorder diagnosis and virtual taste.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2023)

Add to Collection

Article Engineering, Biomedical

In-silico investigation of umami peptides with receptor T1R1/T1R3 for the discovering potential targets: A combined modeling approach

Wenli Wang et al.

Summary: This study analyzed the sequence and properties of umami peptides, and investigated their active sites and binding residues with the receptor T1R1/T1R3. The results identified the key active sites as well as the crucial residues in the receptor that bind umami peptides. A decision rule was proposed to predict potential umami peptides, providing convenience and efficiency.

BIOMATERIALS (2022)

Add to Collection

Review Food Science & Technology

Mechanisms of umami taste perception: From molecular level to brain imaging

Ben Wu et al.

Summary: Umami substances have gained attention in the food industry as potential replacers for sodium or fat to enhance food palatability. Understanding the mechanisms of umami taste perception, from receptor level to brain imaging, is crucial. Research into umami taste perception should not only focus on oral perception, but also on the broader signaling mechanisms throughout the body and interactions between the brain and gut.

CRITICAL REVIEWS IN FOOD SCIENCE AND NUTRITION (2022)

Add to Collection

Review Computer Science, Artificial Intelligence

Human emotion recognition from EEG-based brain-computer interface using machine learning: a comprehensive review

Essam H. Houssein et al.

Summary: Affective computing, a subcategory of artificial intelligence, focuses on detecting, processing, interpreting, and mimicking human emotions. This study reviews various methods of emotion recognition utilizing multi-channel EEG signal-based brain-computer interfaces (BCIs) and provides an overview of the accomplishments in this field. The study also discusses the datasets and methods used to elicit emotional states, along with the EEG feature extraction, machine learning, and deep learning methods employed in emotion recognition. Additionally, the study examines the relationship between EEG rhythms and emotions, as well as comparing different machine and deep learning algorithms for human emotion recognition using EEG data.

NEURAL COMPUTING & APPLICATIONS (2022)

Add to Collection

Article Food Science & Technology

Human Taste-Perception: Brain Computer Interface (BCI) and Its Application as an Engineering Tool for Taste-Driven Sensory Studies

R. Anbarasan et al.

Summary: Sensory satisfaction is crucial for the acceptance of food products, with taste playing a major role. Traditional methods like market surveys and sensory panels cannot fully represent consumers' taste perception. Non-invasive devices and BCI techniques are being explored to sense and decode taste signals, showing potential as future sensory methods.

FOOD ENGINEERING REVIEWS (2022)

Add to Collection

Article Agriculture, Multidisciplinary

Investigating the Influence of Different Umami Tastants on Brain Perception via Scalp Electroencephalogram

Ben Wu et al.

Summary: This study revealed that the brain can partially distinguish between different sensory intensities of umami tastants. Moreover, umami tastants were found to significantly enhance alpha wave activity in specific regions of the brain.

JOURNAL OF AGRICULTURAL AND FOOD CHEMISTRY (2022)

Add to Collection

Article Chemistry, Analytical

Exploratory Research on Sweetness Perception: Decision Trees to Study Electroencephalographic Data and Its Relationship with the Explicit Response to Sweet Odor, Taste, and Flavor

Elena Romeo-Arroyo et al.

Summary: Using implicit responses and self-reported data, this research aimed to study sweetness perception under different stimuli through artificial intelligence analytics. The results showed no clear relationship between explicit and implicit data, providing valuable insights for EEG research and data analysis, although there is still much to learn about properly utilizing implicit measurement technologies and their data.

SENSORS (2022)

Add to Collection

Article Food Science & Technology

Investigating the influence of monosodium L-glutamate on brain responses via scalp-electroencephalogram (scalp-EEG)

Ben Wu et al.

Summary: This study used EEG technology to investigate the responsive regions of the brain to umami taste. The results showed that the most responsive frequency to umami taste was 2 Hz, and the most responsive brain regions were T4CzA2, F8CzA2, and Fp2CzA2. The study also found higher sensitivity to umami taste in the right brain region. This research provides potential for further exploring the relevance between different brain responses to umami taste.

FOOD SCIENCE AND HUMAN WELLNESS (2022)

Add to Collection

Article Chemistry, Analytical

Qualitative Recognition of Primary Taste Sensation Based on Surface Electromyography

You Wang et al.

Summary: A novel recognition method based on sEMG signals was developed to distinguish six primary taste sensations in humans with an accuracy of 74.46%. Optimization of feature combination, electrode positions selection, and analysis of subject diversity can further improve the performance of the model.

SENSORS (2021)

Add to Collection

Article Engineering, Biomedical

Gustatory stimulus-based electroencephalogram signal classification

Kalyana Sundaram Chandran et al.

Summary: The Brain-Computer Interface provides real-time communication between the human brain and a personal computer for controlling external devices. This study utilizes taste composition-based EEG signal classification to differentiate between normal and reduced taste sensitivity. The EEG signal is pre-processed using FIR band pass filtering to reduce noise interference. The proposed method employs Discrete Wavelet Transform for feature extraction, analyzing alpha wave coefficients in the time domain to achieve high accuracy in gall bladder problem identification.

INTERNATIONAL JOURNAL OF BIOMEDICAL ENGINEERING AND TECHNOLOGY (2021)

Add to Collection

Article Biochemical Research Methods