FBANet: An Effective Data Mining Method for Food Olfactory EEG Recognition

ColorNet: An AI-based framework for pork freshness detection using a colorimetric sensor array

Pork freshness is crucial for flavour, nutrition and consumer health. The current colorimetric sensor array (CSA) detection systems face challenges related to high sensor development costs, low recognition accuracy and limitations in the platform use. Herein, we developed a CSA and ColorNet framework to detect pork freshness. The 53-point CSA was designed by selecting sensitised pH indicators and aldehyde/ketone indicators. To optimize the sensor, the Euclidean distance method was used to identify 24 array points with dyes that exhibited more sensitive responses. The ColorNet captured the color information of pork freshness, allowing real-time detection with a 99.5 % accuracy. For practical deployment and mobile applications, a refined 12-point CSA was developed using gradient activation mapping, maintaining a 99 % recognition rate, which is comparable with the 24-point CSA. The proposed CSA and model ensure consumer health and safety, providing strong technical support for quality monitoring and control in the pork industry.

TASA: Temporal Attention With Spatial Autoencoder Network for Odor-Induced Emotion Classification Using EEG

The olfactory system enables humans to smell different odors, which are closely related to emotions. The high temporal resolution and non-invasiveness of Electroencephalogram (EEG) make it suitable to objectively study human preferences for odors. Effectively learning the temporal dynamics and spatial information from EEG is crucial for detecting odor-induced emotional valence. In this paper, we propose a deep learning architecture called Temporal Attention with Spatial Autoencoder Network (TASA) for predicting odor-induced emotions using EEG. TASA consists of a filter-bank layer, a spatial encoder, a time segmentation layer, a Long Short-Term Memory (LSTM) module, a multi-head self-attention (MSA) layer, and a fully connected layer. We improve upon the previous work by utilizing a two-phase learning framework, using the autoencoder module to learn the spatial information among electrodes by reconstructing the given input with a latent representation in the spatial dimension, which aims to minimize information loss compared to spatial filtering with CNN. The second improvement is inspired by the continuous nature of the olfactory process; we propose to use LSTM-MSA in TASA to capture its temporal dynamics by learning the intercorrelation among the time segments of the EEG. TASA is evaluated on an existing olfactory EEG dataset and compared with several existing deep learning architectures to demonstrate its effectiveness in predicting olfactory-triggered emotional responses. Interpretability analyses with DeepLIFT also suggest that TASA learns spatial-spectral features that are relevant to olfactory-induced emotion recognition.

An ensemble model for predicting dispositions of emergency department patients

OBJECTIVE

The healthcare challenge driven by an aging population and rising demand is one of the most pressing issues leading to emergency department (ED) overcrowding. An emerging solution lies in machine learning's potential to predict ED dispositions, thus leading to promising substantial benefits. This study's objective is to create a predictive model for ED patient dispositions by employing ensemble learning. It harnesses diverse data types, including structured and unstructured information gathered during ED visits to address the evolving needs of localized healthcare systems.

METHODS

In this cross-sectional study, 80,073 ED patient records were amassed from a major southern Taiwan hospital in 2018-2019. An ensemble model incorporated structured (demographics, vital signs) and pre-processed unstructured data (chief complaints, preliminary diagnoses) using bag-of-words (BOW) and term frequency-inverse document frequency (TF-IDF). Two random forest base-learners for structured and unstructured data were employed and then complemented by a multi-layer perceptron meta-learner.

RESULTS

The ensemble model demonstrates strong predictive performance for ED dispositions, achieving an area under the receiver operating characteristic curve of 0.94. The models based on unstructured data encoded with BOW and TF-IDF yield similar performance results. Among the structured features, the top five most crucial factors are age, pulse rate, systolic blood pressure, temperature, and acuity level. In contrast, the top five most important unstructured features are pneumonia, fracture, failure, suspect, and sepsis.

CONCLUSIONS

Findings indicate that utilizing ensemble learning with a blend of structured and unstructured data proves to be a predictive method for determining ED dispositions.

Luteolin inhibits the JAK/STAT pathway to alleviate auditory cell apoptosis of acquired sensorineural hearing loss based on network pharmacology, molecular docking, molecular dynamics simulation, and experiments in vitro

PURPOSE

The study aimed to explore the mechanisms of luteolin in acquired sensorineural hearing loss (SNHL) through network pharmacology, molecular docking, molecular dynamics simulation, and experimental verification.

METHODS

First, the practices of network pharmacology were used to obtain the intersecting targets of luteolin and acquired SNHL, construct the PPI (Protein-Protein Interaction) network, conduct GO and KEGG enrichments, and establish luteolin-acquired SNHL-target-pathway network, aiming to gain the core targets and pathways. Then, the affinity between the core targets and luteolin was verified by molecular docking. Moreover, molecular dynamics (MD) simulation was applied to simulate the binding between targets and luteolin. Finally, with the HEI-OC1 cell line, some molecular biology techniques were adopted to verify the pharmacological actions of luteolin and the significance of the pathway from KEGG enrichment in luteolin-protecting auditory cell damage related to acquired SNHL.

RESULTS

14 intersecting targets were obtained, and the 10 core targets were further verified through molecular docking and MD simulation to get 5 core targets. The JAK/STAT was selected as the critical pathway through KEGG enrichment. Luteolin could dose-dependently alleviate auditory cell apoptosis by inhibiting the JAK/STAT pathway, confirmed by a series of experiments in vitro.

CONCLUSION

This study manifested that luteolin could reduce acquired SNHL-related auditory cell apoptosis through the JAK/STAT pathway, which provided a new idea for acquired SNHL pharmacological treatment.