Semi-Supervised Cross-Subject Emotion Recognition Based on Stacked Denoising Autoencoder Architecture Using a Fusion of Multi-Modal Physiological Signals

In recent decades, emotion recognition has received considerable attention. As more enthusiasm has shifted to the physiological pattern, a wide range of elaborate physiological emotion data features come up and are combined with various classifying models to detect one’s emotional states. To circumvent the labor of artificially designing features, we propose to acquire affective and robust representations automatically through the Stacked Denoising Autoencoder (SDA) architecture with unsupervised pre-training, followed by supervised fine-tuning. In this paper, we compare the performances of different features and models through three binary classification tasks based on the Valence-Arousal-Dominance (VAD) affection model. Decision fusion and feature fusion of electroencephalogram (EEG) and peripheral signals are performed on hand-engineered features; data-level fusion is performed on deep-learning methods. It turns out that the fusion data perform better than the two modalities. To take advantage of deep-learning algorithms, we augment the original data and feed it directly into our training model. We use two deep architectures and another generative stacked semi-supervised architecture as references for comparison to test the method’s practical effects. The results reveal that our scheme slightly outperforms the other three deep feature extractors and surpasses the state-of-the-art of hand-engineered features.     

Space-Air-Ground Integrated Mobile Crowdsensing for Partially Observable Data Collection by Multi-Scale Convolutional Graph Reinforcement Learning

Mobile crowdsensing (MCS) is attracting considerable attention in the past few years as a new paradigm for large-scale information sensing. Unmanned aerial vehicles (UAVs) have played a significant role in MCS tasks and served as crucial nodes in the newly-proposed space-air-ground integrated network (SAGIN). In this paper, we incorporate SAGIN into MCS task and present a Space-Air-Ground integrated Mobile CrowdSensing (SAG-MCS) problem. Based on multi-source observations from embedded sensors and satellites, an aerial UAV swarm is required to carry out energy-efficient data collection and recharging tasks. Up to date, few studies have explored such multi-task MCS problem with the cooperation of UAV swarm and satellites. To address this multi-agent problem, we propose a novel deep reinforcement learning (DRL) based method called Multi-Scale Soft Deep Recurrent Graph Network (ms-SDRGN). Our ms-SDRGN approach incorporates a multi-scale convolutional encoder to process multi-source raw observations for better feature exploitation. We also use a graph attention mechanism to model inter-UAV communications and aggregate extra neighboring information, and utilize a gated recurrent unit for long-term performance. In addition, a stochastic policy can be learned through a maximum-entropy method with an adjustable temperature parameter. Specifically, we design a heuristic reward function to encourage the agents to achieve global cooperation under partial observability. We train the model to convergence and conduct a series of case studies. Evaluation results show statistical significance and that ms-SDRGN outperforms three state-of-the-art DRL baselines in SAG-MCS. Compared with the best-performing baseline, ms-SDRGN improves 29.0% reward and 3.8% CFE score. We also investigate the scalability and robustness of ms-SDRGN towards DRL environments with diverse observation scales or demanding communication conditions.     

An Algorithm Framework for Drug-Induced Liver Injury Prediction Based on Genetic Algorithm and Ensemble Learning

In the process of drug discovery, drug-induced liver injury (DILI) is still an active research field and is one of the most common and important issues in toxicity evaluation research. It directly leads to the high wear attrition of the drug. At present, there are a variety of computer algorithms based on molecular representations to predict DILI. It is found that a single molecular representation method is insufficient to complete the task of toxicity prediction, and multiple molecular fingerprint fusion methods have been used as model input. In order to solve the problem of high dimensional and unbalanced DILI prediction data, this paper integrates existing datasets and designs a new algorithm framework, Rotation-Ensemble-GA (R-E-GA). The main idea is to find a feature subset with better predictive performance after rotating the fusion vector of high-dimensional molecular representation in the feature space. Then, an Adaboost-type ensemble learning method is integrated into R-E-GA to improve the prediction accuracy. The experimental results show that the performance of R-E-GA is better than other state-of-art algorithms including ensemble learning-based and graph neural network-based methods. Through five-fold cross-validation, the R-E-GA obtains an ACC of 0.77, an F1 score of 0.769, and an AUC of 0.842.     

A Novel Strategy for Regulating mRNA’s Degradation via Interfering the AUF1’s Binding to mRNA

The study on the mechanism and kinetics of mRNA degradation provides a new vision for chemical intervention on protein expression. The AU enrichment element (ARE) in mRNA 3′-UTR can be recognized and bound by the ARE binding protein (AU-rich Element factor (AUF1) to recruit RNase for degradation. In the present study, we proposed a novel strategy for expression regulation that interferes with the AUF1-RNA binding. A small-molecule compound, JNJ-7706621, was found to bind AUF1 protein and inhibit mRNA degradation by screening the commercial compound library. We discovered that JNJ-7706621 could inhibit the expression of AUF1 targeted gene IL8, an essential pro-inflammatory factor, by interfering with the mRNA homeostatic state. These studies provide innovative drug design strategies to regulate mRNA homeostasis.     

A Comprehensive Review of Rosmarinic Acid: From Phytochemistry to Pharmacology and Its New Insight

Polyphenolic acids are the widely occurring natural products in almost each herbal plant, among which rosmarinic acid (RA, C₁₈H₁₆O₈) is well-known, and is present in over 160 species belonging to many families, especially the Lamiaceae. Aside from this herbal ingredient, dozens of its natural derivatives have also been isolated and characterized from many natural plants. In recent years, with the increasing focus on the natural products as alternative treatments, a large number of pharmacological studies have been carried out to demonstrate the various biological activities of RA such as anti-inflammation, anti-oxidation, anti-diabetes, anti-virus, anti-tumor, neuroprotection, hepatoprotection, etc. In addition, investigations concerning its biosynthesis, extraction, analysis, clinical applications, and pharmacokinetics have also been performed. Although many achievements have been made in various research aspects, there still exist some problems or issues to be answered, especially its toxicity and bioavailability. Thus, we hope that in the case of natural products, the present review can not only provide a comprehensive understanding on RA covering its miscellaneous research fields, but also highlight some of the present issues and future perspectives worth investigating later, in order to help us utilize this polyphenolic acid more efficiently, widely, and safely.     

Development of a ~3He Gas Filling Station at the China Spallation Neutron Source

At the China Spallation Neutron Source(CSNS), we have developed a custom gas-filling station, a glassblowing workshop, and a spin-exchange optical pumping(SEOP) system for producing high-quality ~3He-based neutron spin filter(NSF) cells. The gas-filling station is capable of routinely filling ~3He cells made from GE180 glass of various dimensions, to be used as neutron polarizers and analyzers on beamlines at the CSNS. Performance tests on cells fabricated at our gas-filling station are conducted via neutron transmission and nuclear-magneticresonance measurements, revealing nominal filling pressures, and a saturated ~3He polarization in the region of 80%, with a lifetime of approximately 240 hours. These results demonstrate our ability to produce competitive NSF cells to meet the ever-increasing research needs of the polarized neutron research community.     

Spider Silk-Improved Quartz-Enhanced Conductance Spectroscopy for Medical Mask Humidity Sensing

Spider silk is one of the hottest biomaterials researched currently, due to its excellent mechanical properties. This work reports a novel humidity sensing platform based on a spider silk-modified quartz tuning fork (SSM-QTF). Since spider silk is a kind of natural moisture-sensitive material, it does not demand additional sensitization. Quartz-enhanced conductance spectroscopy (QECS) was combined with the SSM-QTF to access humidity sensing sensitively. The results indicate that the resonance frequency of the SSM-QTF decreased monotonously with the ambient humidity. The detection sensitivity of the proposed SSM-QTF sensor was 12.7 ppm at 1 min. The SSM-QTF sensor showed good linearity of ~0.99. Using this sensor, we successfully measured the humidity of disposable medical masks for different periods of wearing time. The results showed that even a 20 min wearing time can lead to a >70% humidity in the mask enclosed space. It is suggested that a disposable medical mask should be changed <2 h.     

Characterization of Roasting Time on Sensory Quality,Color, Taste,and Nonvolatile Compounds of Yuan An Yellow Tea

Roasting is crucial for producing Yuan An yellow tea (YAYT) as it substantially affects sensory quality. However, the effect of roasting time on YAYT flavor quality is not clear. To investigate the effect of roasting time on the sensory qualities, chemical components, odor profiles, and metabolic profile of YAYTs produced with 13 min roasting, 16 min roasting, 19 min roasting, 22 min roasting, and 25 min roasting were determined. The YAYTs roasted for 22 min got higher sensory scores and better chemical qualities, such as the content of gallocatechin (GC), gallocatechin gallate (GCG), free amino acids, solutable sugar, meanwhile the lightness decreased, the hue of tea brew color (b) increased, which meant the tea brew got darker and yellower. YAYTs roasted for 22 min also increased the contents of key odorants, such as benzaldehyde, nonanal, β-cyclocitral, linalool, nerol, α-cedrol, β-ionone, limonene, 2-methylfuran, indole, and longiborneol. Moreover, non-targeted metabolomics identified up to 14 differentially expressed metabolites through pair-wise comparisons, such as flavonoids, phenolic acids, sucrose, and critical metabolites, which were the main components corresponding to YAYT roasted for 22 min. In summary, the current results provide scientific guidance for the production of high quality YAYT.     

Mulberry Ethanol Extract and Rutin Protect Alcohol-Damaged GES-1 Cells by Inhibiting the MAPK Pathway

Mulberry extract has been proven to have the effect of resisting alcohol damage, but its mechanism is still unclear. In this study, the composition of mulberry ethanol extract (MBE) was identified by LC-MS/MS and the main components of MBE were ascertained by measuring. Gastric mucosal epithelial (GES-1) cells were used to elucidate the mechanism of MBE and rutin (the central part of MBE) helped protect against alcohol damage. The results revealed that phenolics accounted for the majority of MBE, accounting for 308.6 mg/g gallic acid equivalents and 108 substances were identified, including 37 flavonoids and 50 non-flavonoids. The treatment of 400 μg/mL MBE and 320 μM rutin reduced early cell apoptosis and the content of intracellular reactive oxygen species, malondialdehyde and increased glutathione. The qPCR results indicated that the MBE inhibits the expression of genes in the mitogen-activated protein kinase (MAPK) pathway, including p38, JNK, ERK and caspase-3; rutin inhibits the expression of p38 and caspase-3. Overall, MBE was able to reduce the oxidative stress of GES-1 cells and regulated apoptosis-related genes of the MAPK pathway. This study provides information for developing anti-ethanol injury drugs or functional foods.     

Electronic structure of strongly correlated systems: recent developments in multiconfiguration pair-density functional theory and multiconfiguration nonclassical-energy functional theory

Strong electron correlation plays an important role in transition-metal and heavy-metal chemistry, magnetic molecules, bond breaking, biradicals, excited states, and many functional materials, but it provides a significant challenge for modern electronic structure theory. The treatment of strongly correlated systems usually requires a multireference method to adequately describe spin densities and near-degeneracy correlation. However, quantitative computation of dynamic correlation with multireference wave functions is often difficult or impractical. Multiconfiguration pair-density functional theory (MC-PDFT) provides a way to blend multiconfiguration wave function theory and density functional theory to quantitatively treat both near-degeneracy correlation and dynamic correlation in strongly correlated systems; it is more affordable than multireference perturbation theory, multireference configuration interaction, or multireference coupled cluster theory and more accurate for many properties than Kohn–Sham density functional theory. This perspective article provides a brief introduction to strongly correlated systems and previously reviewed progress on MC-PDFT followed by a discussion of several recent developments and applications of MC-PDFT and related methods, including localized-active-space MC-PDFT, generalized active-space MC-PDFT, density-matrix-renormalization-group MC-PDFT, hybrid MC-PDFT, multistate MC-PDFT, spin–orbit coupling, analytic gradients, and dipole moments. We also review the more recently introduced multiconfiguration nonclassical-energy functional theory (MC-NEFT), which is like MC-PDFT but allows for other ingredients in the nonclassical-energy functional. We discuss two new kinds of MC-NEFT methods, namely multiconfiguration density coherence functional theory and machine-learned functionals.

This feature article overviews recent work on active spaces, matrix product reference states, treatment of quasidegeneracy, hybrid theory, density-coherence functionals, machine-learned functionals, spin–orbit coupling, gradients, and dipole moments.