Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module.

Because of its ability to objectively reflect people's emotional states, electroencephalogram (EEG) has been attracting increasing research attention for emotion classification. The classification method based on spatial-domain analysis is one of the research hotspots. However, most previous studies ignored the complementarity of information between different frequency bands, and the information in a single frequency band is not fully mined, which increases the computational time and the difficulty of improving classification accuracy. To address the above problems, this study proposes an emotion classification method based on dynamic simplifying graph convolutional (SGC) networks and a style recalibration module (SRM) for channels, termed SGC-SRM, with multi-band EEG data as input. Specifically, first, the graph structure is constructed using the differential entropy characteristics of each sub-band and the internal relationship between different channels is dynamically learned through SGC networks. Second, a convolution layer based on the SRM is introduced to recalibrate channel features to extract more emotion-related features. Third, the extracted sub-band features are fused at the feature level and classified. In addition, to reduce the redundant information between EEG channels and the computational time, (1) we adopt only 12 channels that are suitable for emotion classification to optimize the recognition algorithm, which can save approximately 90.5% of the time cost compared with using all channels; (2) we adopt information in the θ, α, ß, and γ bands, consequently saving 23.3% of the time consumed compared with that in the full bands while maintaining almost the same level of classification accuracy. Finally, a subject-independent experiment is conducted on the public SEED dataset using the leave-one-subject-out cross-validation strategy. According to experimental results, SGC-SRM improves classification accuracy by 5.51-15.43% compared with existing methods.

EEG Emotion Classification Network Based on Attention Fusion of Multi-Channel Band Features.

Understanding learners' emotions can help optimize instruction sand further conduct effective learning interventions. Most existing studies on student emotion recognition are based on multiple manifestations of external behavior, which do not fully use physiological signals. In this context, on the one hand, a learning emotion EEG dataset (LE-EEG) is constructed, which captures physiological signals reflecting the emotions of boredom, neutrality, and engagement during learning; on the other hand, an EEG emotion classification network based on attention fusion (ECN-AF) is proposed. To be specific, on the basis of key frequency bands and channels selection, multi-channel band features are first extracted (using a multi-channel backbone network) and then fused (using attention units). In order to verify the performance, the proposed model is tested on an open-access dataset SEED (N = 15) and the self-collected dataset LE-EEG (N = 45), respectively. The experimental results using five-fold cross validation show the following: (i) on the SEED dataset, the highest accuracy of 96.45% is achieved by the proposed model, demonstrating a slight increase of 1.37% compared to the baseline models; and (ii) on the LE-EEG dataset, the highest accuracy of 95.87% is achieved, demonstrating a 21.49% increase compared to the baseline models.

An Improved Tiered Head Pose Estimation Network with Self-Adjust Loss Function.

As an important task in computer vision, head pose estimation has been widely applied in both academia and industry. However, there remains two challenges in the field of head pose estimation: (1) even given the same task (e.g., tiredness detection), the existing algorithms usually consider the estimation of the three angles (i.e., roll, yaw, and pitch) as separate facets, which disregard their interplay as well as differences and thus share the same parameters for all layers; and (2) the discontinuity in angle estimation definitely reduces the accuracy. To solve these two problems, a THESL-Net (tiered head pose estimation with self-adjust loss network) model is proposed in this study. Specifically, first, an idea of stepped estimation using distinct network layers is proposed, gaining a greater freedom during angle estimation. Furthermore, the reasons for the discontinuity in angle estimation are revealed, including not only labeling the dataset with quaternions or Euler angles, but also the loss function that simply adds the classification and regression losses. Subsequently, a self-adjustment constraint on the loss function is applied, making the angle estimation more consistent. Finally, to examine the influence of different angle ranges on the proposed model, experiments are conducted on three popular public benchmark datasets, BIWI, AFLW2000, and UPNA, demonstrating that the proposed model outperforms the state-of-the-art approaches.

Mechanisms of chitosan-coated poly(lactic-co-glycolic acid) nanoparticles for improving oral absorption of 7-ethyl-10-hydroxycamptothecin.

Chitosan-modified poly(lactic-co-glycolic acid) nanoparticles (CHI/PLGA NPs) loaded with 7-ethyl-10-hydroxycamptothecin (SN-38), named CHI/PLGA/SN-38 NPs, were successfully prepared using an oil-in-water (O/W) solvent evaporation method. The physicochemical properties of the novel NPs were characterized by DLS, Zeta potential, SEM, DSC, XRD, and FTIR. The encapsulation efficiency and drug loading content were 71.83 (±2.77)% and 6.79 (±0.26)%, respectively. In vitro drug release in the simulated gastric juice was lower than that in the intestinal juice. In situ single-pass intestinal perfusion (SPIP) studies indicated a dramatic improvement of drug absorption as a result of the synergistic effect between CHI and PLGA on P-glycoprotein (Pgp) inhibition. CHI/PLGA NPs showed high cellular uptake and low efflux for drugs in Caco-2 cells. The cytotoxicity studies revealed that CHI/PLGA NPs had a transient effect on the membrane integrity, but did not have an influence on cell viability. Based on the in vitro release studies, SPIP, and intracellular drug accumulation and transport investigations, we speculate rationally that CHI/PLGA NPs were mainly internalized in the form of intact NPs, thus escaping the recognition of enterocyte Pgp and avoiding efflux into the apical part of the enterocytes. After partial release of drugs inside the enterocytes, CHI/PLGA interfered with the microenvironment of Pgp and further weakened the Pgp-mediated efflux. Then, the drug-loaded NPs exited via the exocytose effect from the basal part of the enterocytes and entered the blood circulation. These results showed that CHI/PLGA NPs would be smart oral delivery carriers for antineoplastic agents that are also Pgp substrates.

TPGS2k/PLGA nanoparticles for overcoming multidrug resistance by interfering mitochondria of human alveolar adenocarcinoma cells.

In this study, we successfully synthesized d-α-tocopheryl polyethylene glycol 2000 succinate (TPGS2k) and prepared TPGS2k-modified poly(lactic-co-glycolic acid) nanoparticles (TPGS2k/PLGA NPs) loaded with 7-ethyl-10-hydroxycamptothecin (SN-38), designated TPGS2k/PLGA/SN-38 NPs. Characterization measurements showed that TPGS2k/PLGA/SN-38 NPs displayed flat and spheroidal particles with diameters of 80-104 nm. SN-38 was encapsulated in TPGS2k emulsified PLGA NPs with the entrapment efficiency and loading rates of SN-38 83.6 and 7.85%, respectively. SN-38 could release constantly from TPGS2k/PLGA/SN-38 NPs in vitro. TPGS2k/PLGA/SN-38 NPs induced significantly higher cytotoxicity on A549 cells and the multidrug resistance (MDR) cell line (A549/DDP cells and A549/Taxol cells) compared with free SN-38. Further studies on the mechanism of the NPs in increasing the death of MDR cells showed that following the SN-38 releasing into cytoplasm the remaining TPGS2k/PLGA NPs could reverse the P-gp mediated MDR via interfering with the structure and function of mitochondria and rather than directly inhibiting the enzymatic activity of P-gp ATPase. Therefore, TPGS2k/PLGA NPs can reduce the generation of ATP and the release of energy for the requisite of P-gp efflux transporters. The results indicated that TPGS2k/PLGA NPs could become the nanopharmaceutical materials with the capability to reversal MDR and improve anticancer effects of some chemotherapy drugs as P-gp substrates.

Hydroxypropyl-sulfobutyl-ß-cyclodextrin improves the oral bioavailability of edaravone by modulating drug efflux pump of enterocytes.

The objective of the study was to evaluate the effect of hydroxypropyl-sulfobutyl-ß-cyclodextrin (HP-SBE-ßCD) on the bioavailability and intestinal absorption of edaravone, and identify its mechanism of action. We devised HP-SBE-ßCD as a carrier and modulator of P-glycoprotein (Pgp) efflux pump, and edaravone as a model drug, and prepared edaravone/HP-SBE-ßCD inclusion complex. HP-SBE-ßCD improved the water solubility and enhanced the bioavailability of edaravone by 10.3-fold in rats. Then, in situ single-pass intestinal perfusion showed that HP-SBE-ßCD had an effect of improving the permeability and inhibiting the efflux of edaravone. Furthermore, the effects of HP-SBE-ßCD on Pgp were achieved through interfering with the lipid raft and depleting the cholesterol of enterocytes membrane. From the results, we presented the novel mechanisms. First, edaravone/HP-SBE-ßCD had a lower release from the inclusion compound to protect edaravone from the low pH of the stomach. Then, HP-SBE-ßCD modulated the membrane microenvironment of intestinal absorption epithelial cells. At last, the result was that HP-SBE-ßCD enhanced the absorption of edaravone by interfering with Pgp. In conclusion, HP-SBE-ßCD improves the bioavailability of drug not only because of its enhancing water solubility of the drug, but also because it modulates the Pgp-mediated efflux from enterocytes.

Food emulsifier polysorbate 80 increases intestinal absorption of di-(2-ethylhexyl) phthalate in rats.

The aim of the present research was to explore whether food emulsifier polysorbate 80 can enhance the absorption of di-(2-ethylhexyl) phthalate (DEHP) and its possible mechanism. We established the high-performance liquid chromatography (HPLC) method for detecting DEHP and its major metabolite, mono-ethylhexyl phthalate (MEHP) in rat plasma, and then examined the toxicokinetic and bioavailability of DEHP with or without polysorbate 80 in rats. The study of its mechanism to increase the absorption of phthalates demonstrated that polysorbate 80 can induce mitochondrial dysfunction in time- and concentration-dependence manners in Caco-2 cells by reducing mitochondrial membrane potential, diminishing the production of the adenosine triphosphate, and decreasing the activity of electron transport chain. Our results indicated that food emulsifier applied in relatively high concentrations in even the most frequently consumed foods can increase the absorption of DEHP, and its role may be related to the structure and function damages of mitochondria in enterocytes.