A dual alignment-based multi-source domain adaptation framework for motor imagery EEG classification.

Domain adaptation, as an important branch of transfer learning, can be applied to cope with data insufficiency and high subject variabilities in motor imagery electroencephalogram (MI-EEG) based brain-computer interfaces. The existing methods generally focus on aligning data and feature distribution; however, aligning each source domain with the informative samples of the target domain and seeking the most appropriate source domains to enhance the classification effect has not been considered. In this paper, we propose a dual alignment-based multi-source domain adaptation framework, denoted DAMSDAF. Based on continuous wavelet transform, all channels of MI-EEG signals are converted respectively and the generated time-frequency spectrum images are stitched to construct multi-source domains and target domain. Then, the informative samples close to the decision boundary are found in the target domain by using entropy, and they are employed to align and reassign each source domain with normalized mutual information. Furthermore, a multi-branch deep network (MBDN) is designed, and the maximum mean discrepancy is embedded in each branch to realign the specific feature distribution. Each branch is separately trained by an aligned source domain, and all the single branch transfer accuracies are arranged in descending order and utilized for weighted prediction of MBDN. Therefore, the most suitable number of source domains with top weights can be automatically determined. Extensive experiments are conducted based on 3 public MI-EEG datasets. DAMSDAF achieves the classification accuracies of 92.56%, 69.45% and 89.57%, and the statistical analysis is performed by the kappa value and t-test. Experimental results show that DAMSDAF significantly improves the transfer effects compared to the present methods, indicating that dual alignment can sufficiently use the different weighted samples and even source domains at different levels as well as realizing optimal selection of multi-source domains.

Augmented autophagy suppresses thymocytes development via Bcl10/p-p65 pathway in prenatal nicotine exposed fetal mice.

Tobacco smoke is a common global environmental pollutant. Maternal tobacco smoke/nicotine exposure has long-term toxic effects on immune organs. We previously found that prenatal nicotine exposure (PNE)-induced programmed immune diseases caused by fetal thymic hypoplasia, but the mechanism still unknown. Autophagy has important functions in maintaining thymopoiesis, whether autophagy was involved in PNE-inhibited fetal thymocytes development is also obscure. Therefore, this study aimed to investigate how nicotine changed the development of fetal thymocytes from the perspective of autophagy in vivo and in vitro. PNE model was established by 3 mg/kg nicotine administration in Balb/c mice from gestational day 9 to 18. The results showed that PNE reduced the percentage and absolute number of CD69-CD4+SP cells, suggesting a block of fetal thymocytes mature. PNE promoted autophagosome formation, autophagy related proteins (Beclin1, LC3I/II) expression, and upregulated α7 nAChR as well as AMPK phosphorylation in fetal thymus. Moreover, PNE promoted Bcl10 degradation via autophagy-mediated proteolysis and inhibited p65 activation, blocking the transition of thymocytes between the DP to SP stage. Further, primary thymocytes were treated with nicotine in vitro and showed induced autophagy in a dose- and time-dependent manner. In addition, nicotine-inhibited CD69-CD4+SP cells and the Bcl10/p-p65 pathway have been reversed by an autophagy inhibitor. The α7 nAChR specific antagonist abrogated nicotine-induced AMPK phosphorylation and autophagy initiation. In conclusion, our findings showed that PNE repressed the Bcl10/p-p65 development pathway of CD4+SP cells by triggering autophagy, and illuminated the developmental origin mechanism of programmed immune diseases in PNE offspring.

Protective effect of YHI and HHI-I against experimental acute pancreatitis in rabbits.

AIM:To observe the protective effect of combined i.v. administraction of Yuanhu injection (YHI) and Huoxuehuayu injection-I (HHI-I) against acute pancreatitis (AP) in rabbits.METHODS:Sever acute pancreatitis (SAP) was induced by retrograde infusion of artificial bile juice into biliary-pancreatic duct, and treated with YHI and HHI-I intravenously. The protective effect was judged by the survival time and rate, serum amylase, serum interleukin-6, pancreatic microcirculation and pathological alteration.RESULTS:Combined use of YHI and HHI-I could markedly increase the rabbits' 5-day survival rate after AP (83.3% in the treatment group and 33.3% in control). The serum amylase value (x-± s) decreased to 1596.6U/L± 760.50U/L in the 5th day from the high level (6320.83U/L± 2614.12U/L) in the 1st day after AP in the treatment group, while in the control group the amylase activity in the 5th day was 2095.0U/L± 1081.87U/L, being significantly different from that before AP (837.17U/L± 189.12U/L). YHI and HHI-I also obviously improved the pancreatic microcirculation and lowered the serum interleukin-6 level, one of the indices of severe pancreatitis. Pathological examination indicated all the changes typical for AP in YHI and HHI-I treatment group were milder than those in the control.CONCLUSION:YHI and HHI-I used in combination might have protective effect against acute pancreatitis in rabbits.